【新智元导读】人工智能顶级会议CVPR刚刚公布了最佳论文，谷歌、Facebook和英伟达也随后公布了自家发表的论文共计104篇，本文列出了三家大厂论文的完整列表。

本周，在美国加利福尼亚州长滩举办了CVPR 2019（计算机视觉和模式识别会议），这是一次重要的年度计算机视觉活动，包括主要会议和几个共同举办的研讨会和教程。

本次CVPR参会人数超过6500，CVPR 2018超过6000人；CVPR 2017年超过5000人…如果单纯只看数字，以目前的增长趋势来看，预计再过16年参会人数可以突破100万。

据统计，今年共计1300篇论文被CVPR 2019接收，相比去年被接收论文数量增加了32.8%，今年的接收率为25.2%。论文提交数量是5165篇，相比CVPR 2018增加了56%。

对比CVPR 2018和CVPR 2019的论文关键词，最热的仍然是图像、检测、3d、对象、视频、分割、对抗、识别、视觉等。

CVPR 2019：谷歌论文完整列表

作为计算机视觉研究领域的领导者和白金赞助商，谷歌有超过250名员工出席会议，并组织和参与了多个研讨会。

在现场的朋友可以和谷歌研究人员聊聊，他们正在积极研究下一代智能系统，这些系统利用应用于各种机器感知领域的最新机器学习技术。还可以讨论和演示最近的一些努力，包括预测行人运动的技术，Open Images V5数据集等等。

不在现场的朋友，这里有一份完整谷歌CVPR 2019录取论文：

Oral

论文标题：Relational Action Forecasting

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Relational_Action_Forecasting_CVPR_2019_paper.html

作者：Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy, Cordelia Schmid

论文标题：Pushing the Boundaries of View Extrapolation With Multiplane Images

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Srinivasan_Pushing_the_Boundaries_of_View_Extrapolation_With_Multiplane_Images_CVPR_2019_paper.html

作者：Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, Noah Snavely

论文标题：Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Auto-DeepLab_Hierarchical_Neural_Architecture_Search_for_Semantic_Image_Segmentation_CVPR_2019_paper.html

作者：Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan L. Yuille, Li Fei-Fei

论文标题：AutoAugment: Learning Augmentation Strategies From Data

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Cubuk_AutoAugment_Learning_Augmentation_Strategies_From_Data_CVPR_2019_paper.html

作者：Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le

论文标题：DeepView: View Synthesis With Learned Gradient Descent

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Flynn_DeepView_View_Synthesis_With_Learned_Gradient_Descent_CVPR_2019_paper.html

作者：John Flynn, Michael Broxton, Paul Debevec, Matthew DuVall, Graham Fyffe, Ryan Overbeck, Noah Snavely, Richard Tucker

论文标题：Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Normalized_Object_Coordinate_Space_for_Category-Level_6D_Object_Pose_and_CVPR_2019_paper.html

作者：He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas

论文标题：Do Better ImageNet Models Transfer Better?

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Kornblith_Do_Better_ImageNet_Models_Transfer_Better_CVPR_2019_paper.html

作者：Simon Kornblith, Jonathon Shlens, Quoc V. Le

论文标题：TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Huang_TextureNet_Consistent_Local_Parametrizations_for_Learning_From_High-Resolution_Signals_on_CVPR_2019_paper.html

作者：Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Niessner, Leonidas J. Guibas

论文标题：Diverse Generation for Multi-Agent Sports Games

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Yeh_Diverse_Generation_for_Multi-Agent_Sports_Games_CVPR_2019_paper.html

作者：Raymond A. Yeh, Alexander G. Schwing, Jonathan Huang, Kevin Murphy

论文标题：Occupancy Networks: Learning 3D Reconstruction in Function Space

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Mescheder_Occupancy_Networks_Learning_3D_Reconstruction_in_Function_Space_CVPR_2019_paper.html

作者：Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger

论文标题：A General and Adaptive Robust Loss Function

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Barron_A_General_and_Adaptive_Robust_Loss_Function_CVPR_2019_paper.html

作者：Jonathan T. Barron

论文标题：Learning the Depths of Moving People by Watching Frozen People

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Learning_the_Depths_of_Moving_People_by_Watching_Frozen_People_CVPR_2019_paper.html

作者：Zhengqi Li, Tali Dekel, Forrester Cole, Richard Tucker, Noah Snavely, Ce Liu, William T. Freeman

_(CVPR 2019 Best Paper Honorable Mention)_

论文标题：Composing Text and Image for Image Retrieval - an Empirical Odyssey

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Vo_Composing_Text_and_Image_for_Image_Retrieval_-_an_Empirical_CVPR_2019_paper.html

作者：Nam Vo, Lu Jiang, Chen Sun, Kevin Murphy, Li-Jia Li, Li Fei-Fei, James Hays

论文标题：Learning to Synthesize Motion Blur

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Brooks_Learning_to_Synthesize_Motion_Blur_CVPR_2019_paper.html

作者：Tim Brooks, Jonathan T. Barron

论文标题：Neural Rerendering in the Wild

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Meshry_Neural_Rerendering_in_the_Wild_CVPR_2019_paper.html

作者：Moustafa Meshry, Dan B. Goldman, Sameh Khamis, Hugues Hoppe, Rohit Pandey, Noah Snavely, Ricardo Martin-Brualla

论文标题：Neural Illumination: Lighting Prediction for Indoor Environments

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Song_Neural_Illumination_Lighting_Prediction_for_Indoor_Environments_CVPR_2019_paper.html

作者：Shuran Song, Thomas Funkhouser

论文标题：Unprocessing Images for Learned Raw Denoising

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Brooks_Unprocessing_Images_for_Learned_Raw_Denoising_CVPR_2019_paper.html

作者：Tim Brooks, Ben Mildenhall, Tianfan Xue, Jiawen Chen, Dillon Sharlet, Jonathan T. Barron

Posters

论文标题：Co-Occurrent Features in Semantic Segmentation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.html

作者：Hang Zhang, Han Zhang, Chenguang Wang, Junyuan Xie

论文标题：CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_CrDoCo_Pixel-Level_Domain_Transfer_With_Cross-Domain_Consistency_CVPR_2019_paper.html

作者：Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang

论文标题：Im2Pencil: Controllable Pencil Illustration From Photographs

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Im2Pencil_Controllable_Pencil_Illustration_From_Photographs_CVPR_2019_paper.html

作者：Yijun Li, Chen Fang, Aaron Hertzmann, Eli Shechtman, Ming-Hsuan Yang

论文标题：Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Mao_Mode_Seeking_Generative_Adversarial_Networks_for_Diverse_Image_Synthesis_CVPR_2019_paper.html

作者：Qi Mao, Hsin-Ying Lee, Hung-Yu Tseng, Siwei Ma, Ming-Hsuan Yang

论文标题：Revisiting Self-Supervised Visual Representation Learning

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Kolesnikov_Revisiting_Self-Supervised_Visual_Representation_Learning_CVPR_2019_paper.html

作者：Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer

论文标题：Scene Graph Generation With External Knowledge and Image Reconstruction

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Gu_Scene_Graph_Generation_With_External_Knowledge_and_Image_Reconstruction_CVPR_2019_paper.html

作者：Jiuxiang Gu, Handong Zhao, Zhe Lin, Sheng Li, Jianfei Cai, Mingyang Ling

论文标题：Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Fang_Scene_Memory_Transformer_for_Embodied_Agents_in_Long-Horizon_Tasks_CVPR_2019_paper.html

作者：Kuan Fang, Alexander Toshev, Li Fei-Fei, Silvio Savarese

论文标题：Spatially Variant Linear Representation Models for Joint Filtering

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Pan_Spatially_Variant_Linear_Representation_Models_for_Joint_Filtering_CVPR_2019_paper.html

作者：Jinshan Pan, Jiangxin Dong, Jimmy S. Ren, Liang Lin, Jinhui Tang, Ming-Hsuan Yang

论文标题：Target-Aware Deep Tracking

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Target-Aware_Deep_Tracking_CVPR_2019_paper.html

作者：Xin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang

论文标题：Temporal Cycle-Consistency Learning

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Dwibedi_Temporal_Cycle-Consistency_Learning_CVPR_2019_paper.html

作者：Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

论文标题：Depth-Aware Video Frame Interpolation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Bao_Depth-Aware_Video_Frame_Interpolation_CVPR_2019_paper.html

作者：Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, Ming-Hsuan Yang

论文标题：MnasNet: Platform-Aware Neural Architecture Search for Mobile

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Tan_MnasNet_Platform-Aware_Neural_Architecture_Search_for_Mobile_CVPR_2019_paper.html

作者：Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, Quoc V. Le

论文标题：A Compact Embedding for Facial Expression Similarity

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Vemulapalli_A_Compact_Embedding_for_Facial_Expression_Similarity_CVPR_2019_paper.html

