Discovering Human Interactions in Videos with Limited Data Labeling
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringHuman-Object Interaction DetectionSimilar Papers 제목 키워드 기반
Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding a…
Human-Object Interaction DetectionObjectobject-detectionObject Detection+1Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions
In this paper, we present a general framework for learning social affordance grammar as a spatiotemporal AND-OR graph (ST-AOG) from RGB-D videos of human interactions, and transfer the grammar to humanoids to enable a re…
Learning Asynchronous and Sparse Human-Object Interaction in Videos
Human activities can be learned from video. With effective modeling it is possible to discover not only the action labels but also the temporal structures of the activities such as the progression of the sub-activities. …
Human-Object Interaction DetectionObjectLearning to Imitate Object Interactions from Internet Videos
We study the problem of imitating object interactions from Internet videos. This requires understanding the hand-object interactions in 4D, spatially in 3D and over time, which is challenging due to mutual hand-object oc…
ObjectInterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos
Human motion generation has shown great advances thanks to the recent diffusion models trained on large-scale motion capture data. Most of existing works, however, currently target animation of isolated people in empty s…