1 code implementation • 22 Jan 2022 • Prarthana Bhattacharyya, Chenge Li, Xiaonan Zhao, István Fehérvári, Jason Sun
For few-shot image classification we train SSL-ViTs without any supervision, on external data, and use this trained embedder to adapt quickly to novel classes with limited number of labels.
no code implementations • 4 Feb 2019 • Chenge Li, Gregory Dobler, Xin Feng, Yao Wang
We propose a novel network structure named trackNet that can directly detect a 3D tube enclosing a moving object in a video segment by extending the faster R-CNN framework.
1 code implementation • 4 Feb 2019 • Chenge Li, Weixi Zhang, Yong liu, Yao Wang
In this work, we treat the FoV prediction as a sequence learning problem, and propose to predict the target user's future FoV not only based on the user's own past FoV center trajectory but also other users' future FoV locations.
no code implementations • 20 Nov 2017 • Yilin Song, Chenge Li, Yao Wang
In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background.