Papers › GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval

GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval

1 Apr 2022arXiv:2204.00486archive 2025-07-28

Yuxuan Wang, Difei Gao, Licheng Yu, Stan Weixian Lei, Matt Feiszli, Mike Zheng Shou

Cognitive science has shown that humans perceive videos in terms of events separated by the state changes of dominant subjects. State changes trigger new events and are one of the most useful among the large amount of redundant information perceived. However, previous research focuses on the overall understanding of segments without evaluating the fine-grained status changes inside. In this paper, we introduce a new dataset called Kinetic-GEB+. The dataset consists of over 170k boundaries associated with captions describing status changes in the generic events in 12K videos. Upon this new dataset, we propose three tasks supporting the development of a more fine-grained, robust, and human-like understanding of videos through status changes. We evaluate many representative baselines in our dataset, where we also design a new TPD (Temporal-based Pairwise Difference) Modeling method for visual difference and achieve significant performance improvements. Besides, the results show there are still formidable challenges for current methods in the utilization of different granularities, representation of visual difference, and the accurate localization of status changes. Further analysis shows that our dataset can drive developing more powerful methods to understand status changes and thus improve video level comprehension. The dataset is available at https://github.com/showlab/GEB-Plus

PaperPDFCode

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

Code

yuxuan-w/geb-plus officialmentioned in papermentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

Boundary CaptioningBoundary GroundingRetrievalText to Video Retrieval

Datasets

Introduced by this paper, per the archive.

Kinetics-GEB+

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Boundary Captioning Kinetics-GEB+ ActBERT-revised CIDEr 74.71 #1 of 1 Archive leaderboard report
Boundary Captioning Kinetics-GEB+ ActBERT-revised ROUGE-L 28.15 #1 of 1 Archive leaderboard report
Boundary Captioning Kinetics-GEB+ ActBERT-revised SPICE 19.52 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@0.1s 4.28 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@0.2s 8.54 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@0.5s 18.33 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@1.0s 31.04 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@1.5s 40.48 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@2.0s 47.86 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@2.5s 54.81 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@3.0s 61.45 #1 of 1 Archive leaderboard report
Boundary Grounding Kinetics-GEB+ FROZEN-revised F1@Avg 33.35 #1 of 1 Archive leaderboard report
Text to Video Retrieval Kinetics-GEB+ FROZEN-revised mAP 23.39 #1 of 2 Archive leaderboard report
Text to Video Retrieval Kinetics-GEB+ FROZEN-revised (two-stream) text-to-video R@1 12.8 #2 of 2 Archive leaderboard report
Text to Video Retrieval Kinetics-GEB+ FROZEN-revised (two-stream) text-to-video R@10 45.66 #2 of 2 Archive leaderboard report
Text to Video Retrieval Kinetics-GEB+ FROZEN-revised (two-stream) text-to-video R@5 34.81 #2 of 2 Archive leaderboard report
Text to Video Retrieval Kinetics-GEB+ FROZEN-revised (two-stream) text-to-video R@50 68.1 #2 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