Papers › Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

21 Jul 2015arXiv:1507.05738archive 2025-07-28

Serena Yeung, Olga Russakovsky, Ning Jin, Mykhaylo Andriluka, Greg Mori, Li Fei-Fei

Every moment counts in action recognition. A comprehensive understanding of human activity in video requires labeling every frame according to the actions occurring, placing multiple labels densely over a video sequence. To study this problem we extend the existing THUMOS dataset and introduce MultiTHUMOS, a new dataset of dense labels over unconstrained internet videos. Modeling multiple, dense labels benefits from temporal relations within and across classes. We define a novel variant of long short-term memory (LSTM) deep networks for modeling these temporal relations via multiple input and output connections. We show that this model improves action labeling accuracy and further enables deeper understanding tasks ranging from structured retrieval to action prediction.

PaperPDFCode

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

Code

lauradhatt/Interesting-Reads mentioned on GitHub 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 RecognitionRetrievalTemporal Action Localization

Datasets

Introduced by this paper, per the archive.

MultiTHUMOS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection Multi-THUMOS Two-stream + LSTM mAP 28.1 #7 of 8 Archive leaderboard report
Action Detection Multi-THUMOS Two-stream mAP 27.6 #8 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