2014
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
32,275 citationsRead
Most cited
642 papers in total2000 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized cuts and image segmentation
15,826 citationsRead
1990 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale-space and edge detection using anisotropic diffusion
12,185 citationsRead
2002
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
8,134 citationsRead
2002 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape matching and object recognition using shape contexts
6,349 citationsRead
2010 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour Detection and Hierarchical Image Segmentation
5,625 citationsRead
Newest first
642 papers in total2024
- Real-world humanoid locomotion with reinforcement learningScience Robotics · 203 citations
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration 0Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 177 citations
- Reconstructing Hands in 3D with Transformers151 citations
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset139 citations
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives105 citations
- Sequential Modeling Enables Scalable Learning for Large Vision ModelsIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 102 citations
- NeuralFeels with neural fields: Visuotactile perception for in-hand manipulationScience Robotics · 92 citations
2023
- Humans in 4D: Reconstructing and Tracking Humans with Transformers255 citations
- Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approachACM eBooks · 200 citations
- Navigating to objects in the real worldScience Robotics · 120 citations
- Open X-Embodiment: Robotic Learning Datasets and RT-X ModelsarXiv (Cornell University) · 100 citations
2022
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 793 citations
- Ego4D: Around the World in 3,000 Hours of Egocentric VideoIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 602 citations
- MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 170 citations
- ABO: Dataset and Benchmarks for Real-World 3D Object Understanding2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 153 citations
- PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 150 citations
2021
- Multiscale Vision Transformers2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 1,231 citations
- RMA: Rapid Motor Adaptation for Legged Robots506 citations
- From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 275 citations
- Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 254 citations
- Reconstructing Hand-Object Interactions in the Wild2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 137 citations
- Distribution-free, Risk-controlling Prediction SetsJournal of the ACM · 122 citations
2020
- It Is Not the Journey But the Destination: Endpoint Conditioned Trajectory PredictionLecture notes in computer science · 429 citations
- Long-Term Human Motion Prediction with Scene ContextLecture notes in computer science · 214 citations
- Which Tasks Should Be Learned Together in Multi-task Learning?International Conference on Machine Learning · 176 citations
- Audiovisual SlowFast Networks for Video RecognitionarXiv (Cornell University) · 156 citations
- Side-Tuning: A Baseline for Network Adaptation via Additive Side NetworksLecture notes in computer science · 152 citations
- Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the WildLecture notes in computer science · 113 citations
- Robust Learning Through Cross-Task Consistency107 citations
- Rearrangement: A Challenge for Embodied AIarXiv (Cornell University) · 100 citations
Research in numbers
From OpenAlex- conference paper130
- article49
- preprint16
- book chapter4
- report1
- Lecture notes in computer science24
- IEEE Transactions on Pattern Analysis and Machine Intelligence18
- arXiv (Cornell University)16
- International Journal of Computer Vision9
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)4
- Pablo Arbeláez21
- Ross Girshick17
- Serge Belongie16
- Charless C. Fowlkes15
- Saurabh Gupta12
Experience and education
Universities
1996 to 2026Berkeley College
2025University of Illinois Urbana-Champaign
2008University of California, Irvine
2007University of Cambridge
1999University of Bonn
1999California Institute of Technology
Industry and labs
2019 to 2021Meta (Israel)
2017 to 2019Google (United States)
2018Lawrence Berkeley National Laboratory
2009Adobe Systems (United States)
1995 to 2007International Computer Science Institute
2007Isaac Newton Institute for Mathematical Sciences
2006Executive Office of the President