Papers › Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation

Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation

15 Nov 2021arXiv:2111.07529archive 2025-07-28

Anirudh S Chakravarthy, Won-Dong Jang, Zudi Lin, Donglai Wei, Song Bai, Hanspeter Pfister

Video instance segmentation aims to detect, segment, and track objects in a video. Current approaches extend image-level segmentation algorithms to the temporal domain. However, this results in temporally inconsistent masks. In this work, we identify the mask quality due to temporal stability as a performance bottleneck. Motivated by this, we propose a video instance segmentation method that alleviates the problem due to missing detections. Since this cannot be solved simply using spatial information, we leverage temporal context using inter-frame attentions. This allows our network to refocus on missing objects using box predictions from the neighbouring frame, thereby overcoming missing detections. Our method significantly outperforms previous state-of-the-art algorithms using the Mask R-CNN backbone, by achieving 36.0% mAP on the YouTube-VIS benchmark. Additionally, our method is completely online and requires no future frames. Our code is publicly available at https://github.com/anirudh-chakravarthy/ObjProp.

Paper PDF Code

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

Code

anirudh-chakravarthy/objprop 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

Instance Segmentation Segmentation Semantic Segmentation Video Instance Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Video Instance Segmentation	YouTube-VIS validation	ObjProp (ResNet-50)	AP50	59.4	#32 of 44	Archive leaderboard	report
Video Instance Segmentation	YouTube-VIS validation	ObjProp (ResNet-50)	AP75	39.2	#32 of 44	Archive leaderboard	report
Video Instance Segmentation	YouTube-VIS validation	ObjProp (ResNet-50)	AR1	39.1	#32 of 44	Archive leaderboard	report
Video Instance Segmentation	YouTube-VIS validation	ObjProp (ResNet-50)	AR10	47.7	#32 of 44	Archive leaderboard	report
Video Instance Segmentation	YouTube-VIS validation	ObjProp (ResNet-50)	mask AP	36.0	#32 of 44	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

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Mask R-CNN Max Pooling RPN ReLU Residual Block Residual Connection RoIAlign Softmax

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