Attentive Action and Context Factorization
This work addresses the problem of human action recognition in video for computer vision researchers, offering an incremental improvement through weakly supervised factorization.
The paper tackles the challenge of localizing spatiotemporal regions that define human actions in video by separating actions from co-occurring contextual factors using a novel attentional mechanism, achieving higher accuracy and better interpretability in action recognition.
We propose a method for human action recognition, one that can localize the spatiotemporal regions that `define' the actions. This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual elements. To address this challenge, we utilize conjugate samples of human actions, which are video clips that are contextually similar to human action samples but do not contain the action. We introduce a novel attentional mechanism that can spatially and temporally separate human actions from the co-occurring contextual factors. The separation of the action and context factors is weakly supervised, eliminating the need for laboriously detailed annotation of these two factors in training samples. Our method can be used to build human action classifiers with higher accuracy and better interpretability. Experiments on several human action recognition datasets demonstrate the quantitative and qualitative benefits of our approach.