ICCV2019 全部論文分類彙總（含目標檢測 / 圖像分割等，1008 更新中）

作爲計算機視覺領域三大頂會之一，ICCV2019目前已公佈了所有接收論文ID（會議接收論文1077篇，總提交4303篇，25%的接收率），相關報道：1077篇！ICCV2019接收結果公佈，你中了嗎？

此前我們也對CVPR2019的論文做了分類彙總：CVPR2019 | 論文分類彙總，而本帖是對ICCV2019頂會論文的實時跟進和分類，歡迎點擊文末關注按鈕，即可獲取本帖最新更新消息。
 

• ICCV2019接收論文ID
• Github論文彙總開源項目
• ICCV2019論文分類彙總
• ICCV2019論文解讀彙總
• ICCV2019論文下載及接收ID文檔
  鏈接：https://pan.baidu.com/s/1qiuXHYFAJRzpbsW90a8pGA
  提取碼：提示：此內容登錄後可查看
  
   

 

目錄

目標檢測
語義分割
圖像分割

目標跟蹤
人臉
ReID
OCR
視頻
超分辨率
自動駕駛
3D、點雲
GCN
GAN
其他
（以計算機視覺具體研究方向劃分，如有錯誤歡迎指出~）

目標檢測

1、ThunderNet: Towards Real-time Generic Object Detection
ThunderNet：走向實時通用目標檢測
作者：Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, Jian Sun
論文鏈接：https://arxiv.org/abs/1903.11752
論文解讀：http://bbs.cvmart.net/articles/361


2、MemorizingNormality to Detect Anomaly: Memory-augmented Deep Autoencoder (MemAE) forUnsupervised Anomaly Detection
MemorizingNormality檢測異常：內存增強深度自動編碼器（MemAE）用於非監督異常檢測
作者：Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, Anton van den Hengel
項目鏈接：https://donggong1.github.io/anomdec-memae.html
論文鏈接：https://arxiv.org/abs/1904.02639
GitHub：https://github.com/donggong1/memae-anomaly-detection


3、Deep Hough Voting for 3D Object Detection in Point Clouds（Oral）
深入投票進行點雲中的三維目標檢測
作者：Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas
論文鏈接：https://arxiv.org/abs/1904.09664


4、Multi-adversarial Faster-RCNN for Unrestricted Object Detection
用於無限制目標檢測的多對抗性更快RCNN
作者：Zhenwei He, Lei Zhang
論文鏈接：https://arxiv.org/abs/1907.10343


5、FCOS: Fully Convolutional One-Stage Object Detection
FCOS：完全卷積一級目標檢測
作者：Zhi Tian, Chunhua Shen, Hao Chen, Tong He
論文鏈接：https://arxiv.org/abs/1904.01355
Github鏈接：https://github.com/tianzhi0549/FCOS/
論文解讀： https://mp.weixin.qq.com/s/N93TrVnUuvAgfcoHXevTHw


6、Simultaneous multi-view instance detection with learned geometric soft-constraints
使用學習的幾何軟約束同時進行多視圖實例檢測
作者：Ahmed Samy Nassar, Sebastien Lefevre, Jan D. Wegner
論文鏈接：https://arxiv.org/abs/1907.10892


7、Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Cap2Det：學習放大目標檢測的弱字幕監控
作者：Keren Ye, Mingda Zhang, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent
論文鏈接：https://arxiv.org/abs/1907.10164


8、Towards Adversarially Robust Object Detection
對抗強大的目標檢測
作者：Haichao Zhang, Jianyu Wang
論文鏈接：https://arxiv.org/abs/1907.10310


9、Few-shot Object Detection via Feature Reweighting
通過特徵重新加權的快速物體檢測
作者：Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell
論文鏈接：https://arxiv.org/pdf/1812.01866.pdf


10、Optimizing the F-measure for Threshold-free Salient Object Detection
優化無閾值顯着物體檢測的F-測量
作者：Kai Zhao, Shanghua Gao, Wenguan Wang, Ming-ming Cheng
論文鏈接：http://data.kaizhao.net/publications/iccv2019fmeasure.pdf
Github鏈接：https://github.com/zeakey/iccv2019-fmeasure
項目鏈接：http://kaizhao.net/fmeasure


11、Depth-induced Multi-scale Recurrent Attention Network for Saliency Detection
深度誘導多尺度重複注意網絡用於顯著性檢測
作者：Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu
Github鏈接：https://github.com/jiwei0921/DMRA_RGBD-SOD


10、Learning Lightweight Lane Detection CNNs by Self Attention Distillation
通過自注意蒸餾學習輕量級車道檢測神經網絡
作者：Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy
論文鏈接：https://arxiv.org/abs/1908.00821
Github鏈接：https://github.com/cardwing/Codes-for-Lane-Detection


11、Towards High-Resolution Salient Object Detection
實現高分辨率突出目標檢測
作者：Yi Zeng, Pingping Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu
論文鏈接：https://arxiv.org/abs/1908.07274
Github鏈接：https://github.com/yi94code/HRSOD


12、Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
教師指導學生如何從部分標記的圖像中學習識別面部地標
作者：Xuanyi Dong, Yi Yang
論文鏈接：https://arxiv.org/abs/1908.02116
Github鏈接：https://github.com/D-X-Y/landmark-detection


13、Temporally-Aggregating Spatial Encoder-Decoder for Video Saliency Detection
用於視頻顯著性檢測的時間聚合空間編解碼器
Github鏈接：https://github.com/kylemin/TASED-Net


14、SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
SCRDet：對小的，雜亂的和旋轉的物體進行更加穩健的檢測
作者：Xue Yang, Jirui Yang, Junchi Yan, Yue Zhang, Tengfei Zhang, Zhi Guo, Sun Xian, Kun Fu
論文鏈接：https://arxiv.org/abs/1811.07126
Github鏈接：https://github.com/DetectionTeamUCAS


15、Clustered Object detection in aerial images
航拍圖像中的聚類物體檢測
作者：Fan Yang, Heng Fan, Peng Chu, Erik Blasch, Haibin Ling
論文鏈接：https://arxiv.org/pdf/1904.08008


16、Relation Distillation Networks for Video Object Detection
用於視頻對象檢測的關聯蒸餾網絡
作者： Jiajun Deng, Yingwei Pan, Ting Yao, Wengang Zhou, Houqiang Li, Tao Mei
論文鏈接：https://arxiv.org/abs/1908.09511


17、Scaling Object Detection by Transferring Classification Weights
通過轉移分類權值來縮放目標檢測
作者：Jason Kuen, Federico Perazzi, Zhe Lin, Jianming Zhang, Yap-Peng Tan
論文鏈接：https://arxiv.org/abs/1909.06804
Github鏈接：https://github.com/xternalz/AE-WTN


18、WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
WSOD^2:學習自底向上和自頂向下的對象精餾，用於弱監督對象檢測
作者：Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, Lei Zhang
論文鏈接：https://arxiv.org/abs/1909.04972

圖像分割

1、Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
用RGBD傳感進行語義分割的增量類發現
作者：Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito, Kris Kitani
論文鏈接：https://arxiv.org/abs/1907.10008


2、TensorMask: A Foundation for Dense Object Segmentation
TensorMask：密集對象分割的基礎
作者：Xinlei Chen, Ross Girshick, Kaiming He, and Piotr Dollár
論文鏈接：https://arxiv.org/abs/1903.12174


3、Orientation-aware Semantic Segmentation on Icosahedron Spheres
二十面體球面上的方向感知語義分割
作者：Chao Zhang, Stephan Liwicki, William Smith, Roberto Cipolla
論文鏈接：https://arxiv.org/abs/1907.12849


4、Expectation-Maximization Attention Networks for Semantic Segmentation (Oral)
語義分割的期望最大化注意網絡
作者： Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu
論文鏈接：https://arxiv.org/abs/1907.13426


5、ACE: Adapting to Changing Environments for Semantic Segmentation
ACE：適應不斷變化的環境進行語義分割
作者：Zuxuan Wu, Xin Wang, Joseph E. Gonzalez, Tom Goldstein, Larry S. Davis
論文鏈接：https://arxiv.org/pdf/1904.06268.pdf


6、CCNet: Criss-Cross Attention for Semantic Segmentation
CCNet:交叉關注語義分割
作者：Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, Wenyu Liu
論文鏈接：https://arxiv.org/abs/1811.11721
Github鏈接：https://github.com/speedinghzl/CCNet


7、SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
SemanticKITTI:一個用於激光雷達序列語義場景理解的數據集
作者：J. Behley, M. Garbade, A. Milioto, J. Quenzel, S. Behnke, C. Stachniss, and J. Gall
論文鏈接：https://arxiv.org/abs/1904.01416


8、DADA: Depth-Aware Domain Adaptation in Semantic Segmentation
作者：Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Pérez
論文鏈接：https://arxiv.org/abs/1904.01886


9、Weakly Supervised Energy-Based Learning for Action Segmentation（Oral）
弱監督能源行動學習分割
Github鏈接：https://github.com/JunLi-Galios/CDFL


