Papers › Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

31 Mar 2020ECCV 2020 8arXiv:2004.00163archive 2025-07-28

Zhekun Luo, Devin Guillory, Baifeng Shi, Wei Ke, Fang Wan, Trevor Darrell, Huijuan Xu

Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multiple Instance Learning (MIL) framework, where a bag (video) contains multiple instances (action segments). Since only the bag's label is known, the main challenge is assigning which key instances within the bag to trigger the bag's label. Most previous models use attention-based approaches applying attentions to generate the bag's representation from instances, and then train it via the bag's classification. These models, however, implicitly violate the MIL assumption that instances in negative bags should be uniformly negative. In this work, we explicitly model the key instances assignment as a hidden variable and adopt an Expectation-Maximization (EM) framework. We derive two pseudo-label generation schemes to model the E and M process and iteratively optimize the likelihood lower bound. We show that our EM-MIL approach more accurately models both the learning objective and the MIL assumptions. It achieves state-of-the-art performance on two standard benchmarks, THUMOS14 and ActivityNet1.2.

PaperPDFConference PDFCode

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

Code

airmachine/EM-MIL-WeaklyActionDetection officialmentioned in paperpytorch 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 LocalizationMultiple Instance LearningPseudo LabelWeakly Supervised Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised Action Localization THUMOS14 EM-ML avg-mAP (0.1-0.5) 44.9 #11 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 EM-ML avg-mAP (0.1:0.7) 37.7 #11 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 EM-ML avg-mAP (0.3-0.7) 30.4 #11 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS’14 EM-MIL mAP@0.5 30.5 #10 of 13 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