Papers › Social Fabric: Tubelet Compositions for Video Relation Detection

Social Fabric: Tubelet Compositions for Video Relation Detection

18 Aug 2021ICCV 2021 10arXiv:2108.08363archive 2025-07-28

Shuo Chen, Zenglin Shi, Pascal Mettes, Cees G. M. Snoek

This paper strives to classify and detect the relationship between object tubelets appearing within a video as a <subject-predicate-object> triplet. Where existing works treat object proposals or tubelets as single entities and model their relations a posteriori, we propose to classify and detect predicates for pairs of object tubelets a priori. We also propose Social Fabric: an encoding that represents a pair of object tubelets as a composition of interaction primitives. These primitives are learned over all relations, resulting in a compact representation able to localize and classify relations from the pool of co-occurring object tubelets across all timespans in a video. The encoding enables our two-stage network. In the first stage, we train Social Fabric to suggest proposals that are likely interacting. We use the Social Fabric in the second stage to simultaneously fine-tune and predict predicate labels for the tubelets. Experiments demonstrate the benefit of early video relation modeling, our encoding and the two-stage architecture, leading to a new state-of-the-art on two benchmarks. We also show how the encoding enables query-by-primitive-example to search for spatio-temporal video relations. Code: https://github.com/shanshuo/Social-Fabric.

PaperPDFConference PDFCode

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

Code

shanshuo/social-fabric officialmentioned in paper 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

ObjectVideo Visual Relation DetectionVideo Visual Relation Tagging

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Visual Relation Detection ImageNet-VidVRD Social Fabric Recall@100 16.88 #1 of 2 Archive leaderboard report
Video Visual Relation Detection ImageNet-VidVRD Social Fabric Recall@50 13.73 #1 of 2 Archive leaderboard report
Video Visual Relation Detection ImageNet-VidVRD Social Fabric mAP 20.08 #1 of 2 Archive leaderboard report
Video Visual Relation Detection VidOR Social Fabric Recall@100 11.94 #1 of 2 Archive leaderboard report
Video Visual Relation Detection VidOR Social Fabric Recall@50 9.99 #1 of 2 Archive leaderboard report
Video Visual Relation Detection VidOR Social Fabric mAP 11.21 #1 of 2 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