10、Explicit Shape Encoding for Real-Time Instance Segmentation
實時實例分割的顯式形狀編碼
作者：Wenqiang Xu, Haiyang Wang, Fubo Qi, Cewu Lu
論文鏈接：https://arxiv.org/abs/1908.04067


11、ACFNet: Attentional Class Feature Network for Semantic Segmentation
用於語義分割的注意類特徵網絡
作者：Fan Zhang, Yanqin Chen, Zhihang Li, Zhibin Hong, Jingtuo Liu, Feifei Ma, Junyu Han, Errui Ding
論文鏈接：https://arxiv.org/abs/1909.09408


12、Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
層次式點-邊交互網絡用於點雲語義分割
作者：Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia
論文鏈接：https://arxiv.org/abs/1909.10469


13、SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
SSAP:帶有親緣金字塔的單點實例分割
作者：Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, Kaiqi Huang
論文鏈接：https://arxiv.org/abs/1909.01616

姿態估計

1、Ego-Pose Estimation and Forecasting as Real-Time PD Control
Ego-Pose估計和預測作爲實時PD控制
作者：Ye Yuan, Kris Kitani
論文鏈接：https://arxiv.org/abs/1906.03173


2、xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera
xR-EgoPose：HMD相機的以自我爲中心的3D人體姿態
作者：Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino
論文鏈接：https://arxiv.org/abs/1907.10045


3、Selectivity or Invariance: Boundary-aware Salient Object Detection
選擇性或不變性：邊界感知的突出物體檢測
作者：Jinming Su, Jia Li1, Yu Zhang, Changqun Xia and Yonghong Tian
論文鏈接：https://arxiv.org/pdf/1812.10066.pdf


4、Learnable Triangulation of Human Pose（Oral)
人體姿態的可驗證三角測量
作者：Karim Iskakov, Egor Burkov, Victor Lempitsky, Yury Malkov
論文鏈接：https://arxiv.org/abs/1905.05754
Github鏈接：https://github.com/karfly/learnable-triangulation-pytorch
項目鏈接：https://saic-violet.github.io/learnable-triangulation/


5、Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
來自單個RGB圖像的3D多人姿態估計的攝像距離感知自上而下方法
作者：Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
論文鏈接：https://arxiv.org/abs/1907.11346
Github鏈接：https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE


6、Pose-aware Dynamic Attention for Human Object Interaction Detection
姿態感知動態注意用於人體目標交互檢測
Github鏈接：https://github.com/bobwan1995/Pose-aware-Dynamic-Attention-for-Human-Object-Interaction-Detection


7、SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning
基於半監督學習的三維手部姿態估計自組織網絡
Github鏈接：https://github.com/TerenceCYJ/SO-HandNet


8、Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
動態核蒸餾在視頻中的有效姿態估計
作者：Xuecheng Nie, Yuncheng Li, Linjie Luo, Ning Zhang, Jiashi Feng
論文鏈接：https://arxiv.org/abs/1908.09216


9、Single-Stage Multi-Person Pose Machines
單級多人姿勢機器
作者：Xuecheng Nie, Jianfeng Zhang, Shuicheng Yan, Jiashi Feng
論文鏈接：https://arxiv.org/abs/1908.09220


10、Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
利用多視圖圖像進行人體姿態和形狀重建
作者：Junbang Liang, Ming C. Lin
論文鏈接：https://arxiv.org/abs/1908.09464


11、Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
整體++場景理解:單視圖三維整體場景解析和人-物交互和物理常識下的人體姿態估計
作者：Yixin Chen, Siyuan Huang, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu
論文鏈接：https://arxiv.org/abs/1909.01507


12、Imitation Learning for Human Pose Prediction
模仿學習用於人體姿態預測
作者：Borui Wang, Ehsan Adeli, Hsu-kuang Chiu, De-An Huang, Juan Carlos Niebles
論文鏈接：https://arxiv.org/abs/1909.03449

目標跟蹤

1、Joint Monocular 3D Detection and Tracking
聯合單目3D檢測和跟蹤
作者：Hou-Ning Hu, Qizhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu
論文鏈接：https://arxiv.org/abs/1811.10742
項目鏈接：https://eborboihuc.github.io/Mono-3DT/?fbclid=IwAR1maTNHE5z-vEwAJKIcNEpbMWwBcjWJQ0gEHOwHB-u51w5dfeiZNCh0y-U
GitHub：https://github.com/ucbdrive/3d-vehicle-tracking


2、Deep Meta Learning for Real-Time Target-Aware Visual Tracking
用於實時目標感知視覺跟蹤的深度元學習
作者：Janghoon Choi, Junseok Kwon, and Kyoung Mu Lee
論文鏈接：https://arxiv.org/pdf/1712.09153.pdf


3、Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
學習畸變抑制相關濾波器用於無人機實時跟蹤
作者：Ziyuan Huang, Changhong Fu, Yiming Li, Fuling Lin, Peng Lu
論文鏈接：https://arxiv.org/abs/1908.02231


4、Robust Multi-Modality Multi-Object Tracking
魯棒多模態多目標跟蹤
作者：Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, Chen Change Loy
論文鏈接：https://arxiv.org/abs/1909.03850
Github鏈接：https://github.com/ZwwWayne/mmMOT

人臉

1、Video Face Clustering with Unknown Number of Clusters
視頻人臉聚類，聚類個數未知
作者：M. Tapaswi, M. T. Law, and S. Fidler
Github鏈接：https://github.com/makarandtapaswi/BallClustering_ICCV2019


2、Probabilistic Face Embeddings
作者：Yichun Shi, Anil K. Jain
論文鏈接：https://arxiv.org/abs/1904.09658
Github鏈接：https://github.com/seasonSH/Probabilistic-Face-Embeddings


3、Photo-Realistic Facial Details Synthesis from Single Image(Oral)
從單張圖像合成的真實面部細節
作者：Anpei Chen, Zhang Chen, Guli Zhang, Ziheng Zhang, Kenny Mitchell, Jingyi Yu
論文鏈接：https://arxiv.org/abs/1903.10873
Github鏈接： https://github.com/apchenstu/Facial_Details_Synthesis

ReID

1、One Shot Domain Adaptation for Person Re-Identification（Oral ）
作者：Yang Fu, Yunchao Wei, Guanshuo Wang, Jiwei Li, Xi Zhou, Honghui Shi, Thomas Huang
論文鏈接：https://arxiv.org/abs/1811.10144
Github鏈接：https://github.com/OasisYang/SSG


2、ABD-Net: Attentive but Diverse Person Re-Identification
ABD-Net:專注而多元的人重新識別
作者：Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, Zhangyang Wang
論文鏈接：https://arxiv.org/abs/1908.01114
Github鏈接：https://github.com/TAMU-VITA/ABD-Net


3、A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
一種新的無監督攝像機感知域適應框架，用於人員重新識別
作者：Lei Qi, Lei Wang, Jing Huo, Luping Zhou, Yinghuan Shi, Yang Gao
論文鏈接：https://arxiv.org/abs/1904.03425


4、advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
advPattern：物理世界通過可逆變換模式對人重新識別的攻擊
作者：Zhibo Wangy, Siyan Zhengy, Mengkai Songy, Qian Wangy, Alireza Rahimpourz, Hairong Qi
論文鏈接：https://arxiv.org/abs/1908.09327


5、Re-ID Driven Localization Refinement for Person Search
reid驅動的人員搜索本地化細化
作者：Chuchu Han, Jiacheng Ye, Yunshan Zhong, Xin Tan, Chi Zhang, Changxin Gao, Nong Sang
論文鏈接：https://arxiv.org/abs/1909.08580


6、Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
跨數據集人員重新識別通過無監督的姿態解纏和適應
作者：Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang
論文鏈接：https://arxiv.org/abs/1909.09675

OCR

1、GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
GA-DAN：用於場景文本檢測和識別的幾何感知域適應網絡
作者：Fangneng Zhan, Chuhui Xue, Shijian Lu
論文鏈接：https://arxiv.org/abs/1907.09653


2、Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion（Oral ）
用於全分辨率3D語義場景完成的嵌入式上下文金字塔
作者：Pingping Zhang, Wei Liu, Yinjie Lei, Huchuan Lu, Xiaoyun Yang
論文鏈接：https://arxiv.org/abs/1908.00382


3、Symmetry-constrained Rectification Network for Scene Text Recognition
用於場景文本識別的對稱約束校正網絡
作者：MingKun Yang, Yushuo Guan, Minghui Liao, Xin He, Kaigui Bian, Song Bai, Cong Yao, Xiang Bai
論文鏈接：https://arxiv.org/abs/1908.01957


4、Towards Unconstrained End-to-End Text Spotting（Oral ）
Towards無約束的端到端文本定位
作者：Siyang Qin, Alessandro Bissacco, Michalis Raptis, Yasuhisa Fujii, Ying Xiao
論文鏈接：https://arxiv.org/abs/1908.09231


5、SPGNet: Semantic Prediction Guidance for Scene Parsing
SPGNet：場景分析的語義預測指南
作者：Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-Mei Hwu, Honghui Shi
論文鏈接：https://arxiv.org/abs/1908.09798


