【AI前沿动态】ICCV 2019|70 篇论文抢先读，含目标检测／自动驾驶／GCN／等（提供PDF下载）

Oral 论文

10.Learnable Triangulation of Human Pose
作者：Karim Iskakov, Egor Burkov, Victor Lempitsky, Yury Malkov
论文链接：https://arxiv.org/abs/1905.05754
Github链接：https://github.com/karfly/learnable-triangulation-pytorch
项目链接：https://saic-violet.github.io/learnable-triangulation/

9.Learning Implicit Generative Models by Matching Perceptual Features
作者：Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin
论文链接：https://arxiv.org/abs/1904.02762v1

8.COCO-GAN: Generation by Parts via Conditional Coordinating
作者：Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen
论文链接：https://arxiv.org/abs/1904.00284
Github链接：https://github.com/hubert0527/COCO-GAN
项目链接：https://hubert0527.github.io/COCO-GAN/

7.SlowFast Networks for Video Recognition
作者：Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He
论文链接：https://arxiv.org/abs/1812.03982

6.Exploring Randomly Wired Neural Networks for Image Recognition
作者：Saining Xie, Alexander Kirillov, Ross Girshick, and Kaiming He
论文链接：https://arxiv.org/abs/1904.01569

5.Can GCNs Go as Deep as CNNs?
作者：Guohao Li, Matthias Müller, Ali Thabet, Bernard Ghanem
论文链接：https://arxiv.org/abs/1904.03751
Github链接：https://github.com/lightaime/deep_gcns

4.Deep SR-ITM: Joint Learning of Super-resolution and Inverse Tone-Mapping for 4K UHD HDR Applications
作者：Soo Ye Kim, Jihyong Oh, Munchurl Kim
论文链接：https://arxiv.org/abs/1904.11176

3.Meta-Sim Learning to Generate Synthetic Datasets
作者：Amlan Kar, Aayush Prakash, Ming-Yu Liu, Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler
论文链接：https://arxiv.org/abs/1904.11621
项目链接：https://nv-tlabs.github.io/meta-sim/

2.Deep HoughVoting for 3D Object Detection in Point Clouds
作者：Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas
论文链接：https://arxiv.org/abs/1904.09664

1.Variational Adversarial Active Learning
作者：Samarth Sinha, Sayna Ebrahimi, Trevor Darrell
论文链接：https://arxiv.org/abs/1904.00370

 其他论文

1.Model Vulnerability to Distributional Shifts over Image Transformation Sets
作者：Riccardo Volpi, Vittorio Murino
论文链接：https://arxiv.org/abs/1903.11900
Github链接：https://github.com/ricvolpi/domain-shift-robustness

2.Coherent Semantic Attention for Image Inpainting
作者：Hongyu Liu, Bin Jiang, Yi Xiao, Chao Yang
论文链接：https://arxiv.org/abs/1905.12384

3.Learning to Paint with Model-based Deep Reinforcement Learning
作者：Zhewei Huang, Wen Heng, Shuchang Zhou
论文链接：https://arxiv.org/abs/1903.04411
Github链接：https://github.com/hzwer/ICCV2019-LearningToPaint

4.LayoutVAE: Stochastic Scene Layout Generation from a Label Set
作者：Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
论文链接：https://arxiv.org/abs/1907.10719

5.Co-Evolutionary Compression for Unpaired Image Translation
作者：Han Shu, Yunhe Wang, Xu Jia, Kai Han, Hanting Chen, Chunjing Xu, Qi Tian, Chang Xu
论文链接：https://arxiv.org/abs/1907.10804

6.Enhancing Adversarial Example Transferability with an Intermediate Level Attack
作者：Qian Huang, Isay Katsman, Horace He, Zeqi Gu, Serge Belongie, Ser-Nam Lim
论文链接：https://arxiv.org/abs/1907.10823

7.Simultaneous multi-view instance detection with learned geometric soft-constraints
作者：Ahmed Samy Nassar, Sebastien Lefevre, Jan D. Wegner
论文链接：https://arxiv.org/abs/1907.10892

8.Gated2Depth: Real-time Dense Lidar from Gated Images
作者：Tobias Gruber, Frank Julca-Aguilar,Mario Bijelic,Werner Ritter,Klaus Dietmayer,Felix Heide
论文链接：

https://www.cs.princeton.edu/~fheide/papers/Gated2Depth_preprint.pdf

9.Counting with Focus for Free
作者：Zenglin Shi, Pascal Mettes, Cees G. M. Snoek
论文链接：https://arxiv.org/abs/1903.12206

10.PU-GAN: a Point Cloud Upsampling Adversarial Network
作者：Ruihui Li, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
论文链接：https://arxiv.org/abs/1907.10844

11.Moment Matching for Multi-Source Domain Adaptation
作者：Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang
论文链接：https://arxiv.org/abs/1812.01754

12.3D-RelNet: Joint Object and Relational Network for 3D Prediction
作者：Nilesh Kulkarni, Ishan Misra, Shubham Tulsiani, Abhinav Gupta
论文链接：https://arxiv.org/pdf/1906.02729.pdf

13.Learning Compositional Representations for Few-Shot Recognition
作者：Pavel Tokmakov, Yuxiong Wang, Martial Hebert
论文链接：https://sites.google.com/view/comprepr/home

14.Digging Into Self-Supervised Monocular Depth Estimation
作者：Clement Godard, Oisin Mac Aodha, Michael Firman, Gabriel Brostow
论文链接：https://arxiv.org/pdf/1806.01260.pdf

15.Deep Interpretable Non-Rigid Structure from Motion
作者：Chen Kong, Simon Lucey
论文链接：https://arxiv.org/pdf/1902.10840.pdf

16.PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
作者：Nicholas Rhinehart, Rowan McAllister, Kris Kitani, Sergey Levine
论文链接：https://arxiv.org/pdf/1905.01296.pdf
项目链接：https://sites.google.com/view/precog

17.Lifelong GAN: Continual Learning for Conditional Image Generation
作者：Mengyao Zhai, Lei Chen, Fred Tung, Jiawei He, Megha Nawhal, Greg Mori
论文链接：https://arxiv.org/abs/1907.10107

18.Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
作者：Keren Ye, Mingda Zhang, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent
论文链接：https://arxiv.org/abs/1907.10164

19.Towards Adversarially Robust Object Detection
作者：Haichao Zhang, Jianyu Wang
论文链接：https://arxiv.org/abs/1907.10310

20.6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
作者：Arsalan Mousavian, Clemens Eppner, Dieter Fox
论文链接：https://arxiv.org/abs/1905.10520

21.Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction
作者：Luca Anthony Thiede, Pratik Prabhanjan Brahma
论文链接：https://arxiv.org/abs/1907.10178

22.DAFL: Data-Free Learning of Student Networks
作者：Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, Qi Tian
论文链接：https://arxiv.org/abs/1904.01186

23.Multi-adversarial Faster-RCNN for Unrestricted Object Detection
作者：Zhenwei He, Lei Zhang
论文链接：https://arxiv.org/abs/1907.10343

24.Boosting Few-Shot Visual Learning with Self-Supervision
作者：Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord
论文链接：https://arxiv.org/abs/1906.05186

25.A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
作者：Heng Yang, Luca Carlone
论文链接：https://arxiv.org/abs/1905.12536

26.Embodied Visual Recognition
作者：Jianwei Yang，Zhile Ren，Mingze Xu，Xinlei Chen，David Crandall，Devi Parikh，Dhruv Batra
项目链接：https://www.cc.gatech.edu/~jyang375/evr.html

27.Rethinking ImageNet Pre-training
作者：Kaiming He, Ross Girshick, and Piotr Dollár
论文链接：https://arxiv.org/abs/1811.08883

28.TensorMask: A Foundation for Dense Object Segmentation
作者：Xinlei Chen, Ross Girshick, Kaiming He, and Piotr Dollár
论文链接：https://arxiv.org/abs/1903.12174

29.FCOS: Fully Convolutional One-Stage Object Detectio
作者：Zhi Tian, Chunhua Shen, Hao Chen, Tong He
论文链接：https://arxiv.org/abs/1904.01355
Github链接：https://github.com/tianzhi0549/FCOS/

30.3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition
作者：Zhe Liu, Shunbo Zhou, Chuanzhe Suo, Yingtian Liu, Hesheng Wang, Yun-Hui Liu
论文链接：https://arxiv.org/abs/1812.07050

31.Selectivity or Invariance: Boundary-aware Salient Object Detection
作者：Jinming Su, Jia Li1, Yu Zhang, Changqun Xia and Yonghong Tian
论文链接：https://arxiv.org/pdf/1812.10066.pdf

32.Joint Monocular 3D Detection and Tracking
作者：Hou-Ning Hu, Qizhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu
论文链接：https://arxiv.org/abs/1811.10742
Github链接：https://github.com/ucbdrive/3d-vehicle-tracking
项目链接：https://eborboihuc.github.io/Mono-3DT/?fbclid=IwAR1maTNHE5z-vEwAJKIcNEpbMWwBcjWJQ0gEHOwHB-u51w5dfeiZNCh0y-U

33.Point-to-Point Video Generation
作者：Tsun-Hsuan Wang, Yen-Chi Cheng, Chieh Hubert Lin, Hwann-Tzong Chen, Min Sun
论文链接：https://arxiv.org/abs/1904.02912
Github链接：https://github.com/charlescheng0117/p2pvg
项目链接：https://zswang666.github.io/P2PVG-Project-Page/?fbclid=IwAR1Cr-T54keo5zzaWLQuYNQMcPoKzXGr6-YrTDoauW6Hb5bOSwgluZQ3fIE

34.Creativity Inspired Zero-Shot Learning
作者：Mohamed Elhoseiny, Mohamed Elfeki
论文链接：https://arxiv.org/abs/1904.01109

35.HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
作者：Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, Josef Sivic
论文链接：https://arxiv.org/abs/1906.03327

36.Correlation Congruence for Knowledge Distillation
作者：Baoyun Peng, Xiao Jin, Jiaheng Liu, Shunfeng Zhou, Yichao Wu, Yu Liu, Dongsheng Li, Zhaoning Zhang
论文链接：https://arxiv.org/abs/1904.018029

