1 code implementation • 11 Sep 2023 • Yide Qiu, Shaoxiang Ling, Tong Zhang, Bo Huang, Zhen Cui
To perform effective learning on the large-scale UniKG, two key measures are taken, including (i) the semantic alignment strategy for multi-attribute entities, which projects the feature description of multi-attribute nodes into a common embedding space to facilitate node aggregation in a large receptive field; (ii) proposing a novel plug-and-play anisotropy propagation module (APM) to learn effective multi-hop anisotropy propagation kernels, which extends methods of large-scale homogeneous graphs to heterogeneous graphs.
no code implementations • 17 Aug 2023 • Yuanzhi Wang, Yong Li, Xiaoya Zhang, Xin Liu, Anbo Dai, Antoni B. Chan, Zhen Cui
In addition to the utilization of a pretrained T2I 2D Unet for spatial content manipulation, we establish a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences.
no code implementations • 16 Aug 2023 • Binhui Liu, Xin Liu, Anbo Dai, Zhiyong Zeng, Dan Wang, Zhen Cui, Jian Yang
In particular, the designed two diffusion streams, video content and motion branches, could not only run separately in their private spaces for producing personalized video variations as well as content, but also be well-aligned between the content and motion domains through leveraging our designed cross-transformer interaction module, which would benefit the smoothness of generated videos.
no code implementations • 18 Jun 2023 • Guangbu Liu, Tong Zhang, Xudong Wang, Wenting Zhao, Chuanwei Zhou, Zhen Cui
Instead of a plain use of a base graph dictionary, we propose the variational graph dictionary adaptation (VGDA) to generate a personalized dictionary (named adapted graph dictionary) for catering to each input graph.
1 code implementation • CVPR 2023 • Yong Li, Yuanzhi Wang, Zhen Cui
Specially, the representation of each modality is decoupled into two parts, i. e., modality-irrelevant/-exclusive spaces, in a self-regression manner.
1 code implementation • CVPR 2023 • Hui Lv, Zhongqi Yue, Qianru Sun, Bin Luo, Zhen Cui, Hanwang Zhang
At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones.
1 code implementation • ICCV 2023 • Yuanzhi Wang, Zhen Cui, Yong Li
Recovering missed modality is popular in incomplete multimodal learning because it usually benefits downstream tasks.
no code implementations • ICCV 2023 • Ziqi Gu, Chunyan Xu, Jian Yang, Zhen Cui
Further, considering that the learned knowledge in the human brain is a generalization of actual information and exists in a certain relational structure, we perform continual structure infomax learning to relieve the catastrophic forgetting problem in the continual learning process.
no code implementations • 27 Sep 2022 • Hui Lv, Zhen Cui, Biao Wang, Jian Yang
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly.
no code implementations • 14 Apr 2022 • Yu Wu, Jianle Wei, Weiqin Ying, Yanqi Lan, Zhen Cui, Zhenyu Wang
On the other hand, the parallel reference lines of the parallel decomposition methods including the normal boundary intersection (NBI) might result in poor diversity because of under-sampling near the boundaries for MaOPs with concave frontiers.
1 code implementation • CVPR 2022 • Ziqiang Xu, Chunyan Xu, Zhen Cui, Xiangwei Zheng, Jian Yang
The classic active contour model raises a great promising solution to polygon-based object extraction with the progress of deep learning recently.
no code implementations • 11 Aug 2021 • Yong Li, Yufei Sun, Zhen Cui, Shiguang Shan, Jian Yang
To mitigate racial bias and meantime preserve robust FR, we abstract face identity-related representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition.
1 code implementation • 14 Jul 2021 • Yong Li, Lingjie Lao, Zhen Cui, Shiguang Shan, Jian Yang
To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner.
1 code implementation • CVPR 2021 • Xingkun Xu, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jilin Li, Feiyue Huang, Yong Li, Zhen Cui
Then, an additional penalty term, which is in proportion to the ratio of instance FPR overall FPR, is introduced into the denominator of the softmax-based loss.
