Papers › Attention-Based Context Aware Reasoning for Situation Recognition

Attention-Based Context Aware Reasoning for Situation Recognition

1 Jun 2020CVPR 2020 6archive 2025-07-28

Thilini Cooray, Ngai-Man Cheung, Wei Lu

Situation Recognition (SR) is a fine-grained action recognition task where the model is expected to not only predict the salient action of the image, but also predict values of all associated semantic roles of the action. Predicting semantic roles is very challenging: a vast variety of possibilities can be the match for a semantic role. Existing work has focused on dependency modelling architectures to solve this issue. Inspired by the success achieved by query-based visual reasoning (e.g., Visual Question Answering), we propose to address semantic role prediction as a query-based visual reasoning problem. However, existing query-based reasoning methods have not considered handling of inter-dependent queries which is a unique requirement of semantic role prediction in SR. Therefore, to the best of our knowledge, we propose the first set of methods to address inter-dependent queries in query-based visual reasoning. Extensive experiments demonstrate the effectiveness of our proposed method which achieves outstanding performance on Situation Recognition task. Furthermore, leveraging query inter-dependency, our methods improve upon a state-of-the-art method that answers queries separately. Our code: https://github.com/thilinicooray/context-aware-reasoning-for-sr

PaperPDFCode

Code

thilinicooray/context-aware-reasoning-for-sr 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 RecognitionFine-grained Action RecognitionGrounded Situation RecognitionQuestion AnsweringSituation RecognitionVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Grounded Situation Recognition SWiG CAQ + RE-VGG Top-1 Verb 38.19 #9 of 13 Archive leaderboard report
Grounded Situation Recognition SWiG CAQ + RE-VGG Top-1 Verb & Value 30.23 #9 of 13 Archive leaderboard report
Grounded Situation Recognition SWiG CAQ + RE-VGG Top-5 Verbs 65.05 #9 of 13 Archive leaderboard report
Grounded Situation Recognition SWiG CAQ + RE-VGG Top-5 Verbs & Value 50.21 #9 of 13 Archive leaderboard report
Situation Recognition imSitu CAQ + RE-VGG Top-1 Verb 38.19 #9 of 13 Archive leaderboard report
Situation Recognition imSitu CAQ + RE-VGG Top-1 Verb & Value 30.23 #9 of 13 Archive leaderboard report
Situation Recognition imSitu CAQ + RE-VGG Top-5 Verbs 65.05 #9 of 13 Archive leaderboard report
Situation Recognition imSitu CAQ + RE-VGG Top-5 Verbs & Value 50.21 #9 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