2016
Learning Deep Features for Discriminative Localization
11,058 citationsRead
Most cited
549 papers in total2001 · International Journal of Computer Vision
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
6,450 citationsRead
2007 · International Journal of Computer Vision
LabelMe: A Database and Web-Based Tool for Image Annotation
4,300 citationsRead
2017 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Places: A 10 Million Image Database for Scene Recognition
4,156 citationsRead
2017
Scene Parsing through ADE20K Dataset
3,314 citationsRead
2010
SUN database: Large-scale scene recognition from abbey to zoo
3,297 citationsRead
Newest first
549 papers in total2024
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning255 citations
- Adaptive tactile interaction transfer via digitally embroidered smart glovesNature Communications · 141 citations
- Contextual and combinatorial structure in sperm whale vocalisationsNature Communications · 70 citations
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion ModelsIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 59 citations
2023
- ConceptFusion: Open-set multimodal 3D mapping217 citations
- Improving Factuality and Reasoning in Language Models through Multiagent DebatearXiv (Cornell University) · 95 citations
- Detecting Everything in the Open World: Towards Universal Object DetectionIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 93 citations
- Generalizing Dataset Distillation via Deep Generative PriorIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 60 citations
2022
- Ego4D: Around the World in 3,000 Hours of Egocentric VideoIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 602 citations
- Compositional Visual Generation with Composable Diffusion ModelsLecture notes in computer science · 276 citations
- Dataset Distillation by Matching Training TrajectoriesIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 239 citations
- Self-powered sensing systems with learning capabilityJoule · 131 citations
- BigDatasetGAN: Synthesizing ImageNet with Pixel-wise AnnotationsIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 75 citations
- Robust Contrastive Learning against Noisy ViewsIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 72 citations
- Correcting Robot Plans with Natural Language Feedback71 citations
- Toward understanding the communication in sperm whalesiScience · 64 citations
- MTFormer: Multi-task Learning via Transformer and Cross-Task ReasoningLecture notes in computer science · 63 citations
2021
- BARF: Bundle-Adjusting Neural Radiance FieldsIEEE/CVF International Conference on Computer Vision (ICCV) · 627 citations
- Learning human–environment interactions using conformal tactile textilesNature Electronics · 398 citations
- DatasetGAN: Efficient Labeled Data Factory with Minimal Human EffortIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 241 citations
- Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain GeneralizationIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 174 citations
- Next-generation deep learning based on simulators and synthetic dataTrends in Cognitive Sciences · 165 citations
- AVLnet: Learning Audio-Visual Language Representations from Instructional Videos107 citations
- Intelligent Carpet: Inferring 3D Human Pose from Tactile SignalsIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 77 citations
- DriveGAN: Towards a Controllable High-Quality Neural SimulationIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 70 citations
2020
- Understanding the role of individual units in a deep neural networkProceedings of the National Academy of Sciences · 383 citations
- Using AI and Social Media Multimodal Content for Disaster Response and Management: Opportunities, Challenges, and Future DirectionsInformation Processing & Management · 219 citations
- Music Gesture for Visual Sound SeparationIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 202 citations
- Foley Music: Learning to Generate Music from VideosLecture notes in computer science · 118 citations
- The Hessian Penalty: A Weak Prior for Unsupervised DisentanglementLecture notes in computer science · 95 citations
Research in numbers
From OpenAlex- conference paper110
- article59
- preprint22
- book chapter3
- dissertation2
- Lecture notes in computer science25
- arXiv (Cornell University)20
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)19
- DSpace@MIT (Massachusetts Institute of Technology)13
- IEEE International Conference on Computer Vision (ICCV)13
- Aude Oliva40
- William T. Freeman28
- Bolei Zhou24
- Aditya Khosla19
- Sanja Fidler17
Experience and education
Universities
2026Dominica State College
2007 to 2024Vassar College
2001Carleton College
2001Institute of Cognitive and Brain Sciences
1998 to 1999Institut polytechnique de Grenoble
Industry and labs
2022 to 2026Citigroup
2021Nvidia (United Kingdom)
2019IBM (United States)
2002 to 2011Intel (United States)
2001McGovern Institute for Brain Research