Papers › Timeception for Complex Action Recognition

Timeception for Complex Action Recognition

4 Dec 2018CVPR 2019 6arXiv:1812.01289archive 2025-07-28

Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.

PaperPDFConference PDFCode

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

Code

noureldien/timeception officialmentioned in papermentioned on GitHubpytorchGPL-3.0 report
CMU-CREATE-Lab/deep-smoke-machine mentioned on GitHubpytorch report
QUVA-Lab/timeception mentioned on GitHubpytorchNOASSERTION 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 ClassificationAction RecognitionLong-video Activity RecognitionVideo Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Charades Timeception (R3D) MAP 41.1 #30 of 49 Archive leaderboard report
Action Classification Charades Timeception (I3D) MAP 37.2 #38 of 49 Archive leaderboard report
Action Classification Charades Timeception (R2D) MAP 31.6 #41 of 49 Archive leaderboard report
Long-video Activity Recognition Breakfast Timeception (I3D-K400-Pretrain-feature) mAP 61.82 #7 of 8 Archive leaderboard report
Video Classification Breakfast Timeception Accuracy (%) 71.3 #8 of 9 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

Convolution

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