CVPR 2018 Notes

Below are the links, notes and thoughts about the most interesting papers, challenges and workshops that I came across during the CVPR 2018 conference. Though, you probably may want to form your own notion of the progress in computer vision and pattern recognition by reviewing all 979 accepted papers and walking through the content of all 21 tutorials and 48 workshops:

• CVPR 2018 Papers
• CVPR 2018 Workshops Papers
• CVPR 2018 Tutorials
• CVPR 2018 Workshops

NOTE: The categories and tags of the papers are very soft and often one paper can be in autonomous driving, 3D vision and graph-based related categories but I select one that to my best knowledge suits better and will be easier for me to find later.

Top Papers

Best Paper Award:

• Taskonomy: Disentangling Task Transfer Learning. Amir R. Zamir, Alexander Sax, William Shen, Leonidas J. Guibas, Jitendra Malik, Silvio Savarese [pdf] [project page] [code]

Honorable Mentions:

• Deep Learning of Graph Matching. Andrei Zanfir, Cristian Sminchisescu [pdf]

• SPLATNet: Sparse Lattice Networks for Point Cloud Processing. Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz [pdf] [code]

• CodeSLAM — Learning a Compact, Optimisable Representation for Dense Visual SLAM. Michael Bloesch, Jan Czarnowski, Ronald Clark, Stefan Leutenegger, Andrew J. Davison [pdf]

• Efficient Optimization for Rank-Based Loss Functions Pritish Mohapatra, Michal Rolínek, C.V. Jawahar, Vladimir Kolmogorov, M. Pawan Kumar [pdf]

Autonomous Driving and related topics: Visual odometry, SLAM, Localization.

Self-driving cars were one of the most noticeable topics at the conference with huge booth's on the expo floor from nuTonomy, Aurora, Tesla, Waymo, Didi, Argo.ai, Baidu, Lyft, Uber, NVidia. There were several workshops and challenges. Also it's one that I'm personally most interested in though it get's the biggest chunk of my conference time.

Autonomous Driving Challenges

Challenges related to the autonomous driving at CVPR 2018:

• Autonomous Driving Challenge, CVPR 2018
• Robust Vision Challenge, CVPR 2018

Future autonomous driving challenges:

• Scene Understanding for Autonomous Navigation in Unstructured Environments, ECCV 2018
• ApolloScape: Vision-based Navigation for Autonomous Driving, ECCV 2018

Autonomous Driving Datasets

Most mentioned datasets related to the self-driving car space:

• KITTI Vision Benchmark Suite
• ApolloScape Dataset
• Berkeley DeepDrive (BDD100K)
• Oxford RobotCar Dataset
• Cityscapes Dataset
• HD1K Dataset
• WildDash Dataset
• DAVIS Driving Dataset, and other datasets from INI Zurich
• TorontoCity Dataset (didn't find a link to the dataset page)

Autonomous driving related workshops/tutorials

Mentioned workshops and tutorials cover the most frequent topics related to the self-driving car development space.

• Workshop on Autonomous Driving, [papers]
• Robust Vision Challenge
• Embedded Vision Workshop, [papers]
• Workshop on Visual Odometry and Computer Vision Applications Based on Location Clues, [papers]
• Beyond Supervised Learning
• Computational Imaging for Self-Driving Vehicles
• Computer Vision for Robotics and Driving
• Deep Learning for Visual SLAM, [papers]
• Joint Detection, Tracking, and Prediction in the Wild, [papers]
• [DeepGlobe: A Challenge for Parsing the Earth through Satellite Images]( DeepGlobe: A Challenge for Parsing the Earth through Satellite Images), [papers]

Autonomous Driving Papers

Here the papers that I've noticed during oral or spotlight sessions, or as a poster. Some of they directly related to the autonomous cars and from companies like Uber/Lyft, but some of them cover broader topic or direction that can be used for self-driving car development.

• Semantic Binary Segmentation Using Convolutional Networks Without Decoders. Shubhra Aich, William van der Kamp, Ian Stavness, [pdf] (road extraction)

• D-LinkNet: LinkNet With Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction Lichen Zhou, Chuang Zhang, Ming Wu, [pdf] (road extraction, segmentation)

• Stacked U-Nets With Multi-Output for Road Extraction Tao Sun, Zehui Chen, Wenxiang Yang, Yin Wang, [pdf] (road extraction, segmentation)

• Fully Convolutional Network for Automatic Road Extraction From Satellite Imagery. Alexander Buslaev, Selim Seferbekov, Vladimir Iglovikov, Alexey Shvets [pdf] (road extraction, segmentation)

• Road Detection With EOSResUNet and Post Vectorizing Algorithm. Oleksandr Filin, Anton Zapara, Serhii Panchenko, [pdf] (road extraction, segmentation)

• Residual Inception Skip Network for Binary Segmentation. Jigar Doshi, [pdf] (road extraction)

• Roadmap Generation Using a Multi-Stage Ensemble of Deep Neural Networks With Smoothing-Based Optimization. Dragos Costea, Alina Marcu, Emil Slusanschi, Marius Leordeanu, [pdf] (road extraction, segmentation)

• Rotated Rectangles for Symbolized Building Footprint Extraction. Matt Dickenson, Lionel Gueguen, [pdf] (building detection, segmentation, Uber)

• Feature Pyramid Network for Multi-Class Land Segmentation. Selim Seferbekov, Vladimir Iglovikov, Alexander Buslaev, Alexey Shvets, [pdf] (land segmentation, Lyft)

• The ApolloScape Dataset for Autonomous Driving. Xinyu Huang, Xinjing Cheng, Qichuan Geng, Binbin Cao, Dingfu Zhou, Peng Wang, Yuanqing Lin, Ruigang Yang, [pdf] (dataset, detection, segmentation, localization, Baidu)

• Scene Understanding Networks for Autonomous Driving Based on Around View Monitoring System. Jeong Yeol Baek, Ioana Veronica Chelu, Livia Iordache, Vlad Paunescu, HyunJoo Ryu, Alexandru Ghiuta, Andrei Petreanu, YunSung Soh, Andrei Leica, ByeongMoon Jeon, [pdf] (detection)

• Training Deep Networks With Synthetic Data: Bridging the Reality Gap by Domain Randomization. Jonathan Tremblay, Aayush Prakash, David Acuna, Mark Brophy, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, Stan Birchfield, [pdf] (detection, NVidia)

• On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation. Arantxa Casanova, Guillem Cucurull, Michal Drozdzal, Adriana Romero, Yoshua Bengio, [pdf]

• Minimizing Supervision for Free-Space Segmentation. Satoshi Tsutsui, Tommi Kerola, Shunta Saito, David J. Crandall, [pdf]

• On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach. Nikolai Smolyanskiy, Alexey Kamenev, Stan Birchfield, [pdf] (depth estimation, NVidia)

• Accurate Deep Direct Geo-Localization From Ground Imagery and Phone-Grade GPS. Shaohui Sun, Ramesh Sarukkai, Jack Kwok, Vinay Shet, [pdf] (Lyft)

• Efficient and Safe Vehicle Navigation Based on Driver Behavior Classification. Ernest Cheung, Aniket Bera, Dinesh Manocha, [pdf]

• Detection of Distracted Driver Using Convolutional Neural Network. Bhakti Baheti, Suhas Gajre, Sanjay Talbar, [pdf]

• Classifying Group Emotions for Socially-Aware Autonomous Vehicle Navigation. Aniket Bera, Tanmay Randhavane, Austin Wang, Dinesh Manocha, Emily Kubin, Kurt Gray, [pdf]

• AutonoVi-Sim: Autonomous Vehicle Simulation Platform With Weather, Sensing, and Traffic Control. Andrew Best, Sahil Narang, Lucas Pasqualin, Daniel Barber, Dinesh Manocha, [pdf]

