Papers › LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
Weiheng Lu, Jian Li, An Yu, Ming-Ching Chang, Shengpeng Ji, Min Xia
Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction. We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR), which enables accurate moment retrieval and contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame and Time Encoding (DFTE) for spatial-temporal feature extraction, Informative Frame Selection (IFS) for capturing brief visual and motion patterns, and Dynamic Token Compression (DTC) to manage LLM context limitations. Evaluations on benchmarks like Charades-STA and QVHighlights demonstrate that LLaVA-MR outperforms 11 state-of-the-art methods, achieving an improvement of 1.82% in R1@0.5 and 1.29% in mAP@0.5 on the QVHighlights dataset. Our implementation will be open-sourced upon acceptance.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
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 |
|---|---|---|---|---|---|---|---|
| Moment Retrieval | Charades-STA | LLaVA-MR | R@1 IoU=0.5 | 70.65 | #2 of 25 | Archive leaderboard | report |
| Moment Retrieval | Charades-STA | LLaVA-MR | R@1 IoU=0.7 | 49.58 | #2 of 25 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | LLaVA-MR | R@1 IoU=0.5 | 76.59 | #3 of 32 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | LLaVA-MR | R@1 IoU=0.7 | 61.48 | #3 of 32 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | LLaVA-MR | mAP | 52.73 | #3 of 32 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | LLaVA-MR | mAP@0.5 | 69.41 | #3 of 32 | Archive leaderboard | report |
| Moment Retrieval | QVHighlights | LLaVA-MR | mAP@0.75 | 54.40 | #3 of 32 | Archive leaderboard | report |
| Natural Language Moment Retrieval | ActivityNet Captions | LLaVA-MR | R@1,IoU=0.5 | 55.16 | #2 of 8 | Archive leaderboard | report |
| Natural Language Moment Retrieval | ActivityNet Captions | LLaVA-MR | R@1,IoU=0.7 | 35.68 | #2 of 8 | 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