no code implementations • ECCV 2020 • Jibin Gao, Wei-Shi Zheng, Jia-Hui Pan, Chengying Gao, Yao-Wei Wang, Wei Zeng, Jian-Huang Lai
However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.
no code implementations • 21 Jun 2024 • Zixuan Chen, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie
As a result, CoCPF can accurately estimate the internal measurements between SV projections (i. e., DV sinograms), producing high-quality CT images after re-projection.
no code implementations • 21 Jun 2024 • Zixuan Chen, Ruijie Su, Jiahao Zhu, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie
Text-to-3D generation aims to create 3D assets from text-to-image diffusion models.
1 code implementation • CVPR 2024 • Yanzuo Lu, Manlin Zhang, Andy J Ma, Xiaohua Xie, Jian-Huang Lai
While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image.
no code implementations • 29 Dec 2023 • Yun Chen, Lingxiao Yang, Qi Chen, Jian-Huang Lai, Xiaohua Xie
We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content.
1 code implementation • 13 Dec 2023 • Yanzuo Lu, Meng Shen, Andy J Ma, Xiaohua Xie, Jian-Huang Lai
Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer.
Ranked #2 on
Universal Domain Adaptation
on Office-31
1 code implementation • 16 Jun 2023 • Wen-Zhi Li, Chang-Dong Wang, Hui Xiong, Jian-Huang Lai
Class imbalance is the phenomenon that some classes have much fewer instances than others, which is ubiquitous in real-world graph-structured scenarios.
1 code implementation • 16 Jun 2023 • Wen-Zhi Li, Chang-Dong Wang, Hui Xiong, Jian-Huang Lai
Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised learning on graphs, which generally follows the "augmenting-contrasting" learning scheme.
no code implementations • 12 May 2023 • Si-Guo Fang, Dong Huang, Chang-Dong Wang, Jian-Huang Lai
The bipartite graph structure has shown its promising ability in facilitating the subspace clustering and spectral clustering algorithms for large-scale datasets.
1 code implementation • ICCV 2023 • Zixuan Chen, Jian-Huang Lai, Lingxiao Yang, Xiaohua Xie
Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to super sample medical volumes at arbitrary scales via a single model.
no code implementations • Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2022 • Erna Chen, Zemin Cai, Jian-Huang Lai
To improve the generalization of our model to different echocardiography images, we propose Pseudo-Segmentation Penalty loss function.
Ranked #2 on
LV Segmentation
on Echonet-Dynamic
no code implementations • 25 Aug 2022 • Man-Sheng Chen, Tuo Liu, Chang-Dong Wang, Dong Huang, Jian-Huang Lai
In view of this, we propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity.
1 code implementation • 14 Jul 2022 • Yuankun Xu, Dong Huang, Chang-Dong Wang, Jian-Huang Lai
Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks.
1 code implementation • 26 Jun 2022 • Hua-Bao Ling, Bowen Zhu, Dong Huang, Ding-Hua Chen, Chang-Dong Wang, Jian-Huang Lai
Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning.
no code implementations • 1 Jun 2022 • Dong Huang, Ding-Hua Chen, Xiangji Chen, Chang-Dong Wang, Jian-Huang Lai
In view of this, this paper presents a Deep Clustering via Ensembles (DeepCluE) approach, which bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks.
1 code implementation • 1 Jun 2022 • Xiaozhi Deng, Dong Huang, Ding-Hua Chen, Chang-Dong Wang, Jian-Huang Lai
In this paper, we present an end-to-end deep clustering approach termed Strongly Augmented Contrastive Clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering.
1 code implementation • 22 Mar 2022 • Dong Huang, Chang-Dong Wang, Jian-Huang Lai
Then, a set of diversified base clusterings for different view groups are obtained via fast graph partitioning, which are further formulated into a unified bipartite graph for final clustering in the late-stage fusion.
no code implementations • 12 Mar 2022 • Zhi-Hong Deng, Chang-Dong Wang, Ling Huang, Jian-Huang Lai, Philip S. Yu
G$^3$SR decomposes the session-based recommendation workflow into two steps.
no code implementations • CVPR 2022 • Junhao Dong, YuAn Wang, Jian-Huang Lai, Xiaohua Xie
Extensive experiments show that our method can significantly outperform state-of-the-art adversarially robust FSIC methods on two standard benchmarks.
1 code implementation • CVPR 2022 • Quan Zhang, Kaiheng Dang, Jian-Huang Lai, Zhanxiang Feng, Xiaohua Xie
To the best of our knowledge, 3DT is the first work to address GReID with 3D perspective, and the City1M is the currently largest dataset.
1 code implementation • 10 Mar 2021 • Zi-Yuan Hu, Jin Huang, Zhi-Hong Deng, Chang-Dong Wang, Ling Huang, Jian-Huang Lai, Philip S. Yu
Representation learning tries to learn a common low dimensional space for the representations of users and items.
no code implementations • ICCV 2021 • Zihang Lin, Jiangxin Sun, Jian-Fang Hu, QiZhi Yu, Jian-Huang Lai, Wei-Shi Zheng
In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive.
2 code implementations • 13 Aug 2020 • Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai
However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.
Ranked #2 on
Action Quality Assessment
on Rhythmic Gymnastic
1 code implementation • CVPR 2020 • Haoxin Li, Wei-Shi Zheng, Yu Tao, Haifeng Hu, Jian-Huang Lai
We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling.
no code implementations • IJCNLP 2019 • Lijun Wu, Yiren Wang, Yingce Xia, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
In this work, we study how to use both the source-side and target-side monolingual data for NMT, and propose an effective strategy leveraging both of them.
Ranked #1 on
Machine Translation
on WMT2016 English-German
(SacreBLEU metric, using extra
training data)
no code implementations • IJCNLP 2019 • Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
1) We provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised training signals.
no code implementations • 6 Aug 2019 • Zixuan Chen, Huajun Zhou, Xiaohua Xie, Jian-Huang Lai
Yet the Contour Loss emphasizes on the local saliency.
no code implementations • 27 Jul 2019 • Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang
Most of the existing approaches focus on specific visual tasks while ignoring the relations between them.
no code implementations • 7 Jul 2019 • Jiaxuan Zhuo, Jian-Huang Lai, Peijia Chen
In this paper, we design a teacher-student learning framework to learn an occlusion-robust model from the full-body person domain to the occluded person domain.
1 code implementation • ACL 2019 • Lijun Wu, Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem.
Ranked #11 on
Machine Translation
on WMT2014 English-French
2 code implementations • 30 May 2019 • Pei-Zhen Li, Ling Huang, Chang-Dong Wang, Jian-Huang Lai
Based on the new edge set, the original connectivity structure of the input network is enhanced to generate a rewired network, whereby the motif-based higher-order structure is leveraged and the hypergraph fragmentation issue is well addressed.
Ranked #1 on
Community Detection
on Cora
Social and Information Networks Physics and Society 97R40
1 code implementation • 8 Apr 2019 • Guangrun Wang, Guangcong Wang, Xujie Zhang, Jian-Huang Lai, Zhengtao Yu, Liang Lin
Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem.
Ranked #2 on
Person Re-Identification
on SYSU-30k
1 code implementation • CVPR 2019 • Hong-Xing Yu, Wei-Shi Zheng, An-Cong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai
To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.
Ranked #84 on
Person Re-Identification
on DukeMTMC-reID
no code implementations • 4 Mar 2019 • Dong Huang, Chang-Dong Wang, Jian-Sheng Wu, Jian-Huang Lai, Chee-Keong Kwoh
Experiments on various large-scale datasets have demonstrated the scalability and robustness of our algorithms.
Ranked #3 on
Image/Document Clustering
on pendigits
1 code implementation • 29 Jan 2019 • Guangcong Wang, Jian-Huang Lai, Zhenyu Xie, Xiaohua Xie
With the discovered underlying person structure, the RLD method builds a bridge between the global and local feature representation and thus improves the capacity of feature representation for person re-ID.
2 code implementations • 15 Jan 2019 • Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, Philip S. Yu
To solve this problem, many methods have been studied, which can be generally categorized into two types, i. e., representation learning-based CF methods and matching function learning-based CF methods.
3 code implementations • 8 Dec 2018 • Guangcong Wang, Jian-Huang Lai, Peigen Huang, Xiaohua Xie
In this paper, we propose a novel two-stream spatial-temporal person ReID (st-ReID) framework that mines both visual semantic information and spatial-temporal information.
Ranked #1 on
Person Re-Identification
on Market-1501
(using extra training data)
no code implementations • 9 Nov 2018 • Wenqi Liang, Guangcong Wang, Jian-Huang Lai, Junyong Zhu
Cross-domain transfer learning (CDTL) is an extremely challenging task for the person re-identification (ReID).
no code implementations • 30 Oct 2018 • Dong Huang, Chang-Dong Wang, Hongxing Peng, Jian-Huang Lai, Chee-Keong Kwoh
Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.
no code implementations • NeurIPS 2018 • Lijun Wu, Fei Tian, Yingce Xia, Yang Fan, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher).
no code implementations • ECCV 2018 • Jian-Fang Hu, Wei-Shi Zheng, Jia-Hui Pan, Jian-Huang Lai, Jian-Guo Zhang
In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
no code implementations • EMNLP 2018 • Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
Many previous works have discussed the relationship between error propagation and the \emph{accuracy drop} (i. e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem.
