Learn More
Attributes are visual concepts that can be detected by machines, understood by humans, and shared across categories. They are particularly useful for fine-grained domains where categories are closely related to one other (e.g. bird species recognition). In such scenarios, relevant attributes are often local (e.g. " white belly "), but the question of how to(More)
Detecting humans and recognizing their body poses is a key problem in understanding natural images, since people are the focus of many (if not most) consumer photographs. Pose recognition is a challenging problem due not only to the usual complications of object recognition— cluttered backgrounds, scale changes, illumination variations, etc.—but also(More)
Photo-sharing websites have become very popular in the last few years, leading to huge collections of online images. In addition to image data, these websites collect a variety of multimodal metadata about photos including text tags, captions, GPS coordinates, camera metadata, user profiles, etc. However, this metadata is not well constrained and is often(More)
Vehicle recognition is a challenging task with many useful applications. State-of-the-art methods usually learn dis-criminative classifiers for different vehicle categories or different viewpoint angles, but little work has explored vehicle recognition using semantic visual attributes. In this paper , we propose a novel iterative multiple instance learning(More)
of bladder, prostate for male (uterus for female) and rectum was defined as TPE and the resection of bladder and uterus as APE. The perioperative characters, pathological results and patients' survival were collected and analyzed. Results: There were seven males and 13 females in this study with an average age of 65. Ten case accepted APE and 10 for TPE.(More)
We introduce a hierarchical part-based approach for human pose estimation in static images. Our model is a multi-layer composite of tree-structured pictorial-structure models, each modeling human pose at a different scale and with a different graphical structure. At the highest level, the submodel acts as a person detector, while at the lowest level, the(More)