1 code implementation • CVPR 2021 • Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, Jian Yang
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection.
no code implementations • 14 Apr 2021 • Hui Lv, Chunyan Xu, Zhen Cui
Video anomaly detection (VAD) is currently a challenging task due to the complexity of anomaly as well as the lack of labor-intensive temporal annotations.
no code implementations • 10 Mar 2021 • Xuran Xu, Tong Zhang, Chunyan Xu, Zhen Cui, Jian Yang
We further extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data.
Ranked #1 on Traffic Prediction on SZ-Taxi
no code implementations • ICCV 2021 • Yun Wang, Tong Zhang, Xueya Zhang, Zhen Cui, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang
Then, a Wasserstein coupled dictionary, containing multiple pairs of counterpart graph keys with each key corresponding to one modality, is constructed for further feature learning.
no code implementations • 1 Jan 2021 • Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang, Jian Yang, Wei Liu
In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.
no code implementations • ICCV 2021 • Jingshan Xu, Chuanwei Zhou, Zhen Cui, Chunyan Xu, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang
In this paper, we propose a progressive segmentation inference (PSI) framework to tackle with scribble-supervised semantic segmentation.
no code implementations • 24 Sep 2020 • Qianliang Wu, Tong Zhang, Zhen Cui, Jian Yang
In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics.
no code implementations • 3 Sep 2020 • Yuan Fang, Chunyan Xu, Zhen Cui, Yuan Zong, Jian Yang
In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds.
1 code implementation • 20 Aug 2020 • Hui Lv, Chuanwei Zhou, Chunyan Xu, Zhen Cui, Jian Yang
In addition, in order to fully utilize the spatial context information, the immediate semantics are directly derived from the segment representations.
Anomaly Detection In Surveillance Videos Video Anomaly Detection
no code implementations • 19 Aug 2020 • Yun Wang, Tong Zhang, Zhen Cui, Chunyan Xu, Jian Yang
For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model.
no code implementations • ECCV 2020 • Xueya Zhang, Tong Zhang, Xiaobin Hong, Zhen Cui, Jian Yang
Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning.
no code implementations • ICLR 2020 • Chunyan Xu, Zhen Cui, Xiaobin Hong, Tong Zhang, Jian Yang, Wei Liu
In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures.
no code implementations • 28 Nov 2019 • Xueya Zhang, Tong Zhang, Wenting Zhao, Zhen Cui, Jian Yang
Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification.
2 code implementations • 16 Sep 2019 • Sen Yang, Wankou Yang, Zhen Cui
Neural Architecture Search (NAS) technologies have emerged in many domains to jointly learn the architectures and weights of the neural network.
Ranked #13 on Keypoint Detection on MS COCO
no code implementations • CVPR 2019 • Zhen-Yu Zhang, Zhen Cui, Chunyan Xu, Yan Yan, Nicu Sebe, Jian Yang
In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation.
Ranked #49 on Semantic Segmentation on NYU Depth v2
no code implementations • 19 Dec 2018 • Yuan Zong, Tong Zhang, Wenming Zheng, Xiaopeng Hong, Chuangao Tang, Zhen Cui, Guoying Zhao
Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis.
no code implementations • 30 Nov 2018 • Keyu Yan, Wenming Zheng, Tong Zhang, Yuan Zong, Zhen Cui
Cross-database non-frontal expression recognition is a very meaningful but rather difficult subject in the fields of computer vision and affect computing.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 11 Nov 2018 • Jiatao Jiang, Zhen Cui, Chunyan Xu, Jian Yang
In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs.
Ranked #3 on Graph Classification on PTC
no code implementations • 11 Sep 2018 • Zhen Cui, Chunyan Xu, Wenming Zheng, Jian Yang
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images.
no code implementations • ECCV 2018 • Zhen-Yu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang
In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks.
Ranked #74 on Semantic Segmentation on NYU Depth v2
no code implementations • 7 Jul 2018 • Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhen-Yu Zhang, Jian Yang
In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem.
Ranked #3 on Graph Classification on IMDb-B
no code implementations • 16 Apr 2018 • Jiatao Jiang, Chunyan Xu, Zhen Cui, Tong Zhang, Wenming Zheng, Jian Yang
As an analogy to a standard convolution kernel on image, Gaussian models implicitly coordinate those unordered vertices/nodes and edges in a local receptive field after projecting to the gradient space of Gaussian parameters.
no code implementations • 27 Mar 2018 • Tong Zhang, Wenming Zheng, Zhen Cui, Yang Li
For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across two subgraphs.
no code implementations • IEEE Transactions on Affective Computing 2018 • Zhenyang Zhang, Wenming Zheng, Peng Song, Zhen Cui
In this paper, a multichannel EEG emotion recognition method based on a novel dynamical graph convolutional neural networks (DGCNN) is proposed.
Ranked #2 on Electroencephalogram (EEG) on SEED-IV
no code implementations • 27 Feb 2018 • Chaolong Li, Zhen Cui, Wenming Zheng, Chunyan Xu, Jian Yang
To encode dynamic graphs, the constructed multi-scale local graph convolution filters, consisting of matrices of local receptive fields and signal mappings, are recursively performed on structured graph data of temporal and spatial domain.
Ranked #1 on Skeleton Based Action Recognition on Florence 3D
no code implementations • 17 Nov 2017 • Chaolong Li, Zhen Cui, Wenming Zheng, Chunyan Xu, Rongrong Ji, Jian Yang
The motion analysis of human skeletons is crucial for human action recognition, which is one of the most active topics in computer vision.
no code implementations • 26 Jul 2017 • Yuan Zong, Xiaohua Huang, Wenming Zheng, Zhen Cui, Guoying Zhao
In this paper, we investigate the cross-database micro-expression recognition problem, where the training and testing samples are from two different micro-expression databases.
no code implementations • 18 Jul 2017 • Zhen Cui, You yi Cai, Wen ming Zheng, Jian Yang
Visual object tracking is a challenging computer vision task with numerous real-world applications.
no code implementations • 30 May 2017 • Tong Zhang, Wenming Zheng, Zhen Cui, Chaolong Li
Symmetric positive definite (SPD) matrices (e. g., covariances, graph Laplacians, etc.)
no code implementations • 12 May 2017 • Tong Zhang, Wenming Zheng, Zhen Cui, Yuan Zong, Yang Li
Then a bi-directional temporal RNN layer is further used to learn discriminative temporal dependencies from the sequences concatenating spatial features of each time slice produced from the spatial RNN layer.
no code implementations • 24 Jul 2016 • Yang Li, Wenming Zheng, Zhen Cui
To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network(RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and video-based face recognition.
no code implementations • CVPR 2016 • Wei Wang, Zhen Cui, Yan Yan, Jiashi Feng, Shuicheng Yan, Xiangbo Shu, Nicu Sebe
Modeling the aging process of human face is important for cross-age face verification and recognition.
no code implementations • CVPR 2016 • Zhen Cui, Shengtao Xiao, Jiashi Feng, Shuicheng Yan
The produced confidence maps from the RNNs are employed to adaptively regularize the learning of discriminative correlation filters by suppressing clutter background noises while making full use of the information from reliable parts.
no code implementations • 30 Oct 2015 • Hanjiang Lai, Shengtao Xiao, Yan Pan, Zhen Cui, Jiashi Feng, Chunyan Xu, Jian Yin, Shuicheng Yan
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures.
no code implementations • NeurIPS 2014 • Zhen Cui, Hong Chang, Shiguang Shan, Xilin Chen
In this paper, we propose a generalized Unsupervised Manifold Alignment (GUMA) method to build the connections between different but correlated datasets without any known correspondences.
no code implementations • 10 Feb 2014 • Wen Wang, Zhen Cui, Hong Chang, Shiguang Shan, Xilin Chen
In this paper, we propose a simple but effective coupled neural network, called Deeply Coupled Autoencoder Networks (DCAN), which seeks to build two deep neural networks, coupled with each other in every corresponding layers.
no code implementations • CVPR 2013 • Zhen Cui, Wen Li, Dong Xu, Shiguang Shan, Xilin Chen
Spatial-Temporal Face Region Descriptor, STFRD) for images (resp.