6、CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
CAMP:用於文本-圖像檢索的跨模式自適應消息傳遞
作者：Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao
論文鏈接：https://arxiv.org/abs/1909.05506


7、Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
中文街景文本:部分監督學習的大型中文文本閱讀
作者： Yipeng Sun, Jiaming Liu, Wei Liu, Junyu Han, Errui Ding, Jingtuo Liu
論文鏈接：https://arxiv.org/abs/1909.07808


8、Large-scale Tag-based Font Retrieval with Generative Feature Learning
基於標籤的大規模字體檢索與生成特徵學習
作者：Tianlang Chen, Zhaowen Wang, Ning Xu, Hailin Jin, Jiebo Luo
論文鏈接：https://arxiv.org/abs/1909.02072


9、Visual Semantic Reasoning for Image-Text Matching（Oral）
圖像-文本匹配的視覺語義推理
作者：Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu
論文鏈接：https://arxiv.org/abs/1909.02701
Github鏈接：https://github.com/KunpengLi1994/VSRN


10、Dynamic Context Correspondence Network for Semantic Alignment
用於語義對齊的動態上下文通信網絡
作者：Shuaiyi Huang, Qiuyue Wang, Songyang Zhang, Shipeng Yan, Xuming He
論文鏈接：https://arxiv.org/abs/1909.03444

視頻

1、HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
HowTo100M：通過觀看數以億計的視頻剪輯來學習文本視頻嵌入
作者：Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, Josef Sivic
論文鏈接：https://arxiv.org/abs/1906.03327


2、VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
用於視頻和語言研究的大規模，高質量多語言數據集
作者：Xin Wang, Jiawei Wu, Junkun Chen, Lei Li, Yuan-Fang Wang, William Yang Wang
論文鏈接：https://arxiv.org/abs/1904.03493
項目鏈接：http://vatex.org/main/index.html
論文解讀：https://mp.weixin.qq.com/s/bOpKXshitpQ1YKE53WUPEw


3、BMN: Boundary-Matching Network for Temporal Action Proposal Generation
BMN：用於生成時間行動提案的邊界匹配網絡
作者：Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen
論文鏈接：https://arxiv.org/abs/1907.09702


4、Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
使用3D門控捲積和時間PatchGAN進行自由視頻修復
作者：Ya-Liang Chang, Zhe Yu Liu, Kuan-Ying Lee, Winston Hsu
論文鏈接：https://arxiv.org/abs/1904.10247
Github鏈接：https://github.com/amjltc295/Free-Form-Video-Inpainting


5、SlowFast Networks for Video Recognition(Oral)
用於視頻識別的SlowFast網絡
作者：Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He
論文鏈接：https://arxiv.org/abs/1812.03982


6、Point-to-Point Video Generation
點對點視頻生成
作者：Tsun-Hsuan Wang, Yen-Chi Cheng, Chieh Hubert Lin, Hwann-Tzong Chen, Min Sun
論文鏈接：https://arxiv.org/abs/1904.02912
項目鏈接：https://zswang666.github.io/P2PVG-Project-Page/?fbclid=IwAR1Cr-T54keo5zzaWLQuYNQMcPoKzXGr6-YrTDoauW6Hb5bOSwgluZQ3fIE


7、Disentangling Propagation and Generation for Video Prediction
作者：Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell
論文鏈接：https://arxiv.org/pdf/1812.00452.pdf


8、Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition (Oral)
作者：Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Shilei Wen
論文鏈接：https://arxiv.org/abs/1907.13369


9、VideoBERT: A Joint Model for Video and Language Representation Learning ( Oral )
VideoBERT：視頻和語言表徵學習的聯合模型
作者：Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, Cordelia Schmid
論文鏈接：https://arxiv.org/abs/1904.01766


10、TSM: Temporal Shift Module for Efficient Video Understanding
時間轉移模塊，用於高效的視頻理解
作者：Ji Lin, Chuang Gan, Song Han
論文鏈接：https://arxiv.org/abs/1811.08383
Github鏈接：https://github.com/mit-han-lab/temporal-shift-module


11、Exploiting temporal consistency for real-time video depth estimation
利用時間一致性進行實時視頻深度估計
Github鏈接：https://github.com/hkzhang91/ST-CLSTM


12、EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
EPIC-Fusion:以自我爲中心的動作識別的視聽時間綁定
作者：Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen
Github鏈接：https://github.com/ekazakos/temporal-binding-network


13、Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement
遠程壓縮面部視頻的心率測量：具有視頻增強功能的端到端深度學習解決方案
作者：Zitong Yu, Wei Peng, Xiaobai Li, Xiaopeng Hong, Guoying Zhao
論文鏈接：https://arxiv.org/abs/1907.11921


14、Onion-Peel Networks for Deep Video Completion
用於深度視頻完成的Onion-Peel網絡
作者：Seoung Wug Oh, Sungho Lee, Joon-Young Lee, Seon Joo Kim
論文鏈接：https://arxiv.org/abs/1908.08718


15、An Internal Learning Approach to Video Inpainting
一種內部學習方法的視頻Inpainting
作者：Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin
論文鏈接：https://arxiv.org/abs/1909.07957


16、Graph Convolutional Networks for Temporal Action Localization
時間動作定位的圖卷積網絡
作者：Runhao Zeng, Wenbing Huang, Mingkui Tan, Yu Rong, Peilin Zhao, Junzhou Huang, Chuang Gan
論文鏈接：https://arxiv.org/abs/1909.03252

超分辨率

1、Deep SR-ITM: Joint Learning of Super-resolution and Inverse Tone-Mapping for 4K UHD HDR Applications(Oral)
Deep SR-ITM：4K UHD HDR應用的超分辨率和反色調映射聯合學習
作者：Soo Ye Kim, Jihyong Oh, Munchurl Kim
論文鏈接：https://arxiv.org/abs/1904.11176


2、Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model
面向現實世界的單幅圖像超分辨率:一個新的基準和一個新的模型
論文鏈接：https://csjcai.github.io/papers/RealSR.pdf
Github鏈接：https://github.com/csjcai/RealSR

自動駕駛

1、Exploring the Limitations of Behavior Cloning for Autonomous Driving
探討自動駕駛行爲克隆的侷限性
作者：Felipe Codevilla, Eder Santana, Antonio M. López, Adrien Gaidon
論文鏈接：https://arxiv.org/abs/1904.08980
Github鏈接：https://github.com/felipecode/coiltraine/blob/master/docs/exploring_limitations.md


2、Scalable Place Recognition Under Appearance Change for Autonomous Driving（Oral ）
可伸縮位置識別下外觀變化自主駕駛
作者：Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin, Yu Liu, Thanh-Toan Do, Ian Reid
論文鏈接：https://arxiv.org/abs/1908.00178

3D、點雲

1、Deep Hough Voting for 3D Object Detection in Point Clouds（Oral）
DHV：點雲中的三維物體檢測
作者：Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas
論文鏈接：https://arxiv.org/abs/1904.09664


2、3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition
3D點雲學習用於大規模環境分析和場所識別
作者：Zhe Liu, Shunbo Zhou, Chuanzhe Suo, Yingtian Liu, Hesheng Wang, Yun-Hui Liu
論文鏈接：https://arxiv.org/abs/1812.07050


3、Learning to Reconstruct 3D Manhattan Wireframes from a Single Image ( Oral )
學習從單個圖像重建3D曼哈頓線框
作者：Yichao Zhou, Haozhi Qi, Yuexiang Zhai, Qi Sun, Zhili Chen, Li-Yi Wei, Yi Ma
論文鏈接：https://arxiv.org/abs/1905.07482


4、GarNet: A Two-stream Network for Fast and Accurate 3D Cloth Draping
GarNet：一個快速準確的3D布料覆蓋雙流網絡
作者：Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua
論文鏈接：https://arxiv.org/abs/1811.10983v2
項目鏈接：https://cvlab.epfl.ch/research/garment-simulation/garnet/


5、3D-RelNet: Joint Object and Relational Network for 3D Prediction
3D-RelNet：用於3D預測的聯合對象和關係網絡
作者：Nilesh Kulkarni, Ishan Misra, Shubham Tulsiani, Abhinav Gupta
論文鏈接：https://arxiv.org/pdf/1906.02729.pdf


6、PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows(Oral)
PointFlow：使用連續正常化流程生成3D點雲
作者：Guandao Yang, Xun Huang, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan
論文鏈接：https://arxiv.org/abs/1906.12320
Github鏈接：https://github.com/stevenygd/PointFlow
項目鏈接：https://www.guandaoyang.com/PointFlow/


7、Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
多角度點雲-VAE：通過聯合自我重建和半對半預測從多角度的三維點雲進行無監督特徵學習
作者：Zhizhong Han, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker
論文鏈接：https://arxiv.org/abs/1907.12704


8、SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
SceneGraphNet：神經消息傳遞3D室內場景增強
作者：Yang Zhou, Zachary While, Evangelos Kalogerakis
論文鏈接：https://arxiv.org/abs/1907.11308


