1 code implementation • 23 May 2023 • Mingkun Li, Peng Xu, Chun-Guang Li, Jun Guo
In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change.
Ranked #1 on Unsupervised Person Re-Identification on PRCC
Clothes Changing Person Re-Identification Contrastive Learning +3
no code implementations • 7 Feb 2022 • Mingkun Li, Shupeng Cheng, Peng Xu, Xiatian Zhu, Chun-Guang Li, Jun Guo
We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment.
Clustering Unsupervised Long Term Person Re-Identification +2
no code implementations • 28 Jan 2022 • He Sun, Mingkun Li, Chun-Guang Li
The most popular approaches to tackle unsupervised person ReID are usually performing a clustering algorithm to yield pseudo labels at first and then exploit the pseudo labels to train a deep neural network.
Ranked #1 on Unsupervised Person Re-Identification on DukeMTMCreID (MAP metric)
1 code implementation • CVPR 2021 • Shangzhi Zhang, Chong You, René Vidal, Chun-Guang Li
We show that our SENet can not only learn the self-expressive coefficients with desired properties on the training data, but also handle out-of-sample data.
1 code implementation • 15 Jun 2021 • Mingkun Li, Chun-Guang Li, Jun Guo
To be specific, we propose a novel cluster-level contrastive loss to help the siamese network effectively mine the invariance in feature learning with respect to the cluster structure within and between different data augmentation views, respectively.
1 code implementation • 24 Sep 2020 • Yihao Chen, Xin Tang, Xianbiao Qi, Chun-Guang Li, Rong Xiao
We conduct extensive experiments on benchmark datasets for different tasks, including node classification, link prediction, graph classification and graph regression, and confirm that the learned graph normalization leads to competitive results and that the learned weights suggest the appropriate normalization techniques for the specific task.
no code implementations • ICCV 2019 • Chong You, Chun-Guang Li, Daniel P. Robinson, Rene Vidal
Specifically, our analysis provides conditions that guarantee the correctness of affine subspace clustering methods both with and without the affine constraint, and shows that these conditions are satisfied for high-dimensional data.
no code implementations • CVPR 2020 • Ying Chen, Chun-Guang Li, Chong You
State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points.
no code implementations • IEEE Access 2019 • Junjian Zhang, Chun-Guang Li, Tianming Du, Honggang Zhang, Jun Guo
Standard methods of subspace clustering are based on self-expressiveness in the original data space, which states that a data point in a subspace can be expressed as a linear combination of other points.
no code implementations • CVPR 2019 • Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin
However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces.
Ranked #2 on Image Clustering on Extended Yale-B
no code implementations • 26 Apr 2019 • Xiaokun Pu, Chun-Guang Li
In this paper, we address the problem of adaptive learning for autoregressive moving average (ARMA) model in the quaternion domain.
no code implementations • 1 Mar 2019 • Junhao Hua, Chun-Guang Li
This paper is concerned with the problem of distributed extended object tracking, which aims to collaboratively estimate the state and extension of an object by a network of nodes.
no code implementations • 17 Aug 2018 • Chun-Guang Li, Chong You, René Vidal
In this paper, we develop a novel geometric analysis for a variant of SSC, named affine SSC (ASSC), for the problem of clustering data from a union of affine subspaces.
no code implementations • 21 May 2018 • Chun-Guang Li, Junjian Zhang, Jun Guo
Subspace clustering refers to the problem of segmenting high dimensional data drawn from a union of subspaces into the respective subspaces.
no code implementations • 20 May 2018 • Ruo-Pei Guo, Chun-Guang Li, Yonghua Li, Jia-Ru Lin, Jun Guo
In this paper, we propose to exploit a density-adaptive smooth kernel technique to achieve efficient and effective reranking.
no code implementations • CVPR 2018 • Jianlou Si, Honggang Zhang, Chun-Guang Li, Jason Kuen, Xiangfei Kong, Alex C. Kot, Gang Wang
Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space.
no code implementations • 17 Oct 2016 • Chun-Guang Li, Chong You, René Vidal
In this paper, we propose a joint optimization framework --- Structured Sparse Subspace Clustering (S$^3$C) --- for learning both the affinity and the segmentation.
1 code implementation • CVPR 2016 • Chong You, Chun-Guang Li, Daniel P. Robinson, Rene Vidal
Our geometric analysis also provides a theoretical justification and a geometric interpretation for the balance between the connectedness (due to $\ell_2$ regularization) and subspace-preserving (due to $\ell_1$ regularization) properties for elastic net subspace clustering.
Ranked #7 on Image Clustering on coil-100 (Accuracy metric)
no code implementations • ICCV 2015 • Chun-Guang Li, Zhouchen Lin, Honggang Zhang, Jun Guo
State of the art approaches for Semi-Supervised Learning (SSL) usually follow a two-stage framework -- constructing an affinity matrix from the data and then propagating the partial labels on this affinity matrix to infer those unknown labels.
no code implementations • CVPR 2015 • Chun-Guang Li, Rene Vidal
Our framework is based on expressing each data point as a structured sparse linear combination of all other data points, where the structure is induced by a norm that depends on the unknown segmentation.
no code implementations • 16 Feb 2015 • Xianbiao Qi, Guoying Zhao, Chun-Guang Li, Jun Guo, Matti Pietikäinen
Indirect Immunofluorescence (IIF) HEp-2 cell image is an effective evidence for diagnosis of autoimmune diseases.
no code implementations • 1 Feb 2015 • Xianbiao Qi, Chun-Guang Li, Guoying Zhao, Xiaopeng Hong, Matti Pietikäinen
Moreover we explore two different implementations of the TCoF scheme, i. e., the \textit{spatial} TCoF and the \textit{temporal} TCoF, in which the mean-removed frames and the difference between two adjacent frames are used as the inputs of the ConvNet, respectively.