• Subset Replay Based Continual Learning for Scalable Improvement of Autonomous Systems. Pratik Prabhanjan Brahma, Adrienne Othon, [pdf] (Volkswagen)

• Deep Parametric Continuous Convolutional Neural Networks. Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun, [pdf] (point cloud, segmentation, motion estimation, Uber)

• Hierarchical Recurrent Attention Networks for Structured Online Maps. Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun, [pdf] (point cloud, road extraction, Uber)

• DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion. Zhishuai Zhang, Cihang Xie, Jianyu Wang, Lingxi Xie, Alan L. Yuille, [pdf] (Baidu)

• ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM. Haomin Liu, Mingyu Chen, Guofeng Zhang, Hujun Bao, Yingze Bao, [pdf] [source code] (SLAM, Baidu)

• Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks. Agrim Gupta, Justin Johnson, Li Fei-Fei, Silvio Savarese, Alexandre Alahi, [pdf] (trajectory prediction, Stanford)

• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional Net. Wenjie Luo, Bin Yang, Raquel Urtasun, [pdf] (detection, tracking, prediction, Uber)

• DeLS-3D: Deep Localization and Segmentation With a 3D Semantic Map. Peng Wang, Ruigang Yang, Binbin Cao, Wei Xu, Yuanqing Lin, [pdf] (Baidu)

• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. Alex Kendall, Yarin Gal, Roberto Cipolla, [pdf] (depth estimation)

• Matching Adversarial Networks. Gellért Máttyus, Raquel Urtasun, [pdf] (segmentation, Uber)

3D Reconstruction & 3D Vision

• Learning Hierarchical Models for Class-Specific Reconstruction From Natural Data. Arun CS Kumar, Suchendra M. Bhandarkar, Mukta Prasad, [pdf] (detection, pose estimation, 3d reconstruction)

• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. Danfei Xu, Dragomir Anguelov, Ashesh Jain, [pdf] (3d detection, Zoox)

• Frustum PointNets for 3D Object Detection From RGB-D Data. Charles R. Qi, Wei Liu, Chenxia Wu, Hao Su, Leonidas J. Guibas, [pdf] (3d detection, Nuro)

• 3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare. Abhijit Kundu, Yin Li, James M. Rehg, [pdf] [project page]

• LEGO: Learning Edge With Geometry All at Once by Watching Videos. Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, [pdf] (3d reconstruction, Baidu)

• SurfConv: Bridging 3D and 2D Convolution for RGBD Images. Hang Chu, Wei-Chiu Ma, Kaustav Kundu, Raquel Urtasun, Sanja Fidler, [pdf] (3d segmentation, Uber)

• PIXOR: Real-Time 3D Object Detection From Point Clouds. Bin Yang, Wenjie Luo, Raquel Urtasun, [pdf] (Uber)

Below are papers from other topics that are not always related to the autonomous driving.

Context/Geometry Awareness

Context aware papers:

• COCO-Stuff: Thing and Stuff Classes in Context. Holger Caesar, Jasper Uijlings, Vittorio Ferrari, [pdf] (context, segmentation, Google)

• Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos. De-An Huang, Shyamal Buch, Lucio Dery, Animesh Garg, Li Fei-Fei, Juan Carlos Niebles, [pdf] (Stanford)

• Context Encoding for Semantic Segmentation. Hang Zhang, Kristin Dana, Jianping Shi, Zhongyue Zhang, Xiaogang Wang, Ambrish Tyagi, Amit Agrawal, [pdf] (Amazon)

Geometry awareness:

• Geometry-Aware Learning of Maps for Camera Localization. Samarth Brahmbhatt, Jinwei Gu, Kihwan Kim, James Hays, Jan Kautz, [pdf] [project page] [code] (localization, SLAM, NVidia)

• Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning. Chuang Gan, Boqing Gong, Kun Liu, Hao Su, Leonidas J. Guibas, [pdf] (Stanford, MIT)

• Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric Constraints. Reza Mahjourian, Martin Wicke, Anelia Angelova, [pdf] (Google)

Graph Based, Structure discovery

• Image Generation From Scene Graphs. Justin Johnson, Agrim Gupta, Li Fei-Fei, [pdf]

• Unsupervised Discovery of Object Landmarks as Structural Representations. Yuting Zhang, Yijie Guo, Yixin Jin, Yijun Luo, Zhiyuan He, Honglak Lee [pdf] (unsupervised, GAN, Google)

• Distributable Consistent Multi-Object Matching. Nan Hu, Qixing Huang, Boris Thibert, Leonidas J. Guibas, [pdf] (matching, Stanford)

• Referring Relationships. Ranjay Krishna, Ines Chami, Michael Bernstein, Li Fei-Fei, [pdf] (detection, Stanford)

• Beyond Holistic Object Recognition: Enriching Image Understanding With Part States. Cewu Lu, Hao Su, Yonglu Li, Yongyi Lu, Li Yi, Chi-Keung Tang, Leonidas J. Guibas, [pdf]

• Iterative Visual Reasoning Beyond Convolutions. Xinlei Chen, Li-Jia Li, Li Fei-Fei, Abhinav Gupta, [pdf] [code] (Stanford)

Networks Optimization, Learning, Inference

• MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks. Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Hao Wu, Tien-Ju Yang, Edward Choi, [pdf]

• Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, Dmitry Kalenichenko, [pdf] (Google)

• Low-Latency Video Semantic Segmentation. Yule Li, Jianping Shi, Dahua Lin, [pdf] (optimization)

• Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions. Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, Kurt Keutzer, [pdf] (Berkeley)

• NISP: Pruning Networks Using Neuron Importance Score Propagation. Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad I. Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, Larry S. Davis, [pdf] (DeepMind, Adobe)

• SBNet: Sparse Blocks Network for Fast Inference. Mengye Ren, Andrei Pokrovsky, Bin Yang, Raquel Urtasun, [pdf] (Uber)

• HydraNets: Specialized Dynamic Architectures for Efficient Inference. Ravi Teja Mullapudi, William R. Mark, Noam Shazeer, Kayvon Fatahalian, [pdf] (CMU, Google, Stanford)

• A PID Controller Approach for Stochastic Optimization of Deep Networks. Wangpeng An, Haoqian Wang, Qingyun Sun, Jun Xu, Qionghai Dai, Lei Zhang, [pdf]

• Deep Spatio-Temporal Random Fields for Efficient Video Segmentation. Siddhartha Chandra, Camille Couprie, Iasonas Kokkinos, [pdf] (Facebook)

• MobileNetV2: Inverted Residuals and Linear Bottlenecks. Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen, [pdf] (Google)

• Latent RANSAC. Simon Korman, Roee Litman, [pdf]

Computational Imaging

• Burst Denoising With Kernel Prediction Networks. Ben Mildenhall, Jonathan T. Barron, Jiawen Chen, Dillon Sharlet, Ren Ng, Robert Carroll, [pdf] (Google)

3D Reconstruction | Depth Estimation

• Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling. Xingyuan Sun, Jiajun Wu, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Tianfan Xue, Joshua B. Tenenbaum, William T. Freeman, [pdf] (3d reconstruction, dataset, Google)

• Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene. Shubham Tulsiani, Saurabh Gupta, David F. Fouhey, Alexei A. Efros, Jitendra Malik, [pdf] (3d reconstruction, Berkeley)

• Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction. Shubham Tulsiani, Alexei A. Efros, Jitendra Malik, [pdf] (Berkeley)

• Aperture Supervision for Monocular Depth Estimation. Pratul P. Srinivasan, Rahul Garg, Neal Wadhwa, Ren Ng, Jonathan T. Barron, [pdf] (Berkeley, Google)

• Gibson Env: Real-World Perception for Embodied Agents. Fei Xia, Amir R. Zamir, Zhiyang He, Alexander Sax, Jitendra Malik, Silvio Savarese, [pdf] [project page] (depth estimation, multi task, Berkeley, Stanford)

• Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction. Huangying Zhan, Ravi Garg, Chamara Saroj Weerasekera, Kejie Li, Harsh Agarwal, Ian Reid, [pdf] [code] (localization)

Human pose detection, tracking, re-identification

Humans detection, segmentation, tracking, 3d reconstruction, re-localization and other topics around our body parts was a huge part of the CVPR 2018. Here I just mention a few references because I was more on autonomous, localization, SLAM ans robotics topics.

• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. Longhui Wei, Shiliang Zhang, Wen Gao, Qi Tian, [pdf]

• Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals. Shanxin Yuan et al., [pdf]

• PoseTrack: A Benchmark for Human Pose Estimation and Tracking. Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov, Leonid Pishchulin, Anton Milan, Juergen Gall, Bernt Schiele, [pdf] [project page] (Google, Amazon)

• DensePose: Dense Human Pose Estimation in the Wild. Rıza Alp Güler, Natalia Neverova, Iasonas Kokkinos, [pdf] (Facebook)

3D Vision

• Recurrent Slice Networks for 3D Segmentation of Point Clouds. Qiangui Huang, Weiyue Wang, Ulrich Neumann, [pdf] [source code]

• Consensus Maximization for Semantic Region Correspondences. Pablo Speciale, Danda P. Paudel, Martin R. Oswald, Hayko Riemenschneider, Luc Van Gool, Marc Pollefeys, [pdf] (ETH)

• Manifold Learning in Quotient Spaces. Éloi Mehr, André Lieutier, Fernando Sanchez Bermudez, Vincent Guitteny, Nicolas Thome, Matthieu Cord, [pdf]

• ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans. Angela Dai, Daniel Ritchie, Martin Bokeloh, Scott Reed, Jürgen Sturm, Matthias Nießner, [pdf] (Stanford, Google)

• 3D Semantic Segmentation With Submanifold Sparse Convolutional Networks. Benjamin Graham, Martin Engelcke, Laurens van der Maaten, [pdf] (Facebook)

• Real-Time Seamless Single Shot 6D Object Pose Prediction. Bugra Tekin, Sudipta N. Sinha, Pascal Fua, [pdf] (Microsoft)

• 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild. Alexander Grabner, Peter M. Roth, Vincent Lepetit, [pdf]

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection. Yin Zhou, Oncel Tuzel, [pdf] (Apple)

Localization, SLAM

• CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization. Sixing Hu, Mengdan Feng, Rang M. H. Nguyen, Gim Hee Lee, [pdf]

• Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions. Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, Fredrik Kahl, Tomas Pajdla, [pdf] [project page]

• Semantic Visual Localization. Johannes L. Schönberger, Marc Pollefeys, Andreas Geiger, Torsten Sattler, [pdf] (ETH)

Domain adaptation

• Domain Adaptive Faster R-CNN for Object Detection in the Wild. Yuhua Chen, Wen Li, Christos Sakaridis, Dengxin Dai, Luc Van Gool, [pdf] (ETH)

Other Papers

• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, Oliver Wang, [pdf] (Berkeley, OpenAI, Adobe)

• Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks. Dinesh Jayaraman, Kristen Grauman, [pdf]

• Deep Layer Aggregation. Fisher Yu, Dequan Wang, Evan Shelhamer, Trevor Darrell, [pdf] (Berkeley)

• Partial Transfer Learning With Selective Adversarial Networks. Zhangjie Cao, Mingsheng Long, Jianmin Wang, Michael I. Jordan, [pdf]

• Hybrid Camera Pose Estimation. Federico Camposeco, Andrea Cohen, Marc Pollefeys, Torsten Sattler, [pdf] (3d vision, ETH)

