Social Fabric: Tubelet Compositions for Video Relation Detection

Shuo Chen, Zenglin Shi, Pascal Mettes, Cees G. M. Snoek; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13485-13494


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:

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Chen_2021_ICCV, author = {Chen, Shuo and Shi, Zenglin and Mettes, Pascal and Snoek, Cees G. M.}, title = {Social Fabric: Tubelet Compositions for Video Relation Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {13485-13494} }