Papers › RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos

RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos

11 Dec 2023arXiv:2312.06729archive 2025-07-28

Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, Gedas Bertasius

Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

tanveer81/rgnet officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video ReCap: Recursive Captioning of Hour-Long Videos (arXiv:2402.13250; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tanveer81/revisionllm mentioned on GitHubpytorchSyntology: not harvested report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Moment RetrievalNatural Language QueriesRetrievalText RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Moment Retrieval MAD RGNet R@1,IoU=0.1 12.43 #3 of 8 Archive leaderboard report
Natural Language Moment Retrieval MAD RGNet R@1,IoU=0.3 9.48 #3 of 8 Archive leaderboard report
Natural Language Moment Retrieval MAD RGNet R@1,IoU=0.5 5.61 #3 of 8 Archive leaderboard report
Natural Language Moment Retrieval MAD RGNet R@5,IoU=0.1 25.12 #3 of 8 Archive leaderboard report
Natural Language Moment Retrieval MAD RGNet R@5,IoU=0.3 18.72 #3 of 8 Archive leaderboard report
Natural Language Moment Retrieval MAD RGNet R@5,IoU=0.5 10.86 #3 of 8 Archive leaderboard report
Natural Language Queries Ego4D RGNet R@1 IoU=0.3 20.63 #4 of 10 Archive leaderboard report
Natural Language Queries Ego4D RGNet R@1 IoU=0.5 12.47 #4 of 10 Archive leaderboard report
Natural Language Queries Ego4D RGNet R@1 Mean(0.3 and 0.5) 16.55 #4 of 10 Archive leaderboard report
Natural Language Queries Ego4D RGNet R@5 IoU=0.3 41.67 #4 of 10 Archive leaderboard report
Natural Language Queries Ego4D RGNet R@5 IoU=0.5 25.08 #4 of 10 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.

Methods

CLIP

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