1 code implementation • EMNLP 2018 • Lijun Wu, Fei Tian, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2018 • Jian-Fang Hu, Wei-Shi Zheng, Lianyang Ma, Gang Wang, Jian-Huang Lai, Jian-Guo Zhang
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #82 on
Skeleton Based Action Recognition
on NTU RGB+D 120
no code implementations • CVPR 2018 • Guotian Xie, Jingdong Wang, Ting Zhang, Jian-Huang Lai, Richang Hong, Guo-Jun Qi
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels.
2 code implementations • 17 Apr 2018 • Guotian Xie, Jingdong Wang, Ting Zhang, Jian-Huang Lai, Richang Hong, Guo-Jun Qi
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels.
no code implementations • 9 Apr 2018 • Jiaxuan Zhuo, Zeyu Chen, Jian-Huang Lai, Guangcong Wang
Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places.
1 code implementation • CVPR 2018 • Wen-Yan Lin, Siying Liu, Jian-Huang Lai, Yasuyuki Matsushita
Many high dimensional vector distances tend to a constant.
no code implementations • 30 Mar 2018 • Zhanxiang Feng, Jian-Huang Lai, Xiaohua Xie
In recent years, a growing body of research has focused on the problem of person re-identification (re-id).
no code implementations • 5 Dec 2017 • Zhou Yin, Wei-Shi Zheng, An-Cong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jian-Huang Lai
While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task.
1 code implementation • 9 Oct 2017 • Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Chee-Keong Kwoh
The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.
no code implementations • ICCV 2017 • Guangcong Wang, Xiaohua Xie, Jian-Huang Lai, Jiaxuan Zhuo
A bottleneck of SSL is the overfitting problem when training over the limited labeled data, especially on a complex model like a deep neural network.
no code implementations • ICCV 2017 • Ancong Wu, Wei-Shi Zheng, Hong-Xing Yu, Shaogang Gong, Jian-Huang Lai
To that end, matching RGB images with infrared images is required, which are heterogeneous with very different visual characteristics.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
no code implementations • 25 Jul 2017 • Chunchao Guo, Jian-Huang Lai, Xiaohua Xie
We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos.
no code implementations • 20 Apr 2017 • Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jian-Huang Lai, Tie-Yan Liu
The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human.
no code implementations • 28 Mar 2017 • Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai
More specifically, we exploit depth voxel covariance descriptor and further propose a locally rotation invariant depth shape descriptor called Eigen-depth feature to describe pedestrian body shape.
no code implementations • 26 Mar 2017 • Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai
The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 39 , Issue: 11 , Nov. 1 2017 ) 2016 • Jian-Fang Hu, Wei-Shi Zheng, Jian-Huang Lai, Jian-Guo Zhang
The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets.
Ranked #8 on
Skeleton Based Action Recognition
on SYSU 3D
no code implementations • 3 Aug 2016 • Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Yun Liang, Shan Bian, Yu Chen
Support vector clustering (SVC) is a versatile clustering technique that is able to identify clusters of arbitrary shapes by exploiting the kernel trick.
no code implementations • 3 Jun 2016 • Dong Huang, Jian-Huang Lai, Chang-Dong Wang
To address these two limitations, in this paper, we propose a novel ensemble clustering approach based on sparse graph representation and probability trajectory analysis.
no code implementations • 17 May 2016 • Dong Huang, Chang-Dong Wang, Jian-Huang Lai
Although some efforts have been made to (globally) evaluate and weight the base clusterings, yet these methods tend to view each base clustering as an individual and neglect the local diversity of clusters inside the same base clustering.
no code implementations • ICCV 2015 • Wei-Shi Zheng, Xiang Li, Tao Xiang, Shengcai Liao, Jian-Huang Lai, Shaogang Gong
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views.
no code implementations • 26 May 2015 • Shi-Zhe Chen, Chun-Chao Guo, Jian-Huang Lai
This paper proposes a novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems.
no code implementations • 3 Feb 2015 • Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai
This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree.
no code implementations • 3 Feb 2015 • Xionghao Liu, Wei Yang, Liang Lin, Qing Wang, Zhaoquan Cai, Jian-Huang Lai
In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).
no code implementations • 2 Feb 2015 • Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai
In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images.
no code implementations • 2 Feb 2015 • Liang Lin, Yuanlu Xu, Xiaodan Liang, Jian-Huang Lai
Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e. g., dynamic backgrounds, illumination variations, and indistinct foreground objects.
no code implementations • 6 May 2014 • Dong Huang, Jian-Huang Lai, Chang-Dong Wang
We present the normalized crowd agreement index (NCAI) to evaluate the quality of base clusterings in an unsupervised manner and thus weight the base clusterings in accordance with their clustering validity.