We address the problem of understanding an indoor scene from a single image in terms of recovering the layouts of the faces (floor, ceiling, walls) and furniture. A major challeng...
We present a method for estimating eye gaze direction, which represents a departure from conventional eye gaze estimation methods, the majority of which are based on tracking spec...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Facial attributes such as gender, race, age, hair style, etc., carry rich information for locating designated persons and profiling the communities from image/video collections (...
Yan-Ying Chen, Winston H. Hsu, Hong-Yuan Mark Liao
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...