37.VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
作者：Xin Wang, Jiawei Wu, Junkun Chen, Lei Li, Yuan-Fang Wang, William Yang Wang
论文链接：https://arxiv.org/abs/1904.03493
项目链接：http://vatex.org/main/index.html

38.Episodic Training for Domain Generalization
作者：Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales
论文链接：https://arxiv.org/abs/1902.00113

39.Exploring the Limitations of Behavior Cloning for Autonomous Driving
作者：Felipe Codevilla, Eder Santana, Antonio M. López, Adrien Gaidon
论文链接：https://arxiv.org/abs/1904.08980
Github链接：https://github.com/felipecode/coiltraine/blob/master/docs/exploring_limitations.md

40.GarNet: A Two-stream Network for Fast and Accurate 3D Cloth Draping
作者：Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua
论文链接：https://arxiv.org/abs/1811.10983v2
项目链接：https://cvlab.epfl.ch/research/garment-simulation/garnet/

41.Tex2Shape: Detailed Full Human Body Geometry from a Single Image
作者：Thiemo Alldieck, Gerard Pons-Moll, Christian Theobalt, Marcus Magnor
论文链接：https://arxiv.org/abs/1904.08645
Github链接：https://github.com/thmoa/tex2shape

42.Semi-supervised Domain Adaptation via Minimax Entropy
作者：Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, Kate Saenko
论文链接：https://arxiv.org/abs/1904.06487

43.xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera
作者：Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino
论文链接：https://arxiv.org/abs/1907.10045

44.Canonical Surface Mapping via Geometric Cycle Consistency
作者：Nilesh Kulkarni, Abhinav Gupta, Shubham Tulsiani
论文链接：https://arxiv.org/abs/1907.10043
项目链接：https://nileshkulkarni.github.io/csm/

45.Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
作者：Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito, Kris Kitani
论文链接：https://arxiv.org/abs/1907.10008

46.U4D: Unsupervised 4D Dynamic Scene Understanding
作者：Armin Mustafa, Chris Russell, Adrian Hilton
论文链接：https://arxiv.org/abs/1907.09905

47.BMN: Boundary-Matching Network for Temporal Action Proposal Generation
作者：Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen
论文链接：https://arxiv.org/abs/1907.09702

48.Similarity-Preserving Knowledge Distillation
作者：Frederick Tung, Greg Mori
论文链接：https://arxiv.org/abs/1907.09682

49.GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
作者：Fangneng Zhan, Chuhui Xue, Shijian Lu
论文链接：https://arxiv.org/abs/1907.09653

50.Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
作者：Ya-Liang Chang, Zhe Yu Liu, Kuan-Ying Lee, Winston Hsu
论文链接：https://arxiv.org/abs/1904.10247
Github链接：https://github.com/amjltc295/Free-Form-Video-Inpainting

51.Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction
作者：Alaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, Devon Hjelm, Layla El Asri, Samira Ebrahimi Kahou, Yoshua Bengio, Graham W. Taylor
论文链接：https://arxiv.org/pdf/1811.09845.pdf

52.Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
作者：Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, Chinmay Hegde
论文链接：https://arxiv.org/abs/1904.08489

53.What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention
作者：Antonino Furnari, Giovanni Maria Farinella
论文链接：https://arxiv.org/pdf/1905.09035.pdf
Github链接：https://github.com/antoninofurnari/rulstm
项目链接：https://iplab.dmi.unict.it/rulstm/

54.nocaps: novel object captioning at scale
作者：Harsh Agrawal, Karan Desai, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, Peter Anderson
论文链接：https://arxiv.org/abs/1812.08658
项目链接：https://nocaps.org

55.ThunderNet: Towards Real-time Generic Object Detection
作者：Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, Jian Sun
论文链接：https://arxiv.org/abs/1903.11752

56.MemorizingNormality to Detect Anomaly: Memory-augmented Deep Autoencoder (MemAE) forUnsupervised Anomaly Detection
作者：Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, Anton van den Hengel
论文链接：https://arxiv.org/abs/1904.02639
Github链接：https://github.com/donggong1/memae-anomaly-detection
项目链接：https://donggong1.github.io/anomdec-memae.html

57.Scene GraphPrediction with Limited Labels
作者：Vincent S. Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Re, Li Fei-Fei
论文链接：https://arxiv.org/abs/1904.11622

58.Ego-Pose Estimation and Forecasting as Real-Time PD Control
作者：Ye Yuan, Kris Kitani
论文链接：https://arxiv.org/abs/1906.03173

59.The Trajectron: Probabilistic Multi-Agent Trajectory Modeling withDynamic Spatiotemporal Graphs
作者：Boris Ivanovic, Marco Pavone
论文链接：https://arxiv.org/abs/1810.05993

60.End-to-End Learning of Representations for Asynchronous Event-BasedData
作者：Daniel Gehrig, Antonio Loquercio, Konstantinos G. Derpanis, Davide Scaramuzza
论文链接：https://arxiv.org/abs/1904.08245

转自：智车科技