Papers › LSTA: Long Short-Term Attention for Egocentric Action Recognition

LSTA: Long Short-Term Attention for Egocentric Action Recognition

26 Nov 2018CVPR 2019 6arXiv:1811.10698archive 2025-07-28

Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz

Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention mechanisms, they are either annotation consuming or do not take spatio-temporal patterns into account. In this paper we propose LSTA as a mechanism to focus on features from spatial relevant parts while attention is being tracked smoothly across the video sequence. We demonstrate the effectiveness of LSTA on egocentric activity recognition with an end-to-end trainable two-stream architecture, achieving state of the art performance on four standard benchmarks.

PaperPDFConference PDFCode

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

Code

swathikirans/LSTA 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

Action RecognitionActivity RecognitionEgocentric Activity RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Egocentric Activity Recognition EGTEA LSTA Average Accuracy 61.9 #5 of 6 Archive leaderboard report
Egocentric Activity Recognition EGTEA LSTA Mean class accuracy - #5 of 6 Archive leaderboard report
Egocentric Activity Recognition EPIC-KITCHENS-55 LSTA Actions Top-1 (S2) 16.63 #7 of 7 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