9、HoloGAN: Unsupervised learning of 3D representations from natural images
HoloGAN：從自然圖像中無監督地學習3D表示
作者：Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, Yong-Liang Yang
論文鏈接：https://arxiv.org/abs/1904.01326
項目鏈接：https://www.monkeyoverflow.com/#/hologan-unsupervised-learning-of-3d-representations-from-natural-images/


10、FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
FrameNet：從單個RGB圖像學習3D表面的局部規範框架
作者：Jingwei Huang, Yichao Zhou, Thomas Funkhouser, Leonidas Guibas
論文鏈接：https://arxiv.org/pdf/1903.12305.pdf


11、Face De-occlusion using 3D Morphable Model and Generative Adversarial
使用3D可變模型和生成對抗性進行面部去遮擋
作者：Xaiowei Yuan and In Kyu Park
論文鏈接：http://image.inha.ac.kr/paper/ICCV2019_Xaiowei.pdf


12、Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
用於三維場景重建的多層深度和極線特徵變換器
作者：Daeyun Shin, Zhile Ren, Erik B. Sudderth, Charless C. Fowlkes
論文鏈接：https://arxiv.org/abs/1902.06729


13、Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
Pix2Vox:上下文感知的三維重建從單一和多視圖圖像
作者：Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Shengping Zhang
論文鏈接：https://arxiv.org/abs/1901.11153
Github鏈接：https://github.com/hzxie/Pix2Vox


14、MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation
單目三維行人定位與不確定性估計
作者：Lorenzo Bertoni, Sven Kreiss, Alexandre Alahi
論文鏈接：https://arxiv.org/abs/1906.06059
Github鏈接：https://github.com/vita-epfl/monoloco


15、Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
塑造人類:從單個圖像中估計非參數三維人體形狀
作者：Valentin Gabeur, Jean-Sebastien Franco, Xavier Martin, Cordelia Schmid, Gregory Rogez
論文鏈接：https://arxiv.org/abs/1908.00439


16、Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
Pixel2Mesh++:通過變形生成多視圖3D網格
作者：Chao Wen, Yinda Zhang, Zhuwen Li, Yanwei Fu
論文鏈接：https://arxiv.org/abs/1908.01491


17、View N-gram Network for 3D Object Retrieval
查看N-gram網絡三維對象檢索
作者：Xinwei He, Tengteng Huang, Song Bai, Xiang Bai
論文鏈接：https://arxiv.org/abs/1908.01958


18、GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild
GP2C:野外關節三維位姿和焦距估計的幾何投影參數一致性
作者：Alexander Grabner, Peter M. Roth, Vincent Lepetit
論文鏈接：https://arxiv.org/abs/1908.02809


19、Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
用於視頻顯著性檢測的時間聚合空間編解碼器
作者：Giorgos Bouritsas, Sergiy Bokhnyak, Stylianos Ploumpis, Michael Bronstein, Stefanos Zafeiriou
論文鏈接：https://arxiv.org/abs/1905.02876
Github鏈接：https://github.com/gbouritsas/Neural3DMM


20、DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
DUP-Net：用於3D對抗點雲防禦的Denoiser和Upsampler網絡
作者： Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, Nenghai Yu
論文鏈接：https://arxiv.org/abs/1812.11017


21、Interpolated Convolutional Networks for 3D Point Cloud Understanding（Oral ）
用於3D點雲理解的插值卷積網絡
作者： Jiageng Mao, Xiaogang Wang, Hongsheng Li
論文鏈接：https://arxiv.org/abs/1908.04512


22、Efficient Learning on Point Clouds with Basis Point Sets
基於點集的點雲有效學習
作者：Sergey Prokudin, Christoph Lassner, Javier Romero
論文鏈接：https://arxiv.org/abs/1908.09186


23、Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
基於先驗的單幅圖像三維重建的小鏡頭綜合
作者：Bram Wallace, Bharath Hariharan
論文鏈接：https://arxiv.org/abs/1909.01205


24、DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
DensePoint:學習密集的上下文表示，以實現高效的點雲處理
作者：Yongcheng Liu, Bin Fan, Gaofeng Meng, Jiwen Lu, Shiming Xiang, Chunhong Pan
論文鏈接：https://arxiv.org/abs/1909.03669

GCN

1、Can GCNs Go as Deep as CNNs?
作者：Guohao Li, Matthias Müller, Ali Thabet, Bernard Ghanem
論文鏈接：https://arxiv.org/abs/1904.03751
GitHub：https://github.com/lightaime/deep_gcns

GAN

1、Controllable Artistic Text Style Transfer via Shape-Matching GAN(Oral )
通過形匹配GAN實現可控的藝術文本風格轉換
作者：Shuai Yang, Zhangyang Wang, Zhaowen Wang, Ning Xu, Jiaying Liu, Zongming Guo
論文鏈接：https://arxiv.org/abs/1905.01354
Github鏈接：https://github.com/TAMU-VITA/ShapeMatchingGAN
項目鏈接：https://williamyang1991.github.io/projects/ICCV2019/SMGAN.html


2、Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks
利用生成對抗性網絡，實現逼真的單目凝視重定向
作者：Zhe He, Adrian Spurr, Xucong Zhang, Otmar Hilliges
論文鏈接：https://arxiv.org/abs/1903.12530
Github鏈接：https://github.com/HzDmS/gaze_redirection


3、AutoGAN: Neural Architecture Search for Generative Adversarial Networks
神經結構搜索生成對抗性網絡
Github鏈接：https://github.com/TAMU-VITA/AutoGAN


4、ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
ARGAN:用於陰影檢測和去除的細心的反覆生成的對抗性網絡
作者：Bin Ding, Chengjiang Long, Ling Zhang, Chunxia Xiao
論文鏈接：https://arxiv.org/abs/1908.01323

其他

1、Meta-Sim Learning to Generate Synthetic Datasets (Oral)
Meta-Sim學習生成合成數據集
作者：Amlan Kar, Aayush Prakash, Ming-Yu Liu, Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler
項目鏈接：HTTPS：//nv-tlabs.github.io/meta-sim/
論文鏈接：HTTPS：//arxiv.org/abs/1904.11621


2、nocaps: novel object captioning at scale
nocaps：大規模的新穎物體字幕
作者：Harsh Agrawal, Karan Desai, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, Peter
項目鏈接：https://nocaps.org
論文鏈接：https://arxiv.org/abs/1812.08658


3、Scene GraphPrediction with Limited Labels
作者：Vincent S. Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Re, Li Fei-Fei
論文鏈接：https://arxiv.org/abs/1904.11622


4、Variational Adversarial Active Learning（Oral）
變異對抗主動學習
作者：Samarth Sinha, Sayna Ebrahimi, Trevor Darrell
論文鏈接：https://arxiv.org/abs/1904.00370


5、The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs
Trajectron：使用動態時空圖的概率多智能體軌跡建模
作者：Boris Ivanovic, Marco Pavone
論文鏈接：https://arxiv.org/abs/1810.05993


6、End-to-End Learning of Representations for Asynchronous Event-BasedData
異步事件數據表示的端到端學習
作者：Daniel Gehrig, Antonio Loquercio, Konstantinos G. Derpanis, Davide Scaramuzza
論文鏈接：https://arxiv.org/abs/1904.08245


7、End-to-End Wireframe Parsing
端到端線框解析
作者：Yichao Zhou, Haozhi Qi, Yi Ma
論文鏈接：https://arxiv.org/abs/1905.03246
Github鏈接：https://github.com/zhou13/lcnn


8、Correlation Congruence for Knowledge Distillation
知識蒸餾的相關同餘
作者：Baoyun Peng, Xiao Jin, Jiaheng Liu, Shunfeng Zhou, Yichao Wu, Yu Liu, Dongsheng Li, Zhaoning Zhang
論文鏈接：https://arxiv.org/abs/1904.018029


9、Equivariant Multi-View Networks (Oral)
Equivariant多視圖網絡
作者：Carlos Esteves, Yinshuang Xu, Christine Allen-Blanchette, Kostas Daniilidis
論文鏈接：https://arxiv.org/abs/1904.00993
Github鏈接：https://github.com/daniilidis-group/emvn


10、Episodic Training for Domain Generalization
領域泛化的模式訓練
作者：Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales
論文鏈接：https://arxiv.org/abs/1902.00113


11、Few-shot Unsupervised Image-to-Image Translation
作者：Ming-Yu Liu, Xun Huang, Arun Mallya, Tero Karras, Timo Aila, Jaakko Lehtinen, Jan Kautz
論文鏈接：https://arxiv.org/abs/1905.01723
Github鏈接：https://github.com/nvlabs/FUNIT/
項目鏈接：http://www.cs.cornell.edu/~xhuang/publication/funit/


12、Tex2Shape: Detailed Full Human Body Geometry from a Single Image
Tex2Shape：單個圖像的人體詳細幾何特徵
作者：Thiemo Alldieck, Gerard Pons-Moll, Christian Theobalt, Marcus Magnor
論文鏈接：https://arxiv.org/abs/1904.08645
Github鏈接：https://github.com/thmoa/tex2shape


13、Semi-supervised Domain Adaptation via Minimax Entropy
通過Minimax熵進行半監督的域適應
作者：Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, Kate Saenko
論文鏈接：https://arxiv.org/abs/1904.06487


14、Canonical Surface Mapping via Geometric Cycle Consistency
通過幾何週期一致性的經典表面映射
作者：Nilesh Kulkarni, Abhinav Gupta, Shubham Tulsiani
論文鏈接：https://arxiv.org/abs/1907.10043
項目鏈接：https://nileshkulkarni.github.io/csm/


15、U4D: Unsupervised 4D Dynamic Scene Understanding
U4D：無監督的4D動態場景理解
作者：Armin Mustafa, Chris Russell, Adrian Hilton
論文鏈接：https://arxiv.org/abs/1907.09905


16、Scoot: A Perceptual Metric for Facial Sketches
Scoot：面部草圖的感知度量
作者：Deng-Ping Fan, ShengChuan Zhang, Yu-Huan Wu, Yun Liu, Ming-Ming Cheng, Bo Ren, Paul L Rosin, Rongrong Ji
論文鏈接：http://dpfan.net/wp-content/uploads/FaceSketch.pdf
Github鏈接：http://dpfan.net/wp-content/uploads/Scoot.zip
項目鏈接：http://dpfan.net/Scoot/


17、Similarity-Preserving Knowledge Distillation
相似性 - 保持知識蒸餾
作者：Frederick Tung, Greg Mori
論文鏈接：https://arxiv.org/abs/1907.09682


18、Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction
Tell，Draw和Repeat：基於連續的語言指令生成和修改圖像
作者：Alaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, Devon Hjelm, Layla El Asri, Samira Ebrahimi Kahou, Yoshua Bengio, Graham W. Taylor
論文鏈接：https://arxiv.org/pdf/1811.09845.pdf


19、Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
語義對抗性攻擊：欺騙深度分類器的參數化變換
作者：Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, Chinmay Hegde
論文鏈接：https://arxiv.org/abs/1904.08489


20、What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention
用滾動展開LSTM和模態注意預測自我中心行爲
作者：Antonino Furnari, Giovanni Maria Farinella
項目鏈接：https://iplab.dmi.unict.it/rulstm/
論文鏈接：https://arxiv.org/pdf/1905.09035.pdf
GitHub：https://github.com/antoninofurnari/rulstm


21、Improving Adversarial Robustness via Guided Complement Entropy
通過引導補語熵提高對抗魯棒性
作者：Hao-Yun Chen, Jhao-Hong Liang, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan.
論文鏈接：https://arxiv.org/abs/1903.09799
Github鏈接：https://github.com/henry8527/GCE


22、6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
6-DOF GraspNet：對象操作的變分抓取生成
作者：Arsalan Mousavian, Clemens Eppner, Dieter Fox
論文鏈接：https://arxiv.org/abs/1905.10520


23、Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction
概率彈道預測語境中的變種損失分析
作者：Luca Anthony Thiede, Pratik Prabhanjan Brahma
論文鏈接：https://arxiv.org/abs/1907.10178


24、DAFL: Data-Free Learning of Student Networks
DAFL：學生網絡的無數據學習
作者：Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, Qi Tian
論文鏈接：https://arxiv.org/abs/1904.01186


25、Boosting Few-Shot Visual Learning with Self-Supervision
自我監督推動的少樣本視覺學習
作者：Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord
論文鏈接：https://arxiv.org/abs/1906.05186


26、A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
Wahba問題異常值的基於四元數的可證明最優解
作者：Heng Yang, Luca Carlone
論文鏈接：https://arxiv.org/abs/1905.12536


27、Embodied Visual Recognition
人體視覺識別
作者：Jianwei Yang，Zhile Ren，Mingze Xu，Xinlei Chen，David Crandall，Devi Parikh，Dhruv Batra
項目鏈接：https://www.cc.gatech.edu/~jyang375/evr.html


28、Learning Implicit Generative Models by Matching Perceptual Features(Oral)
作者：Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin
論文鏈接：https://arxiv.org/abs/1904.02762v1


29、Rethinking ImageNet Pre-training
作者：Kaiming He, Ross Girshick, and Piotr Dollár
論文鏈接：https://arxiv.org/abs/1811.08883


30、COCO-GAN: Generation by Parts via Conditional Coordinating(Oral)
COCO-GAN：通過條件協調按部件生成
作者：Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen
論文鏈接：https://arxiv.org/abs/1904.00284
Github鏈接：https://github.com/hubert0527/COCO-GAN
項目鏈接：https://hubert0527.github.io/COCO-GAN/


31、Model Vulnerability to Distributional Shifts over Image Transformation Sets
作者：Riccardo Volpi, Vittorio Murino
論文鏈接：https://arxiv.org/abs/1903.11900
Github鏈接：https://github.com/ricvolpi/domain-shift-robustness


32、Exploring Randomly Wired Neural Networks for Image Recognition(Oral)
探索隨機有線神經網絡進行圖像識別
作者：Saining Xie, Alexander Kirillov, Ross Girshick, and Kaiming He
論文鏈接：https://arxiv.org/abs/1904.01569


33、Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
作者：Min-Hung Chen, Zsolt Kira, Ghassan AlRegib, Jaekwon Woo, Ruxin Chen, Jian Zheng
論文鏈接：https://arxiv.org/abs/1907.12743
Github鏈接：http://github.com/cmhungsteve/TA3N


34、Creativity Inspired Zero-Shot Learning
啓發式的零樣本學習
作者：Mohamed Elhoseiny, Mohamed Elfeki
論文鏈接：https://arxiv.org/abs/1904.01109


35、Model Vulnerability to Distributional Shifts over Image Transformation Sets
作者：Riccardo Volpi, Vittorio Murino
論文鏈接：https://arxiv.org/abs/1903.11900
Github鏈接：https://github.com/ricvolpi/domain-shift-robustness


36、Coherent Semantic Attention for Image Inpainting
圖像修復的連貫語義注意力機制
作者：Hongyu Liu, Bin Jiang, Yi Xiao, Chao Yang
論文鏈接：https://arxiv.org/abs/1905.12384


37、Learning to Paint with Model-based Deep Reinforcement Learning
基於模型的深層強化學習學習繪畫
作者：Zhewei Huang, Wen Heng, Shuchang Zhou
論文鏈接：https://arxiv.org/abs/1903.04411
Github鏈接：https://github.com/hzwer/ICCV2019-LearningToPaint


38、LayoutVAE: Stochastic Scene Layout Generation from a Label Set
LayoutVAE：從標籤集生成隨機場景佈局
作者：Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
論文鏈接：https://arxiv.org/abs/1907.10719


39、Co-Evolutionary Compression for Unpaired Image Translation
非成對圖像翻譯的共同進化壓縮
作者：Han Shu, Yunhe Wang, Xu Jia, Kai Han, Hanting Chen, Chunjing Xu, Qi Tian, Chang Xu
論文鏈接：https://arxiv.org/abs/1907.10804


40、Enhancing Adversarial Example Transferability with an Intermediate Level Attack
通過中級攻擊增強對抗性示例可轉移性
作者：Qian Huang, Isay Katsman, Horace He, Zeqi Gu, Serge Belongie, Ser-Nam Lim
論文鏈接：https://arxiv.org/abs/1907.10823


41、Gated2Depth: Real-time Dense Lidar from Gated Images
Gated2Depth：來自門控圖像的實時密集激光雷達
作者：Tobias Gruber, Frank Julca-Aguilar,Mario Bijelic,Werner Ritter,Klaus Dietmayer,Felix Heide
論文鏈接：https://www.cs.princeton.edu/~fheide/papers/Gated2Depth_preprint.pdf


42、Counting with Focus for Free
作者：Zenglin Shi, Pascal Mettes, Cees G. M. Snoek
論文鏈接：https://arxiv.org/abs/1903.12206
Github鏈接：https://github.com/shizenglin/Counting-with-Focus-for-Free


43、PU-GAN: a Point Cloud Upsampling Adversarial Network
作者：Ruihui Li, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
論文鏈接：https://arxiv.org/abs/1907.10844


44、Moment Matching for Multi-Source Domain Adaptation (Oral)
多源域適應的配套匹配
作者：Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang
論文鏈接：https://arxiv.org/abs/1812.01754


45、EMPNet: Neural Localisation and Mapping using Embedded Memory Points
EMPNet：使用嵌入式存儲點的神經定位和映射
作者：Gil Avraham, Yan Zuo, Thanuja Dharmasiri, Tom Drummond
論文鏈接：https://arxiv.org/abs/1907.13268


46、Learning Compositional Representations for Few-Shot Recognition
少樣本識別的構圖表示學習
作者：Pavel Tokmakov, Yuxiong Wang, Martial Hebert
論文鏈接：https://sites.google.com/view/comprepr/home


47、Digging Into Self-Supervised Monocular Depth Estimation
自我監督單眼深度估計的研究
作者：Clement Godard, Oisin Mac Aodha, Michael Firman, Gabriel Brostow
論文鏈接：https://arxiv.org/pdf/1806.01260.pdf