• Five-point Fundamental Matrix Estimation for Uncalibrated Cameras. Five-Point Fundamental Matrix Estimation for Uncalibrated Cameras, [pdf]

• PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image. Chen Liu, Jimei Yang, Duygu Ceylan, Ersin Yumer, Yasutaka Furukawa, [pdf] (3d reconstruction, Argo.ai)

• Egocentric Activity Recognition on a Budget. Rafael Possas, Sheila Pinto Caceres, Fabio Ramos, [pdf] (AR optimized)

• CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF. Linchao Bao, Baoyuan Wu, Wei Liu, [pdf]

• Features for Multi-Target Multi-Camera Tracking and Re-Identification. Ergys Ristani, Carlo Tomasi, [pdf]

• Occlusion Aware Unsupervised Learning of Optical Flow. Yang Wang, Yi Yang, Zhenheng Yang, Liang Zhao, Peng Wang, Wei Xu, [pdf]

• Adversarial Feature Augmentation for Unsupervised Domain Adaptation. Riccardo Volpi, Pietro Morerio, Silvio Savarese, Vittorio Murino, [pdf] (GAN)

• LIME: Live Intrinsic Material Estimation. Abhimitra Meka, Maxim Maximov, Michael Zollhöfer, Avishek Chatterjee, Hans-Peter Seidel, Christian Richardt, Christian Theobalt, [pdf]

• Learning to Segment Every Thing. Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, Ross Girshick, [pdf] (Berkeley, BAIR, Facebook)

• Efficient Video Object Segmentation via Network Modulation. Linjie Yang, Yanran Wang, Xuehan Xiong, Jianchao Yang, Aggelos K. Katsaggelos, [pdf] (Snap, Google)

• Mobile Video Object Detection With Temporally-Aware Feature Maps. Mason Liu, Menglong Zhu, [pdf] (Google)

• MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction Features. Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff, Peng Wang, Hartwig Adam, [pdf]

• Squeeze-and-Excitation Networks. Jie Hu, Li Shen, Gang Sun, [pdf] [code] (Momenta.ai)

• InLoc: Indoor Visual Localization With Dense Matching and View Synthesis. Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Akihiko Torii, [pdf] (ETH, Microsoft)

• Low-Shot Learning From Imaginary Data, Yu-Xiong Wang, Ross Girshick, Martial Hebert, Bharath Hariharan, [pdf] (Facebook)

• Discriminative Learning of Latent Features for Zero-Shot Recognition. Yan Li, Junge Zhang, Jianguo Zhang, Kaiqi Huang, [pdf]

• PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume. Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz, [pdf] (robust vision winner, NVidia)

• Feature Space Transfer for Data Augmentation. Bo Liu, Xudong Wang, Mandar Dixit, Roland Kwitt, Nuno Vasconcelos, [pdf] (Microsoft)

• Detail-Preserving Pooling in Deep Networks. Faraz Saeedan, Nicolas Weber, Michael Goesele, Stefan Roth, [pdf] (Oculus)

• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing. Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman, Simon Lucey, [pdf] (Adobe, Argo.ai)

• Revisiting Deep Intrinsic Image Decompositions. Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf, [pdf] (Microsoft)

• Accurate and Diverse Sampling of Sequences Based on a “Best of Many” Sample Objective. Apratim Bhattacharyya, Bernt Schiele, Mario Fritz, [pdf]

• ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes, Yuhua Chen, Wen Li, Luc Van Gool, [pdf] (augmentation, ETH)

• DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks. Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiří Matas, [pdf] [code]

• A Perceptual Measure for Deep Single Image Camera Calibration. Yannick Hold-Geoffroy, Kalyan Sunkavalli, Jonathan Eisenmann, Matthew Fisher, Emiliano Gambaretto, Sunil Hadap, Jean-François Lalonde, [pdf] (360 imaging)