Papers › Contextual Action Recognition with R*CNN

Contextual Action Recognition with R*CNN

5 May 2015ICCV 2015 12arXiv:1505.01197archive 2025-07-28

Georgia Gkioxari, Ross Girshick, Jitendra Malik

There are multiple cues in an image which reveal what action a person is performing. For example, a jogger has a pose that is characteristic for jogging, but the scene (e.g. road, trail) and the presence of other joggers can be an additional source of information. In this work, we exploit the simple observation that actions are accompanied by contextual cues to build a strong action recognition system. We adapt RCNN to use more than one region for classification while still maintaining the ability to localize the action. We call our system R*CNN. The action-specific models and the feature maps are trained jointly, allowing for action specific representations to emerge. R*CNN achieves 90.2% mean AP on the PASAL VOC Action dataset, outperforming all other approaches in the field by a significant margin. Last, we show that R*CNN is not limited to action recognition. In particular, R*CNN can also be used to tackle fine-grained tasks such as attribute classification. We validate this claim by reporting state-of-the-art performance on the Berkeley Attributes of People dataset.

PaperPDFConference PDFCode

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

Code

gkioxari/RstarCNN officialmentioned in papermentioned on GitHubcaffe2NOASSERTION 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 RecognitionAttributeGeneral ClassificationHuman-Object Interaction DetectionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human-Object Interaction Detection HICO R*CNN mAP 28.5 #8 of 8 Archive leaderboard report
Weakly Supervised Object Detection Charades R*CNN MAP 0.99 #5 of 6 Archive leaderboard report
Weakly Supervised Object Detection HICO-DET R*CNN MAP 2.15 #4 of 4 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