48、Deep Interpretable Non-Rigid Structure from Motion
運動的深層可解釋的非剛性結構
作者：Chen Kong, Simon Lucey
論文鏈接：https://arxiv.org/pdf/1902.10840.pdf


49、PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
PRECOG：視覺多代理設置中的目標條件
作者：Nicholas Rhinehart, Rowan McAllister, Kris Kitani, Sergey Levine
論文鏈接：https://arxiv.org/pdf/1905.01296.pdf
項目鏈接：https://sites.google.com/view/precog


50、Lifelong GAN: Continual Learning for Conditional Image Generation
終身GAN：條件圖像生成的持續學習
作者：Mengyao Zhai, Lei Chen, Fred Tung, Jiawei He, Megha Nawhal, Greg Mori
論文鏈接：https://arxiv.org/abs/1907.10107


52、An Empirical Study of Spatial Attention Mechanisms in Deep Networks
深度網絡空間注意機制的實證研究
作者：Xizhou Zhu, Dazhi Cheng, Zheng Zhang, Stephen Lin, Jifeng Dai
論文鏈接：https://arxiv.org/pdf/1904.05873.pdf


53、Fashion++: Minimal Edits for Outfit Improvement
Fashion ++：改進裝備的最小編輯
作者：Wei-Lin Hsiao, Isay Katsman, Chao-Yuan Wu, Devi Parikh, Kristen Grauman
論文鏈接：https://arxiv.org/pdf/1904.09261.pdf


54、Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment
Align2Ground：由圖像標題對齊引導的弱監督短語接地
作者：Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja, Devi Parikh, Ajay Divakaran
論文鏈接：https://arxiv.org/pdf/1903.11649.pdf


55、Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
做一個提示：利用解釋使視覺和語言模型更加紮實
作者：Ramprasaath R. Selvaraju, Stefan Lee, Yilin Shen, Hongxia Jin, Dhruv Batra, Devi Parikh
論文鏈接：https://arxiv.org/pdf/1902.03751.pdf


56、SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation
SplitNet：用於體驗視覺導航的Sim2Sim和Task2Task轉移
作者：Daniel Gordon, Abhishek Kadian, Devi Parikh, Judy Hoffman, Dhruv Batra
論文鏈接：https://arxiv.org/pdf/1905.07512.pdf


57、Habitat: A Platform for Embodied AI Research ( Oral )
Habitat：體驗人工智能研究的平臺
作者：Manolis Savva, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, Vladlen Koltun, Jitendra Malik, Devi Parikh, Dhruv Batra
論文鏈接：https://arxiv.org/abs/1904.01201


58、EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association
EM-Fusion：具有概率數據關聯的動態對象級SLAM
作者：Michael Strecke, Jörg Stückler
論文鏈接：https://arxiv.org/abs/1904.11781


59、Texture Fields: Learning Texture Representations in Function Space
紋理字段：在函數空間中學習紋理表示
作者：Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, Andreas Geiger
論文鏈接：https://arxiv.org/abs/1905.07259


60、AMASS: Archive of Motion Capture as Surface Shapes
AMASS：將運動捕捉存檔爲表面形狀
作者：Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, Michael J. Black
論文鏈接：https://arxiv.org/abs/1904.03278


61、End-to-end Learning for Graph Decomposition
圖形分解的端到端學習
作者：Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang
論文鏈接：https://arxiv.org/pdf/1812.09737.pdf


62、Towards Multi-pose Guided Virtual Try-on Network
Towards多姿態引導虛擬試穿網絡
作者：Haoye Dong, Xiaodan Liang, Bochao Wang, Hanjiang Lai, Jia Zhu, Jian Yin
論文鏈接：https://arxiv.org/abs/1902.11026


63、On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
利用無梯度優化和算子分裂方法設計黑盒對抗實例
作者：Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin
論文鏈接：https://arxiv.org/abs/1907.11684


64、Goal-Driven Sequential Data Abstraction
目標驅動的順序數據抽象
作者：Umar Riaz Muhammad, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song
論文鏈接：https://arxiv.org/abs/1907.12336


65、Recursive Cascaded Networks for Unsupervised Medical Image Registration
用於無監督醫學圖像配準的遞歸級聯網絡
作者： Shengyu Zhao, Yue Dong, Eric I-Chao Chang, Yan Xu
論文鏈接：https://arxiv.org/abs/1907.12353


66、Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting
學習規模：爲人羣計數生成多極歸一化密度圖
作者：Chenfeng Xu, Kai Qiu, Jianlong Fu, Song Bai, Yongchao Xu, Xiang Bai
論文鏈接：https://arxiv.org/abs/1907.12428


67、MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
MetaPruning：自動神經網絡通道修剪的元學習
作者：Zechun Liu, Haoyuan Mu, Xiangyu Zhang, Zichao Guo, Xin Yang, Tim Kwang-Ting Cheng, Jian Sun
論文鏈接：https://arxiv.org/abs/1903.10258


68、Switchable Whitening for Deep Representation Learning
作者：Xingang Pan, Xiaohang Zhan, Jianping Shi, Xiaoou Tang, Ping Luo
論文鏈接：https://arxiv.org/abs/1904.09739


69、Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
作者：Yunpeng Chen, Haoqi Fan, Bing Xu, Zhicheng Yan, Yannis Kalantidis, Marcus Rohrbach, Shuicheng Yan, Jiashi Feng
論文鏈接：https://arxiv.org/abs/1904.05049


70、Task2Vec: Task Embedding for Meta-Learning
Task2Vec：元學習的任務嵌入
作者：Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona
論文鏈接：https://arxiv.org/abs/1902.03545


71、CARAFE: Content-Aware ReAssembly of FEatures ( Oral )
CARAFE：內容意識重新組裝特徵
作者：Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin
論文鏈接：https://arxiv.org/pdf/1905.02188.pdf


72、Domain Intersection and Domain Difference
域交和域差
Github鏈接：https://github.com/sagiebenaim/DomainIntersectionDifference


73、A Closed-form Solution to Universal Style Transfer
一種通用樣式轉換的封閉式解決方案
作者：Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen, Feng Xu, Li Zhang
論文鏈接：https://arxiv.org/abs/1906.00668
Github鏈接：https://github.com/lu-m13/OptimalStyleTransfer


74、Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
基於近似方差傳播的無樣本認知不確定性估計
Github鏈接：https://github.com/janisgp/Sampling-free-Epistemic-Uncertainty


75、On the Over-Smoothing Problem of CNN Based Disparity Estimation
基於CNN的視差估計的過平滑問題
Github鏈接：https://github.com/chenchr/otosp


76、Metric Learning with HORDE: High-Order Regularizer for Deep Embeddings
HORDE度量學習:用於深度嵌入的高階正則化器
論文鏈接：https://arxiv.org/abs/1908.02735
Github鏈接：https://github.com/pierre-jacob/ICCV2019-Horde


77、Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data
面具陰影甘:學習從未配對的數據中去除陰影
作者：Xiaowei Hu, Yitong Jiang, Chi-Wing Fu, and Pheng-Ann Heng
Github鏈接：https://github.com/xw-hu/Mask-ShadowGAN


78、Universally Slimmable Networks and Improved Training Techniques
普遍精簡的網絡和改進的培訓技術
作者：Jiahui Yu, Thomas Huang
論文鏈接：https://arxiv.org/abs/1903.05134
Github鏈接：https://github.com/JiahuiYu/slimmable_networks


79、Domain Adaptation for Structured Output via Discriminative Patch Representations (Oral)
通過有區別的Patch表示對結構化輸出進行域適應
作者：Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter, Manmohan Chandraker
論文鏈接：https://arxiv.org/abs/1901.05427


80、Deep Non-Rigid Structure from Motion（Oral）
.深非剛性的結構與運動
作者：Chen Kong, Simon Lucey
論文鏈接：https://arxiv.org/abs/1908.00052


81、Learning the Model Update for Siamese Trackers
學習暹羅語追蹤器的模型更新
作者：Lichao Zhang, Abel Gonzalez-Garcia, Joost van de Weijer, Martin Danelljan, Fahad Shahbaz Khan
論文鏈接：https://arxiv.org/abs/1908.00855


82、Distilling Knowledge From a Deep Pose Regressor Network
從深層位姿迴歸網絡中提取知識
作者：Muhamad Risqi U. Saputra, Pedro P. B. de Gusmao, Yasin Almalioglu, Andrew Markham, Niki Trigoni
論文鏈接：https://arxiv.org/abs/1908.00858


83、Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
基於相關感知的圖像集識別的置換不變特徵重構
作者：Xiaofeng Liu, Zhenhua Guo, Site Li, Lingsheng Kong, Ping Jia, Jane You, B. V. K. Kumar
論文鏈接：https://arxiv.org/abs/1908.01174


84、Restoration of Non-rigidly Distorted Underwater Images using a Combination of Compressive Sensing and Local Polynomial Image Representations（Oral ）
恢復非剛性的扭曲的水下圖像使用壓縮傳感和圖像局部多項式表示的組合
作者： Jerin Geo James, Pranay Agrawal, Ajit Rajwade
論文鏈接：https://arxiv.org/abs/1908.01940


