Two-Branch Collaborative Strategy for Weakly Supervised Behavior Detection
Weakly supervised behavior detection aims to locate start and end boundaries of ac-tion and identify corresponding behavior categories using video-level labels.Most existing models still have problems such as incomplete behavior localization and background infer-ence.In this regard,the paper proposes a two-branch collaborative strategy,which intro-duces auxiliary classes for background frames,and adopts asymmetric training with a weight sharing mechanism,so that the model can suppress the activation of background frames to improve localization performance.In the optimization,the center loss term is proposed,which aims to enhance their discriminability through action-specific clustering and minimi-zing the intra-class variations.The basic branch discards the central regions of the action classes and learns background features.Through iterative training,mining inconspicuous re-gions related to behaviors helps to better simulate the background and achieve complete posi-tioning of behavior.Extensive experiments are carried out on THUMOS14 and Activity-Net1.2 datasets and compared with other relevant literature,which proves the feasibility of the proposed algorithm.
temporal behavior localizationweakly supervised learningcenter loss termbackground classattention mechanism
万方数据
维普
