Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency
Comments To appear at CVPR 2017. Project webpage : https://shubhtuls.github.io/drc/
作者
Jitendra Malik
Computer Vision
Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing
Comments 13 pages, 6 figures; International Conference on Machine Learning (ICML), 2016. This version corrects a typo in the pseudocode
Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
Comments 8 pages, accepted to International Conference on Robotics and Automation (ICRA) 2017
Learning to Poke by Poking: Experiential Learning of Intuitive Physics
Journal ref NIPS 2016
View Synthesis by Appearance Flow
Amodal Instance Segmentation
Comments 23 pages, 14 figures; European Conference on Computer Vision (ECCV), 2016
Pose Induction for Novel Object Categories
Human Pose Estimation with Iterative Error Feedback
Iterative Instance Segmentation
Comments 13 pages, 10 figures; IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Learning to Optimize
Comments 9 pages, 3 figures
Contextual Action Recognition with R*CNN
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
Learning Visual Predictive Models of Physics for Playing Billiards
Exploring Person Context and Local Scene Context for Object Detection
Shape and Symmetry Induction for 3D Objects
Cross Modal Distillation for Supervision Transfer
Comments Updated version (v2) contains additional experiments and results
Amodal Completion and Size Constancy in Natural Scenes
Comments Accepted to ICCV 2015
Recurrent Network Models for Human Dynamics
Comments International Conference on Computer Vision 2015
DeepBox: Learning Objectness with Convolutional Networks
Comments ICCV 2015 Camera-ready version
Bandit Label Inference for Weakly Supervised Learning
Learning to See by Moving
Comments 12 pages
Visual Semantic Role Labeling
Learning to Segment Moving Objects in Videos
Category-Specific Object Reconstruction from a Single Image
Comments First two authors contributed equally. To appear at CVPR 2015
Actions and Attributes from Wholes and Parts
Viewpoints and Keypoints
Hypercolumns for Object Segmentation and Fine-grained Localization
Comments CVPR Camera ready
Inferring 3D Object Pose in RGB-D Images
Comments 13 pages, 8 figures, 4 tables