作者：Raviteja Vemulapalli, Aseem Agarwala

论文标题：Contrastive Adaptation Network for Unsupervised Domain Adaptation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Kang_Contrastive_Adaptation_Network_for_Unsupervised_Domain_Adaptation_CVPR_2019_paper.html

作者：Guoliang Kang, Lu Jiang, Yi Yang, Alexander G. Hauptmann

论文标题：DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/LeGendre_DeepLight_Learning_Illumination_for_Unconstrained_Mobile_Mixed_Reality_CVPR_2019_paper.html

作者：Chloe LeGendre, Wan-Chun Ma, Graham Fyffe, John Flynn, Laurent Charbonnel, Jay Busch, Paul Debevec

论文标题：Detect-To-Retrieve: Efficient Regional Aggregation for Image Search

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Teichmann_Detect-To-Retrieve_Efficient_Regional_Aggregation_for_Image_Search_CVPR_2019_paper.html

作者：Marvin Teichmann, Andre Araujo, Menglong Zhu, Jack Sim

论文标题：Fast Object Class Labelling via Speech

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Gygli_Fast_Object_Class_Labelling_via_Speech_CVPR_2019_paper.html

作者：Michael Gygli, Vittorio Ferrari

论文标题：Learning Independent Object Motion From Unlabelled Stereoscopic Videos

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Cao_Learning_Independent_Object_Motion_From_Unlabelled_Stereoscopic_Videos_CVPR_2019_paper.html

作者：Zhe Cao, Abhishek Kar, Christian Hane, Jitendra Malik

论文标题：Peeking Into the Future: Predicting Future Person Activities and Locations in Videos

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Liang_Peeking_Into_the_Future_Predicting_Future_Person_Activities_and_Locations_CVPR_2019_paper.html

作者：Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander G. Hauptmann, Li Fei-Fei

论文标题：SpotTune: Transfer Learning Through Adaptive Fine-Tuning

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Guo_SpotTune_Transfer_Learning_Through_Adaptive_Fine-Tuning_CVPR_2019_paper.html

作者：Yunhui Guo, Honghui Shi, Abhishek Kumar, Kristen Grauman, Tajana Rosing, Rogerio Feris

论文标题：NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Ghiasi_NAS-FPN_Learning_Scalable_Feature_Pyramid_Architecture_for_Object_Detection_CVPR_2019_paper.html

作者：Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le

论文标题：Class-Balanced Loss Based on Effective Number of Samples

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Cui_Class-Balanced_Loss_Based_on_Effective_Number_of_Samples_CVPR_2019_paper.html

作者：Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie

论文标题：FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Voigtlaender_FEELVOS_Fast_End-To-End_Embedding_Learning_for_Video_Object_Segmentation_CVPR_2019_paper.html

作者：Paul Voigtlaender, Yuning Chai, Florian Schroff, Hartwig Adam, Bastian Leibe, Liang-Chieh Chen

论文标题：Inserting Videos Into Videos

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Lee_Inserting_Videos_Into_Videos_CVPR_2019_paper.html

作者：Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang

论文标题：Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Pandey_Volumetric_Capture_of_Humans_With_a_Single_RGBD_Camera_via_CVPR_2019_paper.html

作者：Rohit Pandey, Anastasia Tkach, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Ricardo Martin-Brualla, Andrea Tagliasacchi, George Papandreou, Philip Davidson, Cem Keskin, Shahram Izadi, Sean Fanello

论文标题：You Look Twice: GaterNet for Dynamic Filter Selection in CNNs

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_You_Look_Twice_GaterNet_for_Dynamic_Filter_Selection_in_CNNs_CVPR_2019_paper.html

作者：Zhourong Chen, Yang Li, Samy Bengio, Si Si

论文标题：Interactive Full Image Segmentation by Considering All Regions Jointly

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Agustsson_Interactive_Full_Image_Segmentation_by_Considering_All_Regions_Jointly_CVPR_2019_paper.html

作者：Eirikur Agustsson, Jasper R. R. Uijlings, Vittorio Ferrari

论文标题：Large-Scale Interactive Object Segmentation With Human Annotators

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Benenson_Large-Scale_Interactive_Object_Segmentation_With_Human_Annotators_CVPR_2019_paper.html

作者：Rodrigo Benenson, Stefan Popov, Vittorio Ferrari

论文标题：Self-Supervised GANs via Auxiliary Rotation Loss

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Self-Supervised_GANs_via_Auxiliary_Rotation_Loss_CVPR_2019_paper.html

