Rearrangement: A Challenge for Embodied AI
Comments Authors are listed in alphabetical order
作者
Jitendra Malik
Computer Vision
3D Shape Reconstruction from Vision and Touch
Comments Accepted at Neurips 2020
Shape, Illumination, and Reflectance from Shading
Journal ref TPAMI 2015
Which Tasks Should Be Learned Together in Multi-task Learning?
Comments Presented to ICML 2020 See project website at http://taskgrouping.stanford.edu/
Inclusive GAN: Improving Data and Minority Coverage in Generative Models
Comments Accepted to ECCV'20
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild
Comments In ECCV 2020. v2: Updated Related Work
Deep Isometric Learning for Visual Recognition
Comments ICML 2020; Code: https://github.com/HaozhiQi/ISONet; Website: https://haozhiqi.github.io/ISONet
Long-term Human Motion Prediction with Scene Context
Comments ECCV 2020 Oral. Dataset & Code: https://github.com/ZheC/GTA-IM-Dataset Video: https://people.eecs.berkeley.edu/~zhecao/hmp/index.html
Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks
Comments In ECCV 2020 (Spotlight). For more, see project website and code at http://sidetuning.berkeley.edu
Shape and Viewpoint without Keypoints
Comments Accepted at ECCV 2020
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
Comments Accepted at ECCV 2020 (Oral)
Robust Learning Through Cross-Task Consistency
Comments CVPR 2020 (Oral). Project website, models, live demo at http://consistency.epfl.ch/
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
Journal ref The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 9207-9216
Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation
Comments To appear in International Journal of Computer Vision (IJCV). arXiv admin note: text overlap with arXiv:1811.12373
Audiovisual SlowFast Networks for Video Recognition
Comments Technical report
Mesh R-CNN
Learning to Navigate Using Mid-Level Visual Priors
Comments In Conference on Robot Learning, 2019. See project website and demos at http://perceptual.actor/
Habitat: A Platform for Embodied AI Research
Comments ICCV 2019
SlowFast Networks for Video Recognition
Comments Technical report
Learning Navigation Subroutines from Egocentric Videos
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera
Comments ICCV 2019
Learning 3D Human Dynamics from Video
Comments To appear in CVPR 2019. Changelog: v3. +an experiment to compare improvement from pseudo-gt data on single view vs temporal context model. v2. camready ver: Minor update in model training where the gaussian shape prior is used, updated results (similar results, same trends), added more ablation study in the appendix. v1. +evaluation protocol subsection in appendix, updated results due to bug fix
Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
Comments 18 pages, 16 figures; IEEE International Conference on Computer Vision (ICCV), 2019
Predicting 3D Human Dynamics from Video
Comments To Appear in ICCV 2019. (v2: Updated "3D Pose from Video" in Related Work.)
Learning Individual Styles of Conversational Gesture
Comments CVPR 2019
Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
Comments See project website, demos, and code at http://perceptual.actor
PatchFCN for Intracranial Hemorrhage Detection
Cognitive Mapping and Planning for Visual Navigation
Comments Extended IJCV Version of the original paper at CVPR17. Project website with code, models, simulation environment and videos: https://sites.google.com/view/cognitive-mapping-and-planning/
