Human vision system actively seeks interesting regions in images to reduce the search effort in tasks, such as object detection and recognition. Similarly, prominent actions in v...
Dynamic events can be regarded as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple st...
Abstract. We present a novel multi-modal evidence fusion method for highlevel feature (HLF) detection in videos. The uni-modal features, such as color histogram, transcript texts, ...
Ming Li, Yantao Zheng, Shouxun Lin, Yong-Dong Zhan...
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
The visual effects of rain are complex. Rain consists of spatially distributed drops falling at high velocities. Each drop refracts and reflects the environment, producing sharp i...