Paper Info
Title
Object Trajectory Proposal via Hierarchical Volume Grouping.
Abstract
Object trajectory proposal aims to locate category-independent object candidates in videos with a limited number of trajectories,i.e.,bounding box sequences. Most existing methods, which derive from combining object proposal with tracking, cannot handle object trajectory proposal effectively due to the lack of comprehensive objectness measurement through analyzing spatio-temporal characteristics over a whole video. In this paper, we propose a novel object trajectory proposal method using hierarchical volume grouping. Specifically, we first represent a given video with hierarchical volumes by mapping hierarchical regions with optical flow. Then, we filter the short volumes and background volumes, and combinatorially group the retained volumes into object candidates. Finally, we rank the object candidates using a multi-modal fusion scoring mechanism, which incorporates both appearance objectness and motion objectness, and generate the bounding boxes of the object candidates with the highest scores as the trajectory proposals. We validated the proposed method on a dataset consisting of 200 videos from ILSVRC2016-VID. The experimental results show that our method is superior to the state-of-the-art object trajectory proposal methods.
Year
DOI
Venue
2018
10.1145/3206025.3206059
ICMR '18: International Conference on Multimedia Retrieval Yokohama Japan June, 2018
Keywords
Field
DocType
Object trajectory proposal, hierarchical volume representation, volume combinatorial grouping, multi-modal fusion scoring
Pattern recognition,Computer science,Artificial intelligence,Optical flow,Trajectory,Bounding overwatch,Minimum bounding box
Conference
ISBN
Citations 
PageRank 
978-1-4503-5046-4
3
0.40
References 
Authors
25
6
Name
Order
Citations
PageRank
Xu Sun193.18
Yuantian Wang230.73
Tongwei Ren332830.22
Zhi Liu479258.22
Zheng-Jun Zha52822152.79
Gangshan Wu627536.63