作者：Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lučić, Neil Houlsby

论文标题：Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/James_Sim-To-Real_via_Sim-To-Sim_Data-Efficient_Robotic_Grasping_via_Randomized-To-Canonical_Adaptation_Networks_CVPR_2019_paper.html

作者：Stephen James, Paul Wohlhart, Mrinal Kalakrishnan, Dmitry Kalashnikov, Alex Irpan, Julian Ibarz, Sergey Levine, Raia Hadsell, Konstantinos Bousmalis

论文标题：Using Unknown Occluders to Recover Hidden Scenes

论文地址：

http://openaccess.thecvf.com/content_CVPR_2019/html/Yedidia_Using_Unknown_Occluders_to_Recover_Hidden_Scenes_CVPR_2019_paper.html

作者：Adam B. Yedidia, Manel Baradad, Christos Thrampoulidis, William T. Freeman, Gregory W. Wornell

CVPR 2019：Facebook论文完整列表

Facebook研究人员和工程师也在整个星期内提供辅导和参与研讨会，包括由研究科学家Cristian Canton和首席AI科学家Yann LeCun共同组织的DeepVision研讨会。

Facebook还组织了第一个全球挑战计算机视觉（CV4GC）研讨会，探索计算机视觉可用于解决全球问题的新方法，如疾病预防，基础设施绘图等。

不在现场的朋友，这里有一份完整Facebook CVPR 2019录取论文：

论文标题：2.5D Visual Sound

论文链接：

https://research.fb.com/publications/2-5d-visual-sound/

论文作者：Ruohan Gao and Kristen Grauman

论文标题：3D Human Pose Estimation in Video with Temporal Convolutions and Semisupervised Training

论文链接：

https://research.fb.com/publications/3d-human-pose-estimation-in-video-with-temporal-convolutions-and-semi-supervised-training/

论文作者：Dario Pavllo, Christoph Feichtenhofer, David Grangier, and Michael Auli

论文标题：Activity Driven Weakly Supervised Object Detection

Code地址：

https://github.com/facebookresearch/astmt

论文作者：Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, and Vignesh Ramanathan

论文标题：Adversarial Inference for Multi-Sentence Video Description

论文链接：

https://research.fb.com/publications/adversarial-inference-for-multi-sentence-video-description/

论文作者：Jae Sung Park, Marcus Rohrbach, Trevor Darrell, and Anna Rohrbach

论文标题：Attentive Single-Tasking of Multiple Tasks

论文作者：Kevis-Kokitsi Maninis, Ilija Radosavovic, and Iasonas Kokkinos

论文标题：ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation

论文链接：

https://research.fb.com/publications/chamnet-towards-efficient-network-design-through-platform-aware-model-adaptation/

论文作者：Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Peter Vajda, Matt Uyttendaele, and Niraj K. Jha

论文标题：Cycle-Consistency for Robust Visual Question Answering

论文链接：

https://research.fb.com/publications/cycle-consistency-for-robust-visual-question-answering/

论文作者：Meet Shah, Xinlei Chen, Marcus Rohrbach, and Devi Parikh

论文标题：DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

论文作者：Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove

论文标题：Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search

论文作者：Abhimanyu Dubey, Laurens van der Maaten, Zeki Yalniz, Yixuan Li, and Dhruv Mahajan

论文标题：DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition

论文链接：

https://research.fb.com/publications/dmc-net-generating-discriminative-motion-cues-for-fast-compressed-video-action-recognition/

论文作者：Zheng Shou, Xudong Lin, Yannis Kalantidis, Laura Sevilla-Lara, Marcus Rohrbach, Shih-Fu Chang, and Zhicheng Yan

论文标题：Embodied Question Answering in Photorealistic Environments with Point Cloud Perception

论文链接：

https://research.fb.com/publications/embodied-question-answering-in-photorealistic-environments-with-point-cloud-perception/

论文作者：Erik Wijmans, Samyak Datta, Oleksandr Maksymets, Abhishek Das, Georgia Gkioxari, Stefan Lee, Irfan Essa, Devi Parikh, and Dhruv Batra

论文标题：Engaging Image Captioning via Personality

论文链接：

https://research.fb.com/publications/engaging-image-captioning-via-personality/

论文作者：Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, and Jason Weston

论文标题：Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

论文作者：Zhenpei Yang, Jeffrey Z. Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman, and Qixing Huang

