Detecting temporally consistent objects in videos through object class label propagation
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Detecting temporally consistent objects in videos through object class label propagation. / Tripathi, Subarna; Belongie, Serge; Hwang, Youngbae; Nguyen, Truong.
In: 2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016, 23.05.2016.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Detecting temporally consistent objects in videos through object class label propagation
AU - Tripathi, Subarna
AU - Belongie, Serge
AU - Hwang, Youngbae
AU - Nguyen, Truong
N1 - Publisher Copyright: © 2016 IEEE.
PY - 2016/5/23
Y1 - 2016/5/23
N2 - Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in learning a better video object detector A deep-learning based video object detector learned using the proposed VOP achieves state-of-the-art detection performance on the Youtube-Objects dataset. We further propose a clustering of VOPs which can efficiently be used for detecting objects in video in a streaming fashion. As opposed to applying per-frame convolutional neural network (CNN) based object detection, our proposed method called Objects in Video Enabler thRough LAbel Propagation (OVERLAP) needs to classify only a small fraction of all candidate proposals in every video frame through streaming clustering of object proposals and class-label propagation. Source code for VOP clustering is available at https://github. com/subtri/streaming-VOP-clustering.
AB - Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in learning a better video object detector A deep-learning based video object detector learned using the proposed VOP achieves state-of-the-art detection performance on the Youtube-Objects dataset. We further propose a clustering of VOPs which can efficiently be used for detecting objects in video in a streaming fashion. As opposed to applying per-frame convolutional neural network (CNN) based object detection, our proposed method called Objects in Video Enabler thRough LAbel Propagation (OVERLAP) needs to classify only a small fraction of all candidate proposals in every video frame through streaming clustering of object proposals and class-label propagation. Source code for VOP clustering is available at https://github. com/subtri/streaming-VOP-clustering.
UR - http://www.scopus.com/inward/record.url?scp=84977665623&partnerID=8YFLogxK
U2 - 10.1109/WACV.2016.7477702
DO - 10.1109/WACV.2016.7477702
M3 - Conference article
AN - SCOPUS:84977665623
JO - 2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016
JF - 2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016
T2 - IEEE Winter Conference on Applications of Computer Vision, WACV 2016
Y2 - 7 March 2016 through 10 March 2016
ER -
ID: 301828559