Papers › Learning Latent Super-Events to Detect Multiple Activities in Videos

Learning Latent Super-Events to Detect Multiple Activities in Videos

5 Dec 2017CVPR 2018 6arXiv:1712.01938archive 2025-07-28

AJ Piergiovanni, Michael S. Ryoo

In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos. We define a super-event as a set of multiple events occurring together in videos with a particular temporal organization; it is the opposite concept of sub-events. Real-world videos contain multiple activities and are rarely segmented (e.g., surveillance videos), and learning latent super-events allows the model to capture how the events are temporally related in videos. We design temporal structure filters that enable the model to focus on particular sub-intervals of the videos, and use them together with a soft attention mechanism to learn representations of latent super-events. Super-event representations are combined with per-frame or per-segment CNNs to provide frame-level annotations. Our approach is designed to be fully differentiable, enabling end-to-end learning of latent super-event representations jointly with the activity detector using them. Our experiments with multiple public video datasets confirm that the proposed concept of latent super-event learning significantly benefits activity detection, advancing the state-of-the-arts.

PaperPDFConference PDFCode

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

Code

piergiaj/super-events-cvpr18 officialmentioned in papermentioned on GitHubpytorch report
piergiaj/tgm-icml19 mentioned 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

Action DetectionActivity Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection Charades Super-events (RGB+Flow) mAP 19.41 #14 of 16 Archive leaderboard report
Action Detection Multi-THUMOS I3D + our super-event mAP 36.4 #6 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