作者
Jitendra Malik
Computer Vision
Visual Memory for Robust Path Following
Comments Neural Information Processing Systems (NeurIPS) 2018. Oral Presentation
Are All Training Examples Created Equal? An Empirical Study
Comments 12 pages, 12 figures
On the Implicit Assumptions of GANs
Comments 8 pages
Implicit Maximum Likelihood Estimation
Comments 21 pages, 4 figures. In the interest of promoting discussion, we make the reviews available at https://people.eecs.berkeley.edu/~ke.li/papers/imle_reviews.pdf
SFV: Reinforcement Learning of Physical Skills from Videos
Super-Resolution via Conditional Implicit Maximum Likelihood Estimation
Comments 12 pages, 7 figures
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection
Gibson Env: Real-World Perception for Embodied Agents
Comments Access the code, dataset, and project website at http://gibsonenv.vision/ . CVPR 2018
Journal ref CVPR 2018
Learning Shape Abstractions by Assembling Volumetric Primitives
Comments Project url: https://shubhtuls.github.io/volumetricPrimitives/
Learning Category-Specific Mesh Reconstruction from Image Collections
Comments Project URL: https://akanazawa.github.io/cmr/
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
Comments 8 pages. Published on IEEE Robotics and Automation Letters (RAL). Website: https://sites.google.com/view/more-than-a-feeling
On Evaluation of Embodied Navigation Agents
Comments Report of a working group on empirical methodology in navigation research. Authors are listed in alphabetical order
End-to-end Recovery of Human Shape and Pose
Comments CVPR 2018, Project page with code: https://akanazawa.github.io/hmr/
Learning Instance Segmentation by Interaction
Comments Website at https://pathak22.github.io/seg-by-interaction/
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Comments To appear in CVPR 2018. Check dataset page https://research.google.com/ava/ for details
Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
Comments Project url with code: https://shubhtuls.github.io/mvcSnP/
Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
Comments Project url with code: https://shubhtuls.github.io/factored3d
Zero-Shot Visual Imitation
Comments Oral presentation at ICLR 2018. Website at https://pathak22.github.io/zeroshot-imitation/
Taskonomy: Disentangling Task Transfer Learning
Comments CVPR 2018 (Oral). See project website and live demos at http://taskonomy.vision/
Unifying Map and Landmark Based Representations for Visual Navigation
Comments Project page with videos: https://s-gupta.github.io/cmpl/
From Lifestyle Vlogs to Everyday Interactions
Comments Project page at: http://people.eecs.berkeley.edu/~dfouhey/2017/VLOG/
Learning to Optimize Neural Nets
Comments 10 pages, 15 figures
Hierarchical Surface Prediction for 3D Object Reconstruction
Comments 3DV 2017
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
Generic 3D Representation via Pose Estimation and Matching
Comments Published in ECCV16. See the project website http://3drepresentation.stanford.edu/ and dataset website https://github.com/amir32002/3D_Street_View
Journal ref ECCV 2016 535-553
Beyond Skip Connections: Top-Down Modulation for Object Detection
Feedback Networks
Comments See a video describing the method at https://youtu.be/MY5Uhv38Ttg and the website at http://feedbacknet.stanford.edu/
Learning a Multi-View Stereo Machine
Fast k-Nearest Neighbour Search via Prioritized DCI
Comments 14 pages, 6 figures; International Conference on Machine Learning (ICML), 2017
