no code implementations • 13 Apr 2024 • Chengpei Xu, Hao Fu, Long Ma, Wenjing Jia, Chengqi Zhang, Feng Xia, Xiaoyu Ai, Binghao Li, Wenjie Zhang
Localizing text in low-light environments is challenging due to visual degradations.
no code implementations • 26 Dec 2023 • Yao Liu, Binghao Li, Xianzhi Wang, Claude Sammut, Lina Yao
We propose Attention-aware Social Graph Transformer Networks for multi-modal trajectory prediction.
no code implementations • 5 May 2023 • Jingcheng Li, Lina Yao, Binghao Li, Claude Sammut
Then the knowledge distillation method is applied to transfer the learned representation from the teacher model to a simpler DMFT student model, which consists of a lite version of the multi-modal spatial-temporal transformer module, to produce the results.
no code implementations • 15 Mar 2023 • Yao Liu, Zesheng Ye, Rui Wang, Binghao Li, Quan Z. Sheng, Lina Yao
Tremendous efforts have been put forth on predicting pedestrian trajectory with generative models to accommodate uncertainty and multi-modality in human behaviors.