Papers › Temporal RoI Align for Video Object Recognition

Temporal RoI Align for Video Object Recognition

8 Sep 2021arXiv:2109.03495archive 2025-07-28

Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng

Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, RoI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted RoI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal RoI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal RoI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal RoI Align can also be applied into video instance segmentation. Codes are available at https://github.com/open-mmlab/mmtracking

PaperPDFCode

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

Code

open-mmlab/mmtracking officialmentioned in paperpytorchApache-2.0 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

Instance SegmentationObjectObject DetectionObject RecognitionSemantic SegmentationVideo Instance SegmentationVideo Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation YouTube-VIS Temporal ROI Align mask AP 38 #1 of 1 Archive leaderboard report
Video Object Detection EPIC KITCHENS-seen splits Temporal ROI Align mAP 42.2 #1 of 1 Archive leaderboard report
Video Object Detection EPIC KITCHENS-unseen splits Temporal ROI Align mAP 39.6 #1 of 1 Archive leaderboard report
Video Object Detection ImageNet VID Temporal ROI Align (ResNeXt101) MAP 84.3 #18 of 33 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

ALIGNTemporal ROIAlign

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