人工智能頂級會議CVPR剛剛公布了最佳論文，谷歌、Facebook和英偉達也隨后公布了自家發表的論文共計104篇，本文列出了三家大廠論文的完整列表。

本周，在美國加利福尼亞州長灘舉辦了CVPR 2019（計算機視覺和模式識別會議），這是一次重要的年度計算機視覺活動，包括主要會議和幾個共同舉辦的研討會和教程。

本次CVPR參會人數超過9000，CVPR 2018超過6000人；CVPR 2017年超過5000人…如果單純只看數字，以目前的增長趨勢來看，預計再過16年參會人數可以突破100萬。

據統計，今年共計1300篇論文被CVPR 2019接收，相比去年被接收論文數量增加了32.8%，今年的接收率為25.2%。論文提交數量是5165篇，相比CVPR 2018增加了56%。

對比CVPR 2018和CVPR 2019的論文關鍵詞，最熱的仍然是圖像、檢測、3d、對象、視頻、分割、對抗、識別、視覺等。

CVPR 2019：谷歌論文完整列表

作為計算機視覺研究領域的領導者和白金贊助商，谷歌有超過250名員工出席會議，并組織和參與了多個研討會。

在現場的朋友可以和谷歌研究人員聊聊，他們正在積極研究下一代智能系統，這些系統利用應用于各種機器感知領域的最新機器學習技術。還可以討論和演示最近的一些努力，包括預測行人運動的技術，Open Images V5數據集等等。

不在現場的朋友，這里有一份完整谷歌CVPR 2019錄取論文：

Oral

論文標題：Relational Action Forecasting

論文地址：

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

論文標題：Pushing the Boundaries of View Extrapolation With Multiplane Images

論文地址：

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

論文標題：Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

論文地址：

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

論文標題：AutoAugment: Learning Augmentation Strategies From Data

論文地址：

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

論文標題：DeepView: View Synthesis With Learned Gradient Descent

論文地址：

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

論文標題：Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

論文地址：

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

論文標題：Do Better ImageNet Models Transfer Better?

論文地址：

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

論文標題：TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes

論文地址：

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

論文標題：Diverse Generation for Multi-Agent Sports Games

論文地址：

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

論文標題：Occupancy Networks: Learning 3D Reconstruction in Function Space

論文地址：

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

論文標題：A General and Adaptive Robust Loss Function

論文地址：

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

論文標題：Learning the Depths of Moving People by Watching Frozen People

論文地址：

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)_

論文標題：Composing Text and Image for Image Retrieval - an Empirical Odyssey

論文地址：

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

論文標題：Learning to Synthesize Motion Blur

論文地址：

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

論文標題：Neural Rerendering in the Wild

論文地址：

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

論文標題：Neural Illumination: Lighting Prediction for Indoor Environments

論文地址：

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

論文標題：Unprocessing Images for Learned Raw Denoising

論文地址：

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

論文標題：Co-Occurrent Features in Semantic Segmentation

論文地址：

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

論文標題：CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency

論文地址：

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

論文標題：Im2Pencil: Controllable Pencil Illustration From Photographs

論文地址：

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

論文標題：Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

論文地址：

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

論文標題：Revisiting Self-Supervised Visual Representation Learning

論文地址：

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

論文標題：Scene Graph Generation With External Knowledge and Image Reconstruction

論文地址：

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

論文標題：Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

論文地址：

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

論文標題：Spatially Variant Linear Representation Models for Joint Filtering

論文地址：

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

論文標題：Target-Aware Deep Tracking

論文地址：

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

論文標題：Temporal Cycle-Consistency Learning

論文地址：

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

論文標題：Depth-Aware Video Frame Interpolation

論文地址：

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

論文標題：MnasNet: Platform-Aware Neural Architecture Search for Mobile

論文地址：

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

論文標題：A Compact Embedding for Facial Expression Similarity

論文地址：

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

論文標題：Contrastive Adaptation Network for Unsupervised Domain Adaptation

論文地址：

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

論文標題：DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality

論文地址：

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

論文標題：Detect-To-Retrieve: Efficient Regional Aggregation for Image Search

論文地址：

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

論文標題：Fast Object Class Labelling via Speech

論文地址：

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

論文標題：Learning Independent Object Motion From Unlabelled Stereoscopic Videos

論文地址：

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

論文標題：Peeking Into the Future: Predicting Future Person Activities and Locations in Videos

論文地址：

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

論文標題：SpotTune: Transfer Learning Through Adaptive Fine-Tuning

論文地址：

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

論文標題：NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

論文地址：

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

論文標題：Class-Balanced Loss Based on Effective Number of Samples

論文地址：

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

論文標題：FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

論文地址：

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

論文標題：Inserting Videos Into Videos

論文地址：

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

論文標題：Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning

論文地址：

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

論文標題：You Look Twice: GaterNet for Dynamic Filter Selection in CNNs

論文地址：

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

論文標題：Interactive Full Image Segmentation by Considering All Regions Jointly

論文地址：

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

論文標題：Large-Scale Interactive Object Segmentation With Human Annotators

論文地址：

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

論文標題：Self-Supervised GANs via Auxiliary Rotation Loss

論文地址：

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 Lu?i?, Neil Houlsby

論文標題：Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks

論文地址：

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

論文標題：Using Unknown Occluders to Recover Hidden Scenes

論文地址：

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論文完整列表

Facebook研究人員和工程師也在整個星期內提供輔導和參與研討會，包括由研究科學家Cristian Canton和首席AI科學家Yann LeCun共同組織的DeepVision研討會。

Facebook還組織了第一個全球挑戰計算機視覺（CV4GC）研討會，探索計算機視覺可用于解決全球問題的新方法，如疾病預防，基礎設施繪圖等。

不在現場的朋友，這里有一份完整Facebook CVPR 2019錄取論文：

論文標題：2.5D Visual Sound

論文鏈接：

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

論文作者：Ruohan Gao and Kristen Grauman

論文標題：3D Human Pose Estimation in Video with Temporal Convolutions and Semisupervised Training

論文鏈接：

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

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

論文標題：Activity Driven Weakly Supervised Object Detection

Code地址：

https://github.com/facebookresearch/astmt

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

論文標題：Adversarial Inference for Multi-Sentence Video Description

論文鏈接：

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

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

論文標題：Attentive Single-Tasking of Multiple Tasks

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

論文標題：ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation

論文鏈接：

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

論文作者：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

論文標題：Cycle-Consistency for Robust Visual Question Answering

論文鏈接：

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

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

論文標題：DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

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

論文標題：Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search

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

論文標題：DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition

論文鏈接：

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

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

論文標題：Embodied Question Answering in Photorealistic Environments with Point Cloud Perception

論文鏈接：

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

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

論文標題：Engaging Image Captioning via Personality

論文鏈接：

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

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

論文標題：Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

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

論文標題：FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

論文鏈接：

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

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

論文標題：Feature Denoising for Improving Adversarial Robustness

論文鏈接：

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

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

論文標題：Graph-Based Global Reasoning Networks

論文鏈接：

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

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

論文標題：Grounded Video Description

論文鏈接：

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

論文作者：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

論文標題：Inverse Cooking: Recipe Generation from Food Images

論文鏈接：

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

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

論文標題：Inverse Path Tracing for Joint Material and Lighting Estimation

論文鏈接：

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

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

論文標題：Kernel Transformer Networks for Compact Spherical Convolution

論文鏈接：

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

論文作者：Yu-Chuan Su and Kristen Grauman

論文標題：Large-Scale Weakly Supervised Pretraining for Video Action Recognition

論文鏈接：

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

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

論文標題：LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds

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

論文標題：Less Is More: Learning Highlight Detection from Video Duration

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

論文標題：Long-Term Feature Banks for Detailed Video Understanding

論文作者：Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Kr?henbühl, and Ross Girshick

