Qixing Huang
University of Texas at Austin
244 Papers
1.2K Citations
Qixing Huang is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 44, co-authored 132 publications. Previous affiliations of Qixing Huang include Stanford University & Google.
Chat about Author
Papers
Attention-guided Temporal Coherent Video Object Matting
Yunke Zhang,Chi Wang,Miaomiao Cui,Peiran Ren,Xuansong Xie,Xian-Sheng Hua,Hujun Bao,Qixing Huang,Weiwei Xu +8 more
TL;DR: In this article, an attention-based temporal aggregation module is proposed for video object matting, which computes temporal correlations for pixels adjacent to each other along the time axis in feature space to be robust against motion noises.
Effect of oil-modified crosslinked starch as a new fat replacer on gel properties, water distribution, and microstructures of pork meat batter.
TL;DR: The authors investigated the effects of oil-modified crosslinked starch (OIL-CTS) as a fat replacer on the gel properties, water distribution, microstructures, and fatty acid composition of pork batter.
33
•Posted Content
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
TL;DR: This work introduces a novel approach that extends the scope to extreme relative poses, with little or even no overlap between the input scans, to infer more complete scene information about the underlying environment and match on the completed scans.
32
Pathlet learning for compressing and planning trajectories
Chen Chen,Hao Su,Qixing Huang,Lin Zhang,Leonidas J. Guibas +4 more
- 05 Nov 2013
TL;DR: This work introduces the notion of pathlet for the purpose of compressing and planning trajectories, and proposes an effective approach whose complexity is linear in the number of trajectories.
Distributable Consistent Multi-object Matching
Nan Hu,Qixing Huang,Boris Thibert,Leonidas J. Guibas +3 more
- 01 Jun 2018
TL;DR: In this paper, the authors propose an optimization-based framework to multiple object matching, which divides the input object collection into overlapping sub-collections and enforce map consistency among each sub-collection.