Tracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos

Zongpu Zhang, Yang Hua, Tao Song, Zhengui Xue, Ruhui Ma, Neil Robertson, Haibing Guan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)
411 Downloads (Pure)


This paper tackles the task of online video object segmentation with weak supervision, i.e., labeling the target object and background with pixel-level accuracy in unconstrained videos, given only one bounding box information in the first frame. We present a novel tracking-assisted visual object segmentation framework to achieve this. On the one hand, initialized with a given bounding box in the first frame, the auxiliary object tracking module guides the segmentation module frame by frame by providing motion and region information, which is usually missing in semi-supervised methods. Moreover, compared with the unsupervised approach, our approach with such minimum supervision can focus on the target object without bringing unrelated objects into the final results. On the other hand, the video object segmentation module also improves the robustness of the visual object tracking module by pixel-level localization and objectness information. Thus, segmentation and tracking in our framework can mutually help each other in an online manner. To verify the generality and effectiveness of the proposed framework, we evaluate our weakly supervised method on two cross-domain datasets, i.e., the DAVIS and VOT2016 datasets, with the same configuration and parameter setting. Experimental results show the top performance of our method, which is even better than the leading semi-supervised methods. Furthermore, we conduct the extensive ablation study on our approach to investigate the influence of each component and main parameters.
Original languageEnglish
Title of host publicationACM International Conference on Multimedia 2018: Proceedings
Number of pages9
Publication statusPublished - 26 Oct 2018


Dive into the research topics of 'Tracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos'. Together they form a unique fingerprint.

Cite this