no code implementations • 5 Nov 2023 • Huining Li, Yalong Jiang, Xianlin Zeng, Feng Li, Zhipeng Wang
Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction.
1 code implementation • 6 Sep 2023 • Yalong Jiang, Changkang Li
In this paper, we propose to completely represent the motion patterns of objects by learning from long-term sequences.
no code implementations • 28 Feb 2023 • Yalong Jiang
To improve the model robustness, we propose a novel method to determine the task-irrelevant content in inputs which increases the domain discrepancy.
1 code implementation • 3 Sep 2022 • Xingrun Xing, Yangguang Li, Wei Li, Wenrui Ding, Yalong Jiang, Yufeng Wang, Jing Shao, Chunlei Liu, Xianglong Liu
Second, to improve the robustness of binary models with contextual dependencies, we compute the contextual dynamic embeddings to determine the binarization thresholds in general binary convolutional blocks.
no code implementations • 8 Dec 2021 • Xianlin Zeng, Yalong Jiang, Wenrui Ding, Hongguang Li, Yafeng Hao, Zifeng Qiu
High-level graph representations encode the trajectories of people and the interactions among multiple identities while low-level graph representations encode the local body postures of each person.