Papers › Mining Inter-Video Proposal Relations for Video Object Detection

Mining Inter-Video Proposal Relations for Video Object Detection

1 Aug 2020ECCV 2020 8archive 2025-07-28

Mingfei Han, Yali Wang, Xiaojun Chang, Yu Qiao

Recent studies have shown that, context aggregating information from proposals in different frames can clearly enhance the performance of video object detection. However, these approaches mainly exploit the intra-proposal relation within single video, while ignoring the intra-proposal relation among different videos, which can provide important discriminative cues for recognizing confusing objects. To address the limitation, we propose a novel Inter-Video Proposal Relation module. Based on a concise multi-level triplet selection scheme, this module can learn effective object representations via modeling relations of hard proposals among different videos. Moreover, we design a Hierarchical Video Relation Network (HVR-Net), by integrating intra-video and inter-video proposal relations in a hierarchical fashion. This design can progressively exploit both intra and inter contexts to boost video object detection. We examine our method on the large-scale video object detection benchmark, i.e., ImageNet VID, where HVR-Net achieves the SOTA results. Codes and models will be released afterwards.

PaperPDFCode

Code

youthHan/HVRNet 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

ObjectObject DetectionRelation NetworkVideo Object Detectionobject-detection

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Detection ImageNet VID HVRNet (ResNeXt101-32x4d) MAP 85.5 #14 of 33 Archive leaderboard report
Video Object Detection ImageNet VID HVRNet (ResNest101) MAP 83.8 #21 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingNon-Local OperationReLUResNeXtResNeXt BlockResidual BlockResidual Connection

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