85、Semi-supervised Skin Detection by Network with Mutual Guidance
基於相互指導的網絡半監督皮膚檢測
作者：Yi He, Jiayuan Shi, Chuan Wang, Haibin Huang, Jiaming Liu, Guanbin Li, Risheng Liu, Jue Wang
論文鏈接：https://arxiv.org/abs/1908.01977


86、Consensus Maximization Tree Search Revisited（Oral）
共識最大化樹搜索重新審視(口語)
作者：Zhipeng Cai, Tat-Jun Chin, Vladlen Koltun
論文鏈接：https://arxiv.org/abs/1908.02021


87、Deep Self-Learning From Noisy Labels
從嘈雜的標籤中進行深度的自我學習
作者：Jiangfan Han, Ping Luo, Xiaogang Wang
論文鏈接：https://arxiv.org/abs/1908.02160


88、Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
用於無監督圖表示學習的對稱圖卷積自編碼器
作者：Jiwoong Park, Minsik Lee, Hyung Jin Chang, Kyuewang Lee, Jin Young Choi
論文鏈接：https://arxiv.org/abs/1908.02441


89、Expert Sample Consensus Applied to Camera Re-Localization
將專家樣本一致性應用於相機再定位
作者：Eric Brachmann, Carsten Rother
論文鏈接：https://arxiv.org/abs/1908.02484


90、SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
空間感:一個反向衆包的空間關係識別基準
作者：Kaiyu Yang, Olga Russakovsky, Jia Deng
論文鏈接：https://arxiv.org/abs/1908.02660


91、Bidirectional One-Shot Unsupervised Domain Mapping
雙向一次無監督域映射
Github鏈接：https://github.com/tomercohen11/BiOST


92、CompenNet++: End-to-end Full Projector Compensation
CompenNet++:端到端全投影儀補償
Github鏈接：https://github.com/BingyaoHuang/CompenNet-plusplus


93、Perspective-Guided Convolution Networks for Crowd Counting
用於人羣計數的透視引導卷積網絡
Github鏈接：https://github.com/Zhaoyi-Yan/PGCNet


94、Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
Larger範數更可轉移：無監督域自適應的自適應特徵範數方法
作者：Ruijia Xu, Guanbin Li, Jihan Yang, Liang Lin
論文鏈接：https://arxiv.org/abs/1811.07456


95、Closed-Form Optimal Two-View Triangulation Based on Angular Errors
基於角度誤差的閉式最優雙視三角剖分
作者：Seong Hun Lee, Javier Civera
論文鏈接：https://arxiv.org/abs/1903.09115


96、Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild
在荒野中克服了未標記數據的災難性遺忘
作者：Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee
論文鏈接：https://arxiv.org/abs/1903.12648
Github鏈接：https://github.com/kibok90/iccv2019-inc


97、Learning Combinatorial Embedding Networks for Deep Graph Matching
用於深度圖匹配的學習組合嵌入網絡
作者：Runzhong Wang, Junchi Yan, Xiaokang Yang
論文鏈接：https://arxiv.org/abs/1904.00597


98、PR Product: A Substitute for Inner Product in Neural Networks（Oral ）
PR產品：神經網絡內部產品替代品（口服）
作者：Zhennan Wang, Wenbin Zou, Chen Xu
論文鏈接：https://arxiv.org/abs/1904.13148
Github鏈接：https://github.com/wzn0828/PR_Product


99、STM: SpatioTemporal and Motion Encoding for Action Recognition
STM：行動識別的SpatioTmporal和運動編碼
作者：Boyuan Jiang, Mengmeng Wang, Weihao Gan, Wei Wu, Junjie Yan
論文鏈接：https://arxiv.org/abs/1908.02486


100、Memory-Based Neighbourhood Embedding for Visual Recognition（Oral ）
基於記憶的鄰域嵌入視覺識別
作者：Suichan Li, Dapeng Chen, Bin Liu, Nenghai Yu, Rui Zhao
論文鏈接：https://arxiv.org/abs/1908.04992


101、Few-Shot Learning with Global Class Representations
全球班級代表的快速學習
作者：Tiange Luo, Aoxue Li, Tao Xiang, Weiran Huang, Liwei Wang
論文鏈接：https://arxiv.org/abs/1908.05257


102、Learning Trajectory Dependencies for Human Motion PredictionOral
學習人體運動預測的軌跡依賴性
作者：Wei Mao, Miaomiao Liu, Mathieu Salzmann, Hongdong Li
論文鏈接：https://arxiv.org/abs/1908.05436
Github鏈接：https://github.com/wei-mao-2019/LearnTrajDep


103、Symmetric Cross Entropy for Robust Learning with Noisy Labels
具有噪聲標籤的魯棒學習的對稱交叉熵
作者：Yisen Wang, Xingjun Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, James Bailey
論文鏈接：https://arxiv.org/abs/1908.06112


104、From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
從打開設置到封閉設置：按空間劃分和計數計算對象
作者：Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Zhiguo Cao, Chunhua Shen
論文鏈接：https://arxiv.org/abs/1908.06473
Github鏈接：https://github. com/xhp-hust-2018-2011/S-DCNet


105、Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
通過骷髏解剖表示從人工圖像中恢復人體網格
作者：Sun Yu, Ye Yun, Liu Wu, Gao Wenpeng, Fu YiLi, Mei Tao
論文鏈接：https://arxiv.org/abs/1908.07172


106、ViCo: Word Embeddings from Visual Co-occurrences
ViCo：來自視覺共現的詞嵌入
作者：Tanmay Gupta, Alexander Schwing, Derek Hoiem
論文鏈接：https://arxiv.org/abs/1908.08527
項目鏈接：http://tanmaygupta.info/vico/


107、Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning
在多樣性圖像標題期間建模意圖的順序潛在空間
作者：Jyoti Aneja, Harsh Agrawal, Dhruv Batra, Alexander Schwing
論文鏈接：https://arxiv.org/abs/1908.08529


108、Learning Similarity Conditions Without Explicit Supervision
在沒有明確監督的情況下學習相似性條件
作者：Reuben Tan, Mariya I. Vasileva, Kate Saenko, Bryan A. Plummer
論文鏈接：https://arxiv.org/abs/1908.08589


109、Shadow Removal via Shadow Image Decomposition
通過陰影圖像分解去除陰影
作者：Hieu Le, Dimitris Samaras
論文鏈接：https://arxiv.org/abs/1908.08628


110、Crowd Counting with Deep Structured Scale Integration Network
深度結構化規模集成網絡的計算
作者：Lingbo Liu, Zhilin Qiu, Guanbin Li, Shufan Liu, Wanli Ouyang, Liang Lin
論文鏈接：https://arxiv.org/abs/1908.08692


111、Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
自我監督的深度視覺測距的順序對抗性學習
作者：Shunkai Li, Fei Xue, Xin Wang, Zike Yan, Hongbin Zha
論文鏈接：https://arxiv.org/abs/1908.08704


112、Learning Filter Basis for Convolutional Neural Network Compression
卷積神經網絡壓縮的學習濾波器基礎
作者：Yawei Li, Shuhang Gu, Luc Van Gool, Radu Timofte
論文鏈接：https://arxiv.org/abs/1908.08932
Github鏈接：https://github.com/ofsoundof/learning_filter_basis


113、Where Is My Mirror?
作者：Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Baocai Yin, Rynson W. H. Lau
論文鏈接：https://arxiv.org/abs/1908.09101
項目鏈接：https://mhaiyang.github.io/ICCV2019_MirrorNet/index.html


114、Towards Unsupervised Image Captioning with Shared Multimodal Embeddings
使用共享多模式嵌入來保護無監督的圖像標題
作者：Iro Laina, Christian Rupprecht, Nassir Navab
論文鏈接：https://arxiv.org/abs/1908.09317


115、Object-Driven Multi-Layer Scene Decomposition From a Single Image
來自單個圖像的對象驅動的多層場景分解
作者：Helisa Dhamo, Nassir Navab, Federico Tombari
論文鏈接：https://arxiv.org/abs/1908.09521


116、Non-local Recurrent Neural Memory for Supervised Sequence Modeling（Oral）
用於監督序列建模的非局部遞歸神經記憶
作者：Canmiao Fu, Wenjie Pei, Qiong Cao, Chaopeng Zhang, Yong Zhao, Xiaoyong Shen, Yu-Wing Tai
論文鏈接：https://arxiv.org/abs/1908.09535


117、Embarrassingly Simple Binary Representation Learning
簡單的二進制表示學習
作者：Yuming Shen, Jie Qin, Jiaxin Chen, Li Liu, Fan Zhu
論文鏈接：https://arxiv.org/abs/1908.09573


118、Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels（Oral ）
簡單的二進制表示學習
作者：Felix J. S. Bragman, Ryutaro Tanno, Sebastien Ourselin, Daniel C. Alexander, M. Jorge Cardoso
論文鏈接：https://arxiv.org/abs/1908.09597


