TY - GEN
T1 - Actionness ranking with lattice conditional ordinal random fields
AU - Chen, Wei
AU - Xiong, Caiming
AU - Xu, Ran
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/9/24
Y1 - 2014/9/24
N2 - Action analysis in image and video has been attracting more and more attention in computer vision. Recognizing specific actions in video clips has been the main focus. We move in a new, more general direction in this paper and ask the critical fundamental question: what is action, how is action different from motion, and in a given image or video where is the action? We study the philosophical and visual characteristics of action, which lead us to define actionness: intentional bodily movement of biological agents (people, animals). To solve the general problem, we propose the lattice conditional ordinal random field model that incorporates local evidence as well as neighboring order agreement. We implement the new model in the continuous domain and apply it to scoring actionness in both image and video datasets. Our experiments demonstrate not only that our new model can outperform the popular ranking SVM but also that indeed action is distinct from motion.
AB - Action analysis in image and video has been attracting more and more attention in computer vision. Recognizing specific actions in video clips has been the main focus. We move in a new, more general direction in this paper and ask the critical fundamental question: what is action, how is action different from motion, and in a given image or video where is the action? We study the philosophical and visual characteristics of action, which lead us to define actionness: intentional bodily movement of biological agents (people, animals). To solve the general problem, we propose the lattice conditional ordinal random field model that incorporates local evidence as well as neighboring order agreement. We implement the new model in the continuous domain and apply it to scoring actionness in both image and video datasets. Our experiments demonstrate not only that our new model can outperform the popular ranking SVM but also that indeed action is distinct from motion.
UR - http://www.scopus.com/inward/record.url?scp=84911442009&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911442009&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.101
DO - 10.1109/CVPR.2014.101
M3 - Conference contribution
AN - SCOPUS:84911442009
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 748
EP - 755
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -