Profiles2019-2026
Davide Modolo
AWS AI Labs
13Papers
5Last author
23Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- STORM: End-to-End Referring Multi-Object Tracking in VideosAuthor 7 of 7CVPR Findings 2026
- Enhancing Numerical Prediction of MLLMS With Soft LabelingAuthor 4 of 5ICCV 2025 · 1 citation
- Self-Supervised Multi-Object Tracking with Path ConsistencyAuthor 5 of 5CVPR 2024 · 13 citations
- Hyperbolic Learning with Synthetic Captions for Open-World DetectionAuthor 4 of 4CVPR 2024
- SkeleTR: Towards Skeleton-based Action Recognition in the WildAuthor 4 of 7ICCV 2023 · 38 citations
- Semi-supervised Vision Transformers at ScaleAuthor 5 of 8NeurIPS 2022 · 82 citations
- What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionsAuthor 6 of 6CVPR 2022 · 50 citations
- Hierarchical Self-supervised Representation Learning for Movie UnderstandingAuthor 4 of 4CVPR 2022 · 21 citations
- Selective Feature Compression for Efficient Activity Recognition InferenceAuthor 4 of 5ICCV 2021 · 10 citations
- SiamMOT: Siamese Multi-Object TrackingAuthor 4 of 5CVPR 2021
- Exploiting weakly supervised visual patterns to learn from partial annotationsAuthor 5 of 6NeurIPS 2020 · 39 citations
- Combining Detection and Tracking for Human Pose Estimation in VideosAuthor 3 of 4CVPR 2020
- Action Recognition With Spatial-Temporal Discriminative Filter BanksAuthor 2 of 4ICCV 2019 · 70 citations
