Yuan-Ting Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yuan-Ting Hu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Alexander G. Schwing
University of Illinois Urbana-Champaign
3 shared publicationsJia-Bin Huang
Virginia Tech
2 shared publications- Alexander G. Schwing
University of Illinois Urbana-Champaign
1 shared publication Heng Wang
Facebook AI
1 shared publication- Jia-Bin Huang
University of Maryland College Park, College Park, USA
1 shared publication Kristen Grauman
Facebook AI Research
1 shared publication
Latest Publications
- 7 October 2018
- Published by Springer Nature
- p. 56-73
VideoMatch: Matching Based Video Object Segmentation
- 7 October 2018
- Published by Springer Nature
- p. 56-73
VideoMatch: Matching Based Video Object Segmentation
- 6 October 2018
- Published by Springer Nature
- p. 813-830
Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation
- 6 October 2018
- Published by Springer Nature
- p. 813-830
Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation
- Open Access
MaskRNN: Instance Level Video Object Segmentation
Instance level video object segmentation is an important technique for video editing and compression. To capture the temporal coherence, in this paper, we develop MaskRNN, a recurrent neural net approach which fuses in each frame the output of two deep nets for each object instance -- a binary segmentation net providing a mask and a localization net providing a bounding box. Due to the recurrent component and the localization component, our method is able to take advantage of long-term temporal structures of the video data as well as rejecting outliers. We validate the proposed algorithm on three challenging benchmark datasets, the DAVIS-2016 dataset, the DAVIS-2017 dataset, and the Segtrack v2 dataset, achieving state-of-the-art performance on all of them.
Open AccessMaskRNN: Instance Level Video Object Segmentation
Instance level video object segmentation is an important technique for video editing and compression. To capture the temporal coherence, in this paper, we develop MaskRNN, a recurrent neural net approach which fuses in each frame the output of two deep nets for each object instance -- a binary segmentation net providing a mask and a localization net providing a bounding box. Due to the recurrent component and the localization component, our method is able to take advantage of long-term temporal structures of the video data as well as rejecting outliers. We validate the proposed algorithm on three challenging benchmark datasets, the DAVIS-2016 dataset, the DAVIS-2017 dataset, and the Segtrack v2 dataset, achieving state-of-the-art performance on all of them.