論文標題：LVIS: A Data Set for Large Vocabulary Instance Segmentation

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

論文標題：Multi-Target Embodied Question Answering

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

論文標題：Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors

論文作者：Yedid Hoshen and Jitendra Malik

論文標題：Panoptic Feature Pyramid Networks

論文鏈接：

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

論文標題：Panoptic Segmentation

論文鏈接：

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

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

論文標題：Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

論文鏈接：

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

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

論文標題：Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking

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

論文標題：Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues

論文鏈接：

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

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

論文標題：StereoDRNet: Dilated Residual StereoNet

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

論文標題：Strand-Accurate Multi-View Hair Capture

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

論文標題：Thinking Outside the Pool: Active Training Image Creation for Relative Attributes

論文作者：Aron Yu and Kristen Grauman

論文標題：Towards VQA Models That Can Read

論文鏈接：

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

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

CVPR 2019：英偉達論文完整列表

英偉達列出了全部被接收的論文，分為Oral和Poster兩個部分。

Oral

論文標題：Semantic Image Synthesis With Spatially-Adaptive Normalization

論文地址：

https://arxiv.org/abs/1903.07291

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

源碼：https://github.com/NVlabs/SPADE

論文標題：STEP: Spatio-Temporal Progressive Learning for Video Action Detection

論文地址：

https://arxiv.org/abs/1904.09288

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

論文標題：Efficient Video Classification Using Fewer Frames

論文地址：

https://arxiv.org/abs/1902.10640

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

論文標題：Joint Discriminative and Generative Learning for Person Re-identification

論文地址：

https://arxiv.org/abs/1904.07223

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

論文標題：A Style-Based Generator Architecture for Generative Adversarial Networks

論文地址：

https://arxiv.org/abs/1812.04948

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

論文標題：PlaneRCNN: 3D Plane Detection and Reconstruction from a Single View

論文地址：

https://arxiv.org/abs/1812.04072

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

論文標題：Barrage of Random Transforms for Adversarially Robust Defense

論文地址：

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

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

論文標題：Improving Semantic Segmentation via Video Propagation and Label Relaxation

論文地址：

https://arxiv.org/abs/1812.01593

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

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

論文標題：CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

論文地址：

https://arxiv.org/abs/1903.09254

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

論文標題：Neural RGB -> D Sensing: Depth and Uncertainty from a Video Camera

論文地址：

https://arxiv.org/abs/1901.02571

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

論文標題：Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

論文地址：

https://arxiv.org/abs/1904.07934

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

Posters

論文標題：SCOPS: Self-Supervised Co-Part Segmentation

論文地址：

https://arxiv.org/abs/1905.01298

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

論文標題：Learning Linear Transformations for Fast Image and Video Style Transfer

論文地址：

https://arxiv.org/abs/1808.04537

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

論文標題：Object Discovery in Videos as Foreground Motion Clustering

論文地址：

https://arxiv.org/abs/1812.02772

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

論文標題：Pixel-Adaptive Convolutional Neural Networks

論文地址：

https://arxiv.org/abs/1904.05373

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

論文標題：Importance Estimation for Neural Network Pruning

論文地址：

jankautz.com/publications/Importance4NNPruning_CVPR19.pdf

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

論文標題：Graphical Contrastive Losses for Scene Graph Parsing

論文地址：

https://arxiv.org/abs/1903.02728

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

論文標題：Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

論文地址：

https://arxiv.org/abs/1805.09806

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

論文標題：Large-scale Distributed Second-order Optimization Using Kronecker-factored Approximate Curvature for Deep Convolutional Neural Networks

論文地址：

https://arxiv.org/abs/1811.12019

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

論文標題：Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments

論文地址：

https://arxiv.org/abs/1903.05690

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