Papers › EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
Shraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin, Hardik Shah, Mike Zheng Shou, Rama Chellappa, Pengchuan Zhang
Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP frameworks utilize separate video and language encoders and learn task-specific cross-modal information only during fine-tuning, limiting the development of a unified system. In this work, we introduce the second generation of egocentric video-language pre-training (EgoVLPv2), a significant improvement from the previous generation, by incorporating cross-modal fusion directly into the video and language backbones. EgoVLPv2 learns strong video-text representation during pre-training and reuses the cross-modal attention modules to support different downstream tasks in a flexible and efficient manner, reducing fine-tuning costs. Moreover, our proposed fusion in the backbone strategy is more lightweight and compute-efficient than stacking additional fusion-specific layers. Extensive experiments on a wide range of VL tasks demonstrate the effectiveness of EgoVLPv2 by achieving consistent state-of-the-art performance over strong baselines across all downstream. Our project page can be found at https://shramanpramanick.github.io/EgoVLPv2/.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Recognition | Charades-Ego | EgoVLPv2 | mAP | 34.1 | #2 of 6 | Archive leaderboard | report |
| Natural Language Queries | Ego4D | EgoVLPv2 | R@1 IoU=0.3 | 12.95 | #10 of 10 | Archive leaderboard | report |
| Natural Language Queries | Ego4D | EgoVLPv2 | R@1 IoU=0.5 | 7.91 | #10 of 10 | Archive leaderboard | report |
| Natural Language Queries | Ego4D | EgoVLPv2 | R@5 IoU=0.3 | 23.80 | #10 of 10 | Archive leaderboard | report |
| Natural Language Queries | Ego4D | EgoVLPv2 | R@5 IoU=0.5 | 16.11 | #10 of 10 | Archive leaderboard | report |
| Question Answering | EgoTaskQA | EgoVLPv2 | Direct | 46.26 | #1 of 4 | Archive leaderboard | report |
| Video Summarization | Query-Focused Video Summarization Dataset | EgoVLPv2 | F1 (avg) | 52.08 | #1 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections