In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
Mobile devices are increasingly powerful in media storage and rendering. The prevalent request of decent video browsing on mobile devices is demanding. However, one limitation com...
In this work, we propose new graph-based data model and indexing to organize and manage video data. To consider spatial and temporal characteristics of video, we introduce a new g...
In this paper, we propose a method for exciting event detection in broadcast soccer video with mid-level description and SVM-based incremental learning. In the method, video frame...
Qixiang Ye, Qingming Huang, Wen Gao, Shuqiang Jian...