Timezone: »

Using body-anchored priors for identifying actions in single images
Leonid Karlinsky · Michael Dinerstein · Shimon Ullman

Wed Dec 08 12:00 AM -- 12:00 AM (PST) @

This paper presents an approach to the visual recognition of human actions using only single images as input. The task is easy for humans but difficult for current approaches to object recognition, because action instances may be similar in terms of body pose, and often require detailed examination of relations between participating objects and body parts in order to be recognized. The proposed approach applies a two-stage interpretation procedure to each training and test image. The first stage produces accurate detection of the relevant body parts of the actor, forming a prior for the local evidence needed to be considered for identifying the action. The second stage extracts features that are ‘anchored’ to the detected body parts, and uses these features and their feature-to-part relations in order to recognize the action. The body anchored priors we propose apply to a large range of human actions. These priors allow focusing on the relevant regions and relations, thereby significantly simplifying the learning process and increasing recognition performance.

Author Information

Leonid Karlinsky (Weizmann Institute of Science)
Michael Dinerstein (Weizmann Institute of Science)
Shimon Ullman (Weizmann Institute of Science)

More from the Same Authors