论文标题：FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

论文链接：

https://research.fb.com/publications/fbnet-hardware-aware-efficient-convnet-design-via-differentiable-neural-architecture-search

论文作者：Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, and Kurt Keutzer

论文标题：Feature Denoising for Improving Adversarial Robustness

论文链接：

https://research.fb.com/publications/feature-denoising-for-improving-adversarial-robustness

论文作者：Cihang Xie, Yuxin Wu, Laurens van der Maaten, Alan Yuille, and Kaiming He

论文标题：Graph-Based Global Reasoning Networks

论文链接：

https://research.fb.com/publications/graph-based-global-reasoning-networks/

论文作者：Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan, Shuicheng Yan, Jiashi Feng, and Yannis Kalantidis

论文标题：Grounded Video Description

论文链接：

https://research.fb.com/publications/grounded-video-description/

论文作者：Luowei Zhou, Yannis Kalantidis, Xinlei Chen, Jason J. Corso, and Marcus Rohrbach

Improved Road Connectivity by Joint Learning of Orientation and Segmentation

Anil Batra, Suriya Singh, Guan Pang, Saikat Basu, C.V. Jawahar, and Manohar Paluri

论文标题：Inverse Cooking: Recipe Generation from Food Images

论文链接：

https://research.fb.com/publications/inverse-cooking-recipe-generation-from-food-images

论文作者：Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, and Adriana Romero

论文标题：Inverse Path Tracing for Joint Material and Lighting Estimation

论文链接：

https://research.fb.com/publications/inverse-path-tracing-for-joint-material-and-lighting-estimation/

论文作者：Dejan Azinovic, Tzu-Mao Li, Anton Kaplanyan, and Matthias Niessner

论文标题：Kernel Transformer Networks for Compact Spherical Convolution

论文链接：

https://research.fb.com/publications/kernel-transformer-networks-for-compact-spherical-convolution/

论文作者：Yu-Chuan Su and Kristen Grauman

论文标题：Large-Scale Weakly Supervised Pretraining for Video Action Recognition

论文链接：

https://research.fb.com/publications/large-scale-weakly-supervised-pre-training-for-video-action-recognition/

论文作者：Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, and Dhruv Mahajan

论文标题：LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds

论文作者：Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos, and Yaser Sheikh

论文标题：Less Is More: Learning Highlight Detection from Video Duration

论文作者：Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, and Kristen Grauman

论文标题：Long-Term Feature Banks for Detailed Video Understanding

论文作者：Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, and Ross Girshick

论文标题：LVIS: A Data Set for Large Vocabulary Instance Segmentation

论文作者：Agrim Gupta, Piotr Dollár, and Ross Girshick

论文标题：Multi-Target Embodied Question Answering

论文作者：Licheng Yu, Xinlei Chen, Georgia Gkioxari, Mohit Bansal, Tamara Berg, and Dhruv Batra

论文标题：Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors

论文作者：Yedid Hoshen and Jitendra Malik

论文标题：Panoptic Feature Pyramid Networks

论文链接：

https://ai.facebook.com/micro_site/url/?click_creative_path

论文标题：Panoptic Segmentation

论文链接：

https://research.fb.com/publications/panoptic-segmentation/

论文作者：Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, and Piotr Dollár

论文标题：Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

论文链接：

https://research.fb.com/publications/reducing-uncertainty-in-undersampled-mri-reconstruction-with-active-acquisition/

论文作者：Zizhao Zhang, Adriana Romero, Matthew J. Muckley, Pascal Vincent, Lin Yang, and Michal Drozdzal

论文标题：Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking

论文作者：Jae Shin Yoon, Takaaki Shiratori, Shoou-I Yu, and Hyun Soo Park

论文标题：Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues

论文链接：

https://research.fb.com/publications/slim-densepose-thrifty-learning-from-sparse-annotations-and-motion-cues/

论文作者：Natalia Neverova, James Thewlis, Riza Alp Güler, Iasonas Kokkinos, and Andrea Vedaldi

论文标题：StereoDRNet: Dilated Residual StereoNet

论文作者：Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, and Henry Fuchs

论文标题：Strand-Accurate Multi-View Hair Capture

论文作者：Giljoo Nam, Chenglei Wu, Min H. Kim, and Yaser Sheikh

论文标题：Thinking Outside the Pool: Active Training Image Creation for Relative Attributes

