Blog

The latest news from Google AI

Google at CVPR 2018

Monday, June 18, 2018

Posted by Christian Howard, Editor-in-Chief, Google AI Communications
2018 Conference on Computer Vision and Pattern Recognitionworkshopstutorialsmachine perceptionportrait mode on the Pixel 2 and Pixel 2 XL smartphonesOpen Images V4 datasetblueOrganization Ramin Zabih Sameer Agarwal Aseem Agrawala Jon Barron Abhinav Shrivastava Carl Vondrick Ming-Hsuan Yang Orals/SpotlightsUnsupervised Discovery of Object Landmarks as Structural Representations Honglak LeeDoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor Kaiwen GuoNeural Kinematic Networks for Unsupervised Motion Retargetting Honglak Lee Burst Denoising with Kernel Prediction Networks Jiawen Chen Jonathan Barron Robert Carroll Dillon SharletQuantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference Benoit Jacob Skirmantas Kligys Bo Chen Matthew Tang Menglong Zhu Andrew Howard Dmitry Kalenichenko Hartwig AdamAVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Chunhui Gu Chen Sun David Ross Carl Vondrick Caroline Pantofaru Yeqing Li Sudheendra Vijayanarasimhan George Toderici Susanna Ricco Rahul Sukthankar Cordelia SchmidFocal Visual-Text Attention for Visual Question Answering Lu JiangLi-Jia LiInferring Light Fields from Shadows William FreemanModifying Non-Local Variations Across Multiple Views Tali DekelIterative Visual Reasoning Beyond Convolutions Li-jia Li Fei-Fei Li Abhinav GuptaUnsupervised Training for 3D Morphable Model RegressionForrester Cole Aaron Maschinot Daniel Vlasic Aaron Sarna William FreemanLearning Transferable Architectures for Scalable Image RecognitionBarret Zoph Vijay Vasudevan Jonathon Shlens Quoc LeThe iNaturalist Species Classification and Detection Dataset Yang SongChen SunHartwig AdamLearning Intrinsic Image Decomposition from Watching the World Noah Snavely Learning Intelligent Dialogs for Bounding Box Annotation Jasper UijlingsPostersRevisiting Knowledge Transfer for Training Object Class Detectors Jasper Uijlings Stefan Popov Vittorio FerrariRethinking the Faster R-CNN Architecture for Temporal Action Localization Sudheendra Vijayanarasimhan Bryan Seybold David RossRahul SukthankarHierarchical Novelty Detection for Visual Object Recognition Honglak Lee COCO-Stuff: Thing and Stuff Classes in Context Jasper Uijlings Vittorio FerrariAppearance-and-Relation Networks for Video Classification Wei LiMorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep NetworksAriel Gordon Elad Eban Bo Chen Ofir Nachum Tien-Ju YangDeformable Shape Completion with Graph Convolutional AutoencodersAmeesh Makadia MegaDepth: Learning Single-View Depth Prediction from Internet Photos Noah Snavely Unsupervised Discovery of Object Landmarks as Structural Representations Honglak Lee Burst Denoising with Kernel Prediction Networks Jiawen Chen Jonathan Barron Robert Carroll Dillon SharletPix3D: Dataset and Methods for Single-Image 3D Shape ModelingTianfan XueWilliam FreemanSparse, Smart Contours to Represent and Edit Images Tali Dekel Dilip KrishnanCe Liu William FreemanMaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features Liang-Chieh ChenGeorge Papandreou Florian SchroffHartwig AdamLarge Scale Fine-Grained Categorization and Domain-Specific Transfer Learning Yang Song Chen Sun Andrew Howard Serge BelongieImproved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks Nick Johnston Damien Vincent David Minnen Michele Covell Saurabh Singh Sung Jin Hwang George Toderici Troy Chinen Joel ShorMobileNetV2: Inverted Residuals and Linear BottlenecksMark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov Liang-Chieh ChenScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans Martin Bokeloh Scott Reed Juergen SturmSim2Real View Invariant Visual Servoing by Recurrent Control Fereshteh Sadeghi Alexander Toshev Eric Jang Sergey LevineAlternating-Stereo VINS: Observability Analysis and Performance Evaluation Mrinal Kanti Paul Stergios RoumeliotisSoccer on Your Tabletop Steve Seitz Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints Martin Wicke Anelia AngelovaAVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Chunhui Gu Chen Sun David Ross Carl Vondrick Caroline Pantofaru Yeqing Li Sudheendra Vijayanarasimhan George Toderici Susanna Ricco Rahul Sukthankar Cordelia Schmid Jitendra MalikInferring Light Fields from Shadows William FreemanModifying Non-Local Variations Across Multiple Views Tali DekelAperture Supervision for Monocular Depth Estimation Rahul Garg Neal WadhwaJonathan BarronInstance Embedding Transfer to Unsupervised Video Object SegmentationBryan Seybold Alexey Vorobyov Alireza FathiFrame-Recurrent Video Super-Resolution Raviteja Vemulapalli Matthew BrownWeakly Supervised Action Localization by Sparse Temporal Pooling Network Ting LiuGautam PrasadIterative Visual Reasoning Beyond Convolutions Li-jia Li Fei-Fei Li,Learning and Using the Arrow of Time William FreemanHydraNets: Specialized Dynamic Architectures for Efficient Inference Noam Shazeer William MarkThoracic Disease Identification and Localization with Limited Supervision Chong Wang Mei Han Yuan Xue Wei WeiLi-jia Li Fei-Fei LiInferring Semantic Layout for Hierarchical Text-to-Image Synthesis Honglak LeeDeep Semantic Face Deblurring Ming-Hsuan YangUnsupervised Training for 3D Morphable Model Regression Kyle Genova Forrester Cole Aaron Maschinot Daniel Vlasic Aaron Sarna William FreemanLearning Transferable Architectures for Scalable Image Recognition Barret Zoph Vijay Vasudevan Jonathon Shlens Quoc LeLearning Intrinsic Image Decomposition from Watching the World Noah Snavely PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection Ming-Hsuan YangMobile Video Object Detection with Temporally-Aware Feature MapsMenglong ZhuTutorials Computer Vision for Robotics and Driving Anelia AngelovaUnsupervised Visual Learning Pierre Sermanet Anelia AngelovaUltraFast 3D Sensing, Reconstruction and Understanding of People, Objects and EnvironmentsSean Fanello Julien Valentin Jonathan Taylor Christoph Rhemann Adarsh Kowdle Jürgen Sturm Christine Kaeser-Chen Pavel Pidlypenskyi Rohit Pandey Andrea Tagliasacchi Sameh Khamis David KimMingsong Dou Kaiwen Guo Danhang Tang Shahram IzadiGenerative Adversarial NetworksIan Goodfellow