119、Confidence Regularized Self-Training
肯定的自我訓練
作者：Yang Zou, Zhiding Yu, Xiaofeng Liu, B. V. K. Vijaya Kumar, Jinsong Wang
論文鏈接：https://arxiv.org/abs/1908.09822
Github鏈接：https://github.com/yzou2/CRST


120、SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
軟三重損失:沒有三重抽樣的深度度量學習
作者：Qi Qian, Lei Shang, Baigui Sun, Juhua Hu, Hao Li, Rong Jin
論文鏈接：https://arxiv.org/abs/1909.05235


121、A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays
一種CNNs相機:面向像素處理器陣列上的嵌入式神經網絡
作者：Laurie Bose, Jianing Chen, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas
論文鏈接：https://arxiv.org/abs/1909.05647


122、DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
深度修剪:通過可微PatchMatch學習有效的立體匹配
作者：Shivam Duggal, Shenlong Wang, Wei-Chiu Ma, Rui Hu, Raquel Urtasun
論文鏈接：https://arxiv.org/abs/1909.05845


123、Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
反思零鏡頭學習:一個有條件的視覺分類視角
作者：Kai Li, Martin Renqiang Min, Yun Fu
論文鏈接：https://arxiv.org/abs/1909.05995


124、Learning Spatial Awareness to Improve Crowd Counting（Oral）
作者：Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Alexander Hauptmann
論文鏈接：https://arxiv.org/abs/1909.07057


125、AdaptIS: Adaptive Instance Selection Network
AdaptIS:自適應實例選擇網絡
作者：Konstantin Sofiiuk, Olga Barinova, Anton Konushin
論文鏈接：https://arxiv.org/abs/1909.07829
Github鏈接：https://github.com/saic-vul/adaptis


126、Self-Supervised Monocular Depth Hints
自我監督單眼深度提示
作者：Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov
論文鏈接：https://arxiv.org/abs/1909.09051


127、Making the Invisible Visible: Action Recognition Through Walls and Occlusions
使不可見變爲可見:通過牆壁和遮擋的動作識別
作者：Tianhong Li, Lijie Fan, Mingmin Zhao, Yingcheng Liu, Dina Katabi
論文鏈接：https://arxiv.org/abs/1909.09300


128、Adversarial Learning with Margin-based Triplet Embedding Regularization
基於邊值的三重嵌入正則化的對抗性學習
作者： Yaoyao Zhong, Weihong Deng
論文鏈接：https://arxiv.org/abs/1909.09481


129、Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
交互式草圖和填充:多級草圖到圖像的翻譯
作者： Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman
論文鏈接：https://arxiv.org/abs/1909.11081
項目鏈接：https://arnabgho.github.io/iSketchNFill/


130、Anchor Loss: Modulating Loss Scale based on Prediction Difficulty（Oral ）
錨點損失:基於預測難度的調整損失量表
作者：Serim Ryou, Seong-Gyun Jeong, Pietro Perona
論文鏈接：https://arxiv.org/abs/1909.11155


131、Learning Propagation for Arbitrarily-structured Data
任意結構數據的學習傳播
作者：Sifei Liu, Xueting Li, Varun Jampani, Shalini De Mello, Jan Kautz
論文鏈接：https://arxiv.org/abs/1909.11237


132、MIC: Mining Interclass Characteristics for Improved Metric Learning
MIC:挖掘類間特徵以改進度量學習
作者：Karsten Roth, Biagio Brattoli, Björn Ommer
論文鏈接：https://arxiv.org/abs/1909.11574


133、Compact Trilinear Interaction for Visual Question Answering
緊湊的三線性互動視覺問題回答
作者：Tuong Do, Thanh-Toan Do, Huy Tran, Erman Tjiputra, Quang D. Tran
論文鏈接：https://arxiv.org/abs/1909.11874


134、Convex Relaxations for Consensus and Non-Minimal Problems in 3D Vision
三維視覺中一致和非最小問題的凸鬆弛
作者：Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool
論文鏈接：https://arxiv.org/abs/1909.12034


135、Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
可區分的學習到組的通道通過可分組的卷積神經網絡
作者：Zhaoyang Zhang, Jingyu Li, Wenqi Shao, Zhanglin Peng, Ruimao Zhang, Xiaogang Wang, Ping Luo
論文鏈接：https://arxiv.org/abs/1908.05867
Github鏈接：https://github.com/d-li14/dgconv.pytorch


136、HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
HBONet:兩個正交維度上的和諧瓶頸
作者：Duo Li, Aojun Zhou, Anbang Yao
論文鏈接：https://arxiv.org/abs/1908.03888
Github鏈接：https://github.com/d-li14/HBONet


137、Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
雙元學生:打破教師在半監督學習中的限制
作者：Zhanghan Ke, Daoye Wang, Qiong Yan, Jimmy Ren, Rynson W. H. Lau
論文鏈接：https://arxiv.org/abs/1909.01804


138、


139、Program-Guided Image Manipulators
Program-Guided形象操縱者
作者：Jiayuan Mao, Xiuming Zhang, Yikai Li, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
論文鏈接：https://arxiv.org/abs/1909.02116
項目鏈接：http://pgim.csail.mit.edu/


140、Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
通過時空圖推理來理解人類的目光交流
作者：Lifeng Fan, Wenguan Wang, Siyuan Huang, Xinyu Tang, Song-Chun Zhu
論文鏈接：https://arxiv.org/abs/1909.02144


141、Gravity as a Reference for Estimating a Person's Height from Video
重力作爲一個參考，從視頻估計一個人的高度
作者：Didier Bieler, Semih Günel, Pascal Fua, Helge Rhodin
論文鏈接：https://arxiv.org/abs/1909.02211


142、Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
貝葉斯-因素- vae:用於因素分解的層次貝葉斯深度自動編碼器模型
作者：Minyoung Kim, Yuting Wang, Pritish Sahu, Vladimir Pavlovic
論文鏈接：https://arxiv.org/abs/1909.02820


143、Hierarchy Parsing for Image Captioning
用於圖像字幕的層次結構解析
作者： Ting Yao, Yingwei Pan, Yehao Li, Tao Mei
論文鏈接：https://arxiv.org/abs/1909.03918


144、Learning Object-specific Distance from a Monocular Image
.從單眼圖像學習物體特定的距離
作者：Jing Zhu, Yi Fang, Husam Abu-Haimed, Kuo-Chin Lien, Dongdong Fu, Junli Gu
論文鏈接：https://arxiv.org/abs/1909.04182


145、Bayesian Relational Memory for Semantic Visual Navigation
用於語義視覺導航的貝葉斯關係記憶
作者：Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
論文鏈接：https://arxiv.org/abs/1909.04306


146、FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
FreiHAND:用於從單個RGB圖像捕獲手部姿勢和形狀的無標記數據集
作者：Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox
論文鏈接：https://arxiv.org/abs/1909.04349
項目鏈接：https://lmb.informatik.uni-freiburg.de/projects/freihand/


147、Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
聯合深度特徵的結構化建模和突出目標檢測的預測精化
作者： Yingyue Xu, Dan Xu, Xiaopeng Hong, Wanli Ouyang, Rongrong Ji, Min Xu, Guoying Zhao
論文鏈接：https://arxiv.org/abs/1909.04366


148、FDA: Feature Disruptive Attack
特性破壞性攻擊
作者： Aditya Ganeshan, B. S. Vivek, R. Venkatesh Babu
論文鏈接：https://arxiv.org/abs/1909.04385
Github鏈接：https://github.com/BardOfCodes/fda


149、Cross-X Learning for Fine-Grained Visual Categorization
用於細粒度視覺分類的交叉x學習
作者：Wei Luo, Xitong Yang, Xianjie Mo, Yuheng Lu, Larry S. Davis, Jun Li, Jian Yang, Ser-Nam Lim
論文鏈接：https://arxiv.org/abs/1909.04412
Github鏈接：https://github.com/cswluo/CrossX


150、Reasoning About Human-Object Interactions Through Dual Attention Networks
通過雙重注意力網絡對人-物交互進行推理
作者：Tete Xiao, Quanfu Fan, Dan Gutfreund, Mathew Monfort, Aude Oliva, Bolei Zhou
論文鏈接：https://arxiv.org/abs/1909.04743


151、Variable Rate Deep Image Compression With a Conditional Autoencoder
可變速率深圖像壓縮與條件自動編碼器
作者： Yoojin Choi, Mostafa El-Khamy, Jungwon Lee
論文鏈接：https://arxiv.org/abs/1909.04802


152、Deep Elastic Networks with Model Selection for Multi-Task Learning
具有多任務學習模型選擇的深度彈性網絡
作者：Chanho Ahn, Eunwoo Kim, Songhwai Oh
論文鏈接：https://arxiv.org/abs/1909.04860


153、Sparse and Imperceivable Adversarial Attacks
稀疏的和不可感知的對抗攻擊
作者：Francesco Croce, Matthias Hein
論文鏈接：https://arxiv.org/abs/1909.05040

 

本文章首發在 極市計算機視覺技術社區

微信公衆號: 極市平臺（ID: extrememart ）
每天推送最新CV乾貨