1 code implementation • 6 May 2024 • Xingcheng Fu, Yisen Gao, Yuecen Wei, Qingyun Sun, Hao Peng, JianXin Li, Xianxian Li
Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation.
1 code implementation • 6 Jan 2024 • Liangtao Shi, Bineng Zhong, Qihua Liang, Ning li, Shengping Zhang, Xianxian Li
Specifically, we utilize spatio-temporal tokens to propagate information between consecutive frames without focusing on updating templates.
1 code implementation • 3 Jan 2024 • Yaozong Zheng, Bineng Zhong, Qihua Liang, Zhiyi Mo, Shengping Zhang, Xianxian Li
To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named \textbf{ODTrack}, which densely associates the contextual relationships of video frames in an online token propagation manner.
Ranked #1 on Visual Object Tracking on TrackingNet
Semi-Supervised Video Object Segmentation Visual Object Tracking +1
no code implementations • 19 Dec 2023 • Yuecen Wei, Haonan Yuan, Xingcheng Fu, Qingyun Sun, Hao Peng, Xianxian Li, Chunming Hu
Specifically, PoinDP first learns the hierarchy weights for each entity based on the Poincar\'e model in hyperbolic space.
1 code implementation • 27 Aug 2023 • Yaozong Zheng, Bineng Zhong, Qihua Liang, Guorong Li, Rongrong Ji, Xianxian Li
In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task.
1 code implementation • 2 Oct 2022 • Yuecen Wei, Xingcheng Fu, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang, Xianxian Li
To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology.
1 code implementation • CVPR 2021 • Siyuan Cheng, Bineng Zhong, Guorong Li, Xin Liu, Zhenjun Tang, Xianxian Li, Jing Wang
RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
1 code implementation • 3 Dec 2020 • Jinhuan Duan, Xianxian Li, Shiqi Gao, Jinyan Wang, Zili Zhong
In this paper, to prevent gradient leakage while keeping the accuracy of model, we propose the super stochastic gradient descent approach to update parameters by concealing the modulus length of gradient vectors and converting it or them into a unit vector.