Discovering Human Interactions in Videos with Limited Data Labeling

Resource type
Thesis type
(Thesis) M.Sc.
Date created
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not available in many practical cases. Here, we focus on recovering semantically meaningful clusters of human-human and human-object interaction in an unsupervised fashion. A new iterative solution is introduced based on Maximum Margin Clustering (MMC), which also accepts user feedback to refine clusters. This is achieved by formulating the whole process as a unified constrained latent max-margin clustering problem. Extensive experiments have been carried out over three challenging datasets, Collective Activity, VIRAT, and UT-interaction. Empirical results demonstrate that the proposed algorithm can efficiently discover perfect semantic clusters of human interactions with only a small amount of labeling effort.
Copyright statement
Copyright is held by the author.
The author granted permission for the file to be printed and for the text to be copied and pasted.
Scholarly level
Supervisor or Senior Supervisor
Thesis advisor: Mori, Greg
Thesis advisor: Li, Ze-Nian
Member of collection
Attachment Size
etd8839_MKhodabandeh.pdf 9.08 MB