论文作者：Aron Yu and Kristen Grauman

论文标题：Towards VQA Models That Can Read

论文链接：

https://research.fb.com/publications/towards-vqa-models-that-can-read/

论文作者：Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach

CVPR 2019：英伟达论文完整列表

英伟达列出了全部被接收的论文，分为Oral和Poster两个部分。

Oral

论文标题：Semantic Image Synthesis With Spatially-Adaptive Normalization

论文地址：

https://arxiv.org/abs/1903.07291

论文作者：Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

源码：https://github.com/NVlabs/SPADE

论文标题：STEP: Spatio-Temporal Progressive Learning for Video Action Detection

论文地址：

https://arxiv.org/abs/1904.09288

论文作者：Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz

论文标题：Efficient Video Classification Using Fewer Frames

论文地址：

https://arxiv.org/abs/1902.10640

论文作者：Shweta Bhardwaj, Mukundhan Srinivasan, Mitesh M. Khapra

论文标题：Joint Discriminative and Generative Learning for Person Re-identification

论文地址：

https://arxiv.org/abs/1904.07223

论文作者：Zhedong Zheng, Xiaodong Yang, Zhiding Yu, Liang Zheng, Yi Yang, Jan Kautz

论文标题：A Style-Based Generator Architecture for Generative Adversarial Networks

论文地址：

https://arxiv.org/abs/1812.04948

论文作者：Tero Karras, Samuli Laine, Timo Aila

论文标题：PlaneRCNN: 3D Plane Detection and Reconstruction from a Single View

论文地址：

https://arxiv.org/abs/1812.04072

论文作者：Chen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, Jan Kautz

论文标题：Barrage of Random Transforms for Adversarially Robust Defense

论文地址：

openaccess.thecvf.com/content_CVPR_2019/papers/Raff_Barrage_of_Random_Transforms_for_Adversarially_Robust_Defense_CVPR_2019_paper.pdf

论文作者：Edward Raff; Jared Sylvester; Steven Forsyth; Mark McLean

论文标题：Improving Semantic Segmentation via Video Propagation and Label Relaxation

论文地址：

https://arxiv.org/abs/1812.01593

论文作者：Yi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro

源码：https://nv-adlr.github.io/publication/2018-Segmentation

论文标题：CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

论文地址：

https://arxiv.org/abs/1903.09254

论文作者：Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwang

论文标题：Neural RGB -> D Sensing: Depth and Uncertainty from a Video Camera

论文地址：

https://arxiv.org/abs/1901.02571

论文作者：Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan, Jan Kautz

论文标题：Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

论文地址：

https://arxiv.org/abs/1904.07934

论文作者：David Acuna, Amlan Kar, Sanja Fidler

Posters

论文标题：SCOPS: Self-Supervised Co-Part Segmentation

论文地址：

https://arxiv.org/abs/1905.01298

论文作者：Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, and Jan Kautz

论文标题：Learning Linear Transformations for Fast Image and Video Style Transfer

论文地址：

https://arxiv.org/abs/1808.04537

论文作者：Xueting Li, Sifei Liu, Jan Kautz, Ming-Hsuan Yang

论文标题：Object Discovery in Videos as Foreground Motion Clustering

论文地址：

https://arxiv.org/abs/1812.02772

论文作者：Christopher Xie, Yu Xiang, Zaid Harchaoui, Dieter Fox

论文标题：Pixel-Adaptive Convolutional Neural Networks

论文地址：

https://arxiv.org/abs/1904.05373

论文作者：Hang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, Jan Kautz

论文标题：Importance Estimation for Neural Network Pruning

论文地址：

jankautz.com/publications/Importance4NNPruning_CVPR19.pdf

论文作者：Pavlo Molchanov, Arun Mallya, Stephen Tyree, Iuri Frosio, Jan Kautz

论文标题：Graphical Contrastive Losses for Scene Graph Parsing

论文地址：

https://arxiv.org/abs/1903.02728

论文作者：Ji Zhang, Kevin J. Shih, Ahmed Elgammal, Andrew Tao, Bryan Catanzaro

论文标题：Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

论文地址：

https://arxiv.org/abs/1805.09806

论文作者：Anurag Ranjan, Varun Jampani, Lukas Balles, Kihwan Kim, Deqing Sun, Jonas Wulff, Michael J. Black

论文标题：Large-scale Distributed Second-order Optimization Using Kronecker-factored Approximate Curvature for Deep Convolutional Neural Networks

论文地址：

https://arxiv.org/abs/1811.12019

论文作者：Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka

论文标题：Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments

论文地址：

https://arxiv.org/abs/1903.05690

论文作者：Xueting Li, Sifei Liu, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz