1 code implementation • ECCV 2020 • Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li
However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
no code implementations • 29 May 2024 • Zhangyang Gao, Jue Wang, Cheng Tan, Lirong Wu, Yufei Huang, Siyuan Li, Zhirui Ye, Stan Z. Li
We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization.
1 code implementation • 16 May 2024 • Lirong Wu, Yijun Tian, Haitao Lin, Yufei Huang, Siyuan Li, Nitesh V Chawla, Stan Z. Li
Protein-protein bindings play a key role in a variety of fundamental biological processes, and thus predicting the effects of amino acid mutations on protein-protein binding is crucial.
no code implementations • 13 May 2024 • Siyuan Li, Zedong Wang, Zicheng Liu, Di wu, Cheng Tan, Jiangbin Zheng, Yufei Huang, Stan Z. Li
In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning.
no code implementations • 17 Apr 2024 • Zicheng Liu, Li Wang, Siyuan Li, Zedong Wang, Haitao Lin, Stan Z. Li
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences.
no code implementations • 9 Mar 2024 • Jun Xia, Shaorong Chen, Jingbo Zhou, Tianze Ling, Wenjie Du, Sizhe Liu, Stan Z. Li
Moreover, AdaNovo excels in identifying amino acids with PTMs and exhibits robustness against data noise.
no code implementations • 8 Mar 2024 • Bozhen Hu, Cheng Tan, Lirong Wu, Jiangbin Zheng, Jun Xia, Zhangyang Gao, Zicheng Liu, Fandi Wu, Guijun Zhang, Stan Z. Li
Protein representation learning plays a crucial role in understanding the structure and function of proteins, which are essential biomolecules involved in various biological processes.
1 code implementation • 6 Mar 2024 • Lirong Wu, Haitao Lin, Zhangyang Gao, Guojiang Zhao, Stan Z. Li
As a result, TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference.
no code implementations • 5 Mar 2024 • Haitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, Stan Z. Li
Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades.
1 code implementation • 3 Mar 2024 • Tianyu Fan, Lirong Wu, Yufei Huang, Haitao Lin, Cheng Tan, Zhangyang Gao, Stan Z. Li
In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance.
no code implementations • 1 Mar 2024 • Rui Sun, Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li
Augmentation is an effective alternative to utilize the small amount of labeled protein data.
no code implementations • 24 Feb 2024 • Chenrui Duan, Zelin Zang, Yongjie Xu, Hang He, Zihan Liu, Zijia Song, Ju-Sheng Zheng, Stan Z. Li
Metagenomic data, comprising mixed multi-species genomes, are prevalent in diverse environments like oceans and soils, significantly impacting human health and ecological functions.
1 code implementation • 22 Feb 2024 • Lirong Wu, Yijun Tian, Yufei Huang, Siyuan Li, Haitao Lin, Nitesh V Chawla, Stan Z. Li
In addition, microenvironments defined in previous work are largely based on experimentally assayed physicochemical properties, for which the "vocabulary" is usually extremely small.
2 code implementations • 14 Feb 2024 • Siyuan Li, Zicheng Liu, Juanxi Tian, Ge Wang, Zedong Wang, Weiyang Jin, Di wu, Cheng Tan, Tao Lin, Yang Liu, Baigui Sun, Stan Z. Li
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.
1 code implementation • 13 Feb 2024 • Lirong Wu, Yufei Huang, Cheng Tan, Zhangyang Gao, Bozhen Hu, Haitao Lin, Zicheng Liu, Stan Z. Li
Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery.
no code implementations • 4 Feb 2024 • Zhangyang Gao, Cheng Tan, Jue Wang, Yufei Huang, Lirong Wu, Stan Z. Li
Is there a foreign language describing protein sequences and structures simultaneously?
1 code implementation • 4 Feb 2024 • Zhangyang Gao, Daize Dong, Cheng Tan, Jun Xia, Bozhen Hu, Stan Z. Li
(4) The edge-centric pretraining framework GraphsGPT demonstrates its efficacy in graph domain tasks, excelling in both representation and generation.
no code implementations • 3 Feb 2024 • Zhe Li, Laurence T. Yang, Bocheng Ren, Xin Nie, Zhangyang Gao, Cheng Tan, Stan Z. Li
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning.
no code implementations • 3 Feb 2024 • Zhe Li, Zhangyang Gao, Cheng Tan, Stan Z. Li, Laurence T. Yang
Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.
1 code implementation • 15 Jan 2024 • Zelin Zang, Liangyu Li, Yongjie Xu, Chenrui Duan, Kai Wang, Yang You, Yi Sun, Stan Z. Li
MuST integrates the multi-modality information contained in the ST data effectively into a uniform latent space to provide a foundation for all the downstream tasks.
no code implementations • 12 Jan 2024 • Bozhen Hu, Zelin Zang, Jun Xia, Lirong Wu, Cheng Tan, Stan Z. Li
Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding.
no code implementations • 12 Jan 2024 • Bozhen Hu, Zelin Zang, Cheng Tan, Stan Z. Li
Protein representation learning is critical in various tasks in biology, such as drug design and protein structure or function prediction, which has primarily benefited from protein language models and graph neural networks.
no code implementations • 5 Jan 2024 • Ge Wang, Zelin Zang, Jiangbin Zheng, Jun Xia, Stan Z. Li
The mainstream method is utilizing contrastive learning to facilitate graph feature extraction, known as Graph Contrastive Learning (GCL).
1 code implementation • 31 Dec 2023 • Siyuan Li, Luyuan Zhang, Zedong Wang, Di wu, Lirong Wu, Zicheng Liu, Jun Xia, Cheng Tan, Yang Liu, Baigui Sun, Stan Z. Li
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
1 code implementation • 11 Dec 2023 • Jiangbin Zheng, Siyuan Li, Yufei Huang, Zhangyang Gao, Cheng Tan, Bozhen Hu, Jun Xia, Ge Wang, Stan Z. Li
Protein design involves generating protein sequences based on their corresponding protein backbones.
no code implementations • 7 Dec 2023 • Yijie Zhang, Zhangyang Gao, Cheng Tan, Stan Z. Li
Predicting protein stability changes induced by single-point mutations has been a persistent challenge over the years, attracting immense interest from numerous researchers.
1 code implementation • 23 Nov 2023 • Cheng Tan, Jingxuan Wei, Zhangyang Gao, Linzhuang Sun, Siyuan Li, Xihong Yang, Stan Z. Li
Remarkably, we show that even smaller base models, when equipped with our proposed approach, can achieve results comparable to those of larger models, illustrating the potential of our approach in harnessing the power of rationales for improved multimodal reasoning.
Ranked #1 on Science Question Answering on ScienceQA
no code implementations • 17 Nov 2023 • Bozhen Hu, Bin Gao, Cheng Tan, Tongle Wu, Stan Z. Li
Defect detection plays a crucial role in infrared non-destructive testing systems, offering non-contact, safe, and efficient inspection capabilities.
no code implementations • 25 Oct 2023 • Zhe Li, Zhangyang Gao, Cheng Tan, Stan Z. Li, Laurence T. Yang
This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks.
no code implementations • 9 Oct 2023 • Cheng Tan, Jue Wang, Zhangyang Gao, Siyuan Li, Lirong Wu, Jun Xia, Stan Z. Li
In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective.
1 code implementation • 4 Oct 2023 • Zihan Liu, Ge Wang, Jiaqi Wang, Jiangbin Zheng, Stan Z. Li
Peptides are formed by the dehydration condensation of multiple amino acids.
1 code implementation • 4 Oct 2023 • Siyuan Li, Weiyang Jin, Zedong Wang, Fang Wu, Zicheng Liu, Cheng Tan, Stan Z. Li
The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.
2 code implementations • 17 Aug 2023 • Xihong Yang, Cheng Tan, Yue Liu, Ke Liang, Siwei Wang, Sihang Zhou, Jun Xia, Stan Z. Li, Xinwang Liu, En Zhu
To address these problems, we propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (CONVERT).
2 code implementations • 13 Aug 2023 • Yue Liu, Ke Liang, Jun Xia, Xihong Yang, Sihang Zhou, Meng Liu, Xinwang Liu, Stan Z. Li
To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC).
1 code implementation • 24 Jul 2023 • Jingxuan Wei, Cheng Tan, Zhangyang Gao, Linzhuang Sun, Siyuan Li, Bihui Yu, Ruifeng Guo, Stan Z. Li
Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks.
1 code implementation • 17 Jul 2023 • Zihan Liu, Jiaqi Wang, Yun Luo, Shuang Zhao, Wenbin Li, Stan Z. Li
In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides.
no code implementations • 30 Jun 2023 • Jun Xia, Lecheng Zhang, Xiao Zhu, Stan Z. Li
Molecular property prediction (MPP) is a crucial task in the drug discovery pipeline, which has recently gained considerable attention thanks to advances in deep neural networks.
2 code implementations • NeurIPS 2023 • Cheng Tan, Siyuan Li, Zhangyang Gao, Wenfei Guan, Zedong Wang, Zicheng Liu, Lirong Wu, Stan Z. Li
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner.
1 code implementation • 9 Jun 2023 • Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li
To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP.
no code implementations • NeurIPS 2023 • Haitao Lin, Yufei Huang, Odin Zhang, Lirong Wu, Siyuan Li, ZhiYuan Chen, Stan Z. Li
In this way, however, it is hard to generate realistic fragments with complicated structures.
3 code implementations • 28 May 2023 • Yue Liu, Ke Liang, Jun Xia, Sihang Zhou, Xihong Yang, Xinwang Liu, Stan Z. Li
Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner.
1 code implementation • 20 May 2023 • Zhangyang Gao, Xingran Chen, Cheng Tan, Stan Z. Li
Is there a unified framework for graph-based retrosynthesis prediction?
1 code implementation • 20 May 2023 • Zhangyang Gao, Cheng Tan, Stan Z. Li
After witnessing the great success of pretrained models on diverse protein-related tasks and the fact that recovery is highly correlated with confidence, we wonder whether this knowledge can push the limits of protein design further.
Ranked #1 on Word Sense Disambiguation on TS50
1 code implementation • 18 May 2023 • Lirong Wu, Haitao Lin, Yufei Huang, Tianyu Fan, Stan Z. Li
Furthermore, we identified a potential information drowning problem for existing GNN-to-MLP distillation, i. e., the high-frequency knowledge of the pre-trained GNNs may be overwhelmed by the low-frequency knowledge during distillation; we have described in detail what it represents, how it arises, what impact it has, and how to deal with it.
no code implementations • 5 May 2023 • Ajian Liu, Zichang Tan, Zitong Yu, Chenxu Zhao, Jun Wan, Yanyan Liang, Zhen Lei, Du Zhang, Stan Z. Li, Guodong Guo
The availability of handy multi-modal (i. e., RGB-D) sensors has brought about a surge of face anti-spoofing research.
no code implementations • 27 Apr 2023 • Tianyi Huang, Shenghui Cheng, Stan Z. Li, Zhengjun Zhang
Then, the anchors of different clusters are sorted on the optimal Hamiltonian cycle generated by the cluster similarities and mapped on the circumference of a circle.
1 code implementation • 21 Apr 2023 • Cheng Tan, Zhangyang Gao, Lirong Wu, Jun Xia, Jiangbin Zheng, Xihong Yang, Yue Liu, Bozhen Hu, Stan Z. Li
In this paper, we propose a \textit{simple yet effective} model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
1 code implementation • 8 Apr 2023 • Fang Wu, Huiling Qin, Siyuan Li, Stan Z. Li, Xianyuan Zhan, Jinbo Xu
In the field of artificial intelligence for science, it is consistently an essential challenge to face a limited amount of labeled data for real-world problems.
1 code implementation • 29 Mar 2023 • Zihan Liu, Yun Luo, Lirong Wu, Zicheng Liu, Stan Z. Li
It has become cognitive inertia to employ cross-entropy loss function in classification related tasks.
no code implementations • 19 Mar 2023 • Jiangbin Zheng, Ge Wang, Yufei Huang, Bozhen Hu, Siyuan Li, Cheng Tan, Xinwen Fan, Stan Z. Li
In this work, we introduce a novel unsupervised protein structure representation pretraining with a robust protein language model.
1 code implementation • CVPR 2023 • Jiangbin Zheng, Yile Wang, Cheng Tan, Siyuan Li, Ge Wang, Jun Xia, Yidong Chen, Stan Z. Li
In this work, we propose a novel contrastive visual-textual transformation for SLR, CVT-SLR, to fully explore the pretrained knowledge of both the visual and language modalities.
no code implementations • 14 Feb 2023 • Zhangyang Gao, Yuqi Hu, Cheng Tan, Stan Z. Li
Is there a unified model for generating molecules considering different conditions, such as binding pockets and chemical properties?
1 code implementation • 8 Feb 2023 • Yun Luo, Zihan Liu, Stan Z. Li, Yue Zhang
(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text.
no code implementations • 5 Feb 2023 • Yifeng Zhao, Xiangbo Gao, Pei Zhang, Liang Lei, S. A. Galindo-Torres, Stan Z. Li
This algorithm can capture the main contour of parental particles with a series of non-overlapping spheres and refine surface-texture details through gradient search.
no code implementations • 5 Feb 2023 • Yufei Huang, Lirong Wu, Haitao Lin, Jiangbin Zheng, Ge Wang, Stan Z. Li
Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design.
1 code implementation • 25 Jan 2023 • Cheng Tan, Yijie Zhang, Zhangyang Gao, Bozhen Hu, Siyuan Li, Zicheng Liu, Stan Z. Li
We crafted a large, well-curated benchmark dataset and designed a comprehensive structural modeling approach to represent the complex RNA tertiary structure.
1 code implementation • 22 Jan 2023 • Zhangyang Gao, Cheng Tan, Stan Z. Li
Have you ever been troubled by the complexity and computational cost of SE(3) protein structure modeling and been amazed by the simplicity and power of language modeling?
1 code implementation • 7 Jan 2023 • Fang Wu, Siyuan Li, Xurui Jin, Yinghui Jiang, Dragomir Radev, Zhangming Niu, Stan Z. Li
It takes advantage of MatchExplainer to fix the most informative portion of the graph and merely operates graph augmentations on the rest less informative part.
no code implementations • 3 Jan 2023 • Hao Fang, Ajian Liu, Jun Wan, Sergio Escalera, Chenxu Zhao, Xu Zhang, Stan Z. Li, Zhen Lei
In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks.
1 code implementation • ICCV 2023 • Zelin Zang, Lei Shang, Senqiao Yang, Fei Wang, Baigui Sun, Xuansong Xie, Stan Z. Li
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Ranked #3 on Universal Domain Adaptation on Office-31
1 code implementation • 31 Dec 2022 • Lirong Wu, Yufei Huang, Haitao Lin, Stan Z. Li
To pave the way for AI researchers with little bioinformatics background, we present a timely and comprehensive review of PRL formulations and existing PRL methods from the perspective of model architectures, pretext tasks, and downstream applications.
no code implementations • 9 Dec 2022 • Haitao Lin, Lirong Wu, Yongjie Xu, Yufei Huang, Siyuan Li, Guojiang Zhao, Stan Z. Li
Solving partial differential equations is difficult.
no code implementations • 8 Dec 2022 • Zicheng Liu, Da Li, Javier Fernandez-Marques, Stefanos Laskaridis, Yan Gao, Łukasz Dudziak, Stan Z. Li, Shell Xu Hu, Timothy Hospedales
Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for diverse device capabilities.
1 code implementation • 7 Dec 2022 • Fang Wu, Lirong Wu, Dragomir Radev, Jinbo Xu, Stan Z. Li
Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area.
1 code implementation • 2 Dec 2022 • Cheng Tan, Zhangyang Gao, Hanqun Cao, Xingran Chen, Ge Wang, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. Li
In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space.
1 code implementation • 30 Nov 2022 • Bozhen Hu, Jun Xia, Jiangbin Zheng, Cheng Tan, Yufei Huang, Yongjie Xu, Stan Z. Li
The prediction of protein structures from sequences is an important task for function prediction, drug design, and related biological processes understanding.
2 code implementations • 23 Nov 2022 • Yue Liu, Jun Xia, Sihang Zhou, Xihong Yang, Ke Liang, Chenchen Fan, Yan Zhuang, Stan Z. Li, Xinwang Liu, Kunlun He
However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field.
2 code implementations • 22 Nov 2022 • Cheng Tan, Zhangyang Gao, Siyuan Li, Stan Z. Li
Without introducing any extra tricks and strategies, SimVP can achieve superior performance on various benchmark datasets.
Ranked #1 on Video Prediction on Moving MNIST
no code implementations • 21 Nov 2022 • Haitao Lin, Yufei Huang, Meng Liu, Xuanjing Li, Shuiwang Ji, Stan Z. Li
Previous works usually generate atoms in an auto-regressive way, where element types and 3D coordinates of atoms are generated one by one.
no code implementations • 21 Nov 2022 • Zelin Zang, Lei Shang, Senqiao Yang, Fei Wang, Baigui Sun, Xuansong Xie, Stan Z. Li
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
1 code implementation • 21 Nov 2022 • Zelin Zang, Shenghui Cheng, Linyan Lu, Hanchen Xia, Liangyu Li, Yaoting Sun, Yongjie Xu, Lei Shang, Baigui Sun, Stan Z. Li
The proposed techniques are integrated with a visual interface to help the user to adjust EVNet to achieve better DR performance and explainability.
6 code implementations • 7 Nov 2022 • Siyuan Li, Zedong Wang, Zicheng Liu, Cheng Tan, Haitao Lin, Di wu, ZhiYuan Chen, Jiangbin Zheng, Stan Z. Li
Notably, MogaNet hits 80. 0\% and 87. 8\% accuracy with 5. 2M and 181M parameters on ImageNet-1K, outperforming ParC-Net and ConvNeXt-L, while saving 59\% FLOPs and 17M parameters, respectively.
Ranked #1 on Pose Estimation on COCO val2017
no code implementations • 1 Nov 2022 • Jiangbin Zheng, Siyuan Li, Cheng Tan, Chong Wu, Yidong Chen, Stan Z. Li
Therefore, we propose to introduce additional word-level semantic knowledge of sign language linguistics to assist in improving current end-to-end neural SLT models.
1 code implementation • ACL 2022 • Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang, Stan Z. Li
Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e. g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability.
2 code implementations • 29 Oct 2022 • Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z. Li
Deep learning has achieved remarkable success in learning representations for molecules, which is crucial for various biochemical applications, ranging from property prediction to drug design.
no code implementations • 5 Oct 2022 • Lirong Wu, Jun Xia, Haitao Lin, Zhangyang Gao, Zicheng Liu, Guojiang Zhao, Stan Z. Li
Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications.
no code implementations • 5 Oct 2022 • Lirong Wu, Yufei Huang, Haitao Lin, Zicheng Liu, Tianyu Fan, Stan Z. Li
Self-supervised learning on graphs has recently achieved remarkable success in graph representation learning.
1 code implementation • 22 Sep 2022 • Zhangyang Gao, Cheng Tan, Pablo Chacón, Stan Z. Li
How can we design protein sequences folding into the desired structures effectively and efficiently?
1 code implementation • 11 Sep 2022 • Siyuan Li, Zedong Wang, Zicheng Liu, Di wu, Cheng Tan, Weiyang Jin, Stan Z. Li
Data mixing, or mixup, is a data-dependent augmentation technique that has greatly enhanced the generalizability of modern deep neural networks.
1 code implementation • 6 Sep 2022 • Hanqun Cao, Cheng Tan, Zhangyang Gao, Yilun Xu, Guangyong Chen, Pheng-Ann Heng, Stan Z. Li
Deep generative models are a prominent approach for data generation, and have been used to produce high quality samples in various domains.
no code implementations • 26 Aug 2022 • Zihan Liu, Ge Wang, Yun Luo, Stan Z. Li
To address this issue, we propose a novel surrogate model with multi-level propagation that preserves the node dissimilarity information.
1 code implementation • 7 Aug 2022 • Zihan Liu, Yun Luo, Lirong Wu, Siyuan Li, Zicheng Liu, Stan Z. Li
These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure.
1 code implementation • 3 Aug 2022 • Haitao Lin, Lirong Wu, Guojiang Zhao, Pai Liu, Stan Z. Li
While lots of previous works have focused on `goodness-of-fit' of TPP models by maximizing the likelihood, their predictive performance is unsatisfactory, which means the timestamps generated by models are far apart from true observations.
no code implementations • 8 Jul 2022 • Zelin Zang, Yongjie Xu, Linyan Lu, Yulan Geng, Senqiao Yang, Stan Z. Li
We propose that the ideal DR approach combines both FS and FP into a unified end-to-end manifold learning framework, simultaneously performing fundamental feature discovery while maintaining the intrinsic relationships between data samples in the latent space.
2 code implementations • 7 Jul 2022 • Zelin Zang, Siyuan Li, Di wu, Ge Wang, Lei Shang, Baigui Sun, Hao Li, Stan Z. Li
To overcome the underconstrained embedding problem, we design a loss and theoretically demonstrate that it leads to a more suitable embedding based on the local flatness.
Ranked #2 on Image Classification on ImageNet-100
2 code implementations • CVPR 2023 • Cheng Tan, Zhangyang Gao, Lirong Wu, Yongjie Xu, Jun Xia, Siyuan Li, Stan Z. Li
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames.
Ranked #12 on Video Prediction on Moving MNIST
no code implementations • 23 Jun 2022 • Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li
Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space?
3 code implementations • CVPR 2022 • Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies.
Ranked #2 on Video Prediction on Human3.6M
1 code implementation • CVPR 2022 • Cheng Tan, Zhangyang Gao, Lirong Wu, Siyuan Li, Stan Z. Li
Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier.
1 code implementation • 15 May 2022 • Fang Wu, Siyuan Li, Lirong Wu, Dragomir Radev, Stan Z. Li
Graph neural networks (GNNs) mainly rely on the message-passing paradigm to propagate node features and build interactions, and different graph learning tasks require different ranges of node interactions.
1 code implementation • 24 Apr 2022 • Xiangyu Zhu, Tingting Liao, Jiangjing Lyu, Xiang Yan, Yunfeng Wang, Kan Guo, Qiong Cao, Stan Z. Li, Zhen Lei
In this paper, we consider a novel problem of reconstructing a 3D human avatar from multiple unconstrained frames, independent of assumptions on camera calibration, capture space, and constrained actions.
1 code implementation • 21 Apr 2022 • Cheng Tan, Zhangyang Gao, Jun Xia, Bozhen Hu, Stan Z. Li
Thus, we propose the Global-Context Aware generative de novo protein design method (GCA), consisting of local and global modules.
no code implementations • 19 Apr 2022 • Fang Wu, Stan Z. Li
To waive this requirement, we propose a novel model called DiffMD by directly estimating the gradient of the log density of molecular conformations.
no code implementations • 18 Apr 2022 • Haitao Lin, Guojiang Zhao, Lirong Wu, Stan Z. Li
Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks.
no code implementations • 9 Apr 2022 • Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, Stan Z. Li
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.
1 code implementation • NeurIPS 2023 • Zicheng Liu, Siyuan Li, Ge Wang, Cheng Tan, Lirong Wu, Stan Z. Li
However, we found that the extra optimizing step may be redundant because label-mismatched mixed samples are informative hard mixed samples for deep models to localize discriminative features.
3 code implementations • 16 Feb 2022 • Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z. Li
Pretrained Language Models (PLMs) such as BERT have revolutionized the landscape of Natural Language Processing (NLP).
1 code implementation • 13 Feb 2022 • Fang Wu, Nicolas Courty, Shuting Jin, Stan Z. Li
Training data are usually limited or heterogeneous in many chemical and biological applications.
no code implementations • 12 Feb 2022 • Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li
Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods.
no code implementations • 10 Feb 2022 • Cheng Tan, Zhangyang Gao, Stan Z. Li
Building on the recent advantages of flow-based molecular generation models, we propose SiamFlow, which forces the flow to fit the distribution of target sequence embeddings in latent space.
1 code implementation • 7 Feb 2022 • Jun Xia, Lirong Wu, Jintao Chen, Bozhen Hu, Stan Z. Li
Furthermore, we devise adversarial training scheme, dubbed \textbf{AT-SimGRACE}, to enhance the robustness of graph contrastive learning and theoretically explain the reasons.
1 code implementation • 1 Feb 2022 • Zhangyang Gao, Cheng Tan, Stan Z. Li
While DeepMind has tentatively solved protein folding, its inverse problem -- protein design which predicts protein sequences from their 3D structures -- still faces significant challenges.
1 code implementation • 30 Nov 2021 • Siyuan Li, Zicheng Liu, Zedong Wang, Di wu, Zihan Liu, Stan Z. Li
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on Image Classification on Places205
1 code implementation • 27 Oct 2021 • Siyuan Li, Zicheng Liu, Zelin Zang, Di wu, ZhiYuan Chen, Stan Z. Li
For example, dimension reduction methods, t-SNE, and UMAP optimize pair-wise data relationships by preserving the global geometric structure, while self-supervised learning, SimCLR, and BYOL focus on mining the local statistics of instances under specific augmentations.
no code implementations • 20 Oct 2021 • Zihan Liu, Yun Luo, Zelin Zang, Stan Z. Li
Gray-box graph attacks aim at disrupting the performance of the victim model by using inconspicuous attacks with limited knowledge of the victim model.
1 code implementation • 5 Oct 2021 • Jun Xia, Lirong Wu, Ge Wang, Jintao Chen, Stan Z. Li
Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negatives) apart.
2 code implementations • 4 Oct 2021 • Fang Wu, Dragomir Radev, Stan Z. Li
Then HMGs are constructed with both atom-level and motif-level nodes.
no code implementations • 29 Sep 2021 • Siyuan Li, Zicheng Liu, Di wu, Stan Z. Li
In this paper, we decompose mixup into two sub-tasks of mixup generation and classification and formulate it for discriminative representations as class- and instance-level mixup.
no code implementations • 29 Sep 2021 • Lirong Wu, Stan Z. Li
Specifically, the GCL framework is optimized with three well-designed consistency constraints: neighborhood consistency, label consistency, and class-center consistency.
1 code implementation • 5 Aug 2021 • Cheng Tan, Jun Xia, Lirong Wu, Stan Z. Li
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance.
no code implementations • 16 Jul 2021 • Yifeng Zhao, Pei Zhang, S. A. Galindo-Torres, Stan Z. Li
Then, a global optimal feature set (the channel width, the flow velocity, the channel slope and the cross sectional area) was proposed through numerical comparison of the distilled local optimums in performance with representative ML models.
1 code implementation • 30 Jun 2021 • Di wu, Siyuan Li, Zelin Zang, Stan Z. Li
Self-supervised contrastive learning has demonstrated great potential in learning visual representations.
Ranked #22 on Fine-Grained Image Classification on NABirds
no code implementations • 17 Jun 2021 • Yifeng Zhao, Zicheng Liu, Pei Zhang, S. A. Galindo-Torres, Stan Z. Li
Whereas implicit ML-driven methods are black-boxes in nature, explicit ML-driven methods have more potential in prediction of LDC.
1 code implementation • 27 Apr 2021 • Zelin Zang, Siyuan Li, Di wu, Jianzhu Guo, Yongjie Xu, Stan Z. Li
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.
Ranked #2 on Node Clustering on Pubmed
no code implementations • 13 Apr 2021 • Ajian Liu, Chenxu Zhao, Zitong Yu, Jun Wan, Anyang Su, Xing Liu, Zichang Tan, Sergio Escalera, Junliang Xing, Yanyan Liang, Guodong Guo, Zhen Lei, Stan Z. Li, Du Zhang
To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask).
2 code implementations • 28 Mar 2021 • Fang Wu, Stan Z. Li
Sentence insertion is an interesting NLP problem but received insufficient attention.
2 code implementations • 24 Mar 2021 • Zicheng Liu, Siyuan Li, Di wu, Zihan Liu, ZhiYuan Chen, Lirong Wu, Stan Z. Li
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on Image Classification on Places205
no code implementations • 1 Jan 2021 • Stan Z. Li, Zelin Zang, Lirong Wu
The ability to preserve local geometry of highly nonlinear manifolds in high dimensional spaces and properly unfold them into lower dimensional hyperplanes is the key to the success of manifold computing, nonlinear dimensionality reduction (NLDR) and visualization.
no code implementations • 1 Jan 2021 • Jun Xia, Haitao Lin, Yongjie Xu, Lirong Wu, Zhangyang Gao, Siyuan Li, Stan Z. Li
A pseudo label is computed from the neighboring labels for each node in the training set using LP; meta learning is utilized to learn a proper aggregation of the original and pseudo label as the final label.
no code implementations • 1 Dec 2020 • Stan Z. Li, Lirong Wu, Zelin Zang
In this paper, we propose a novel neural network-based method, called Consistent Representation Learning (CRL), to accomplish the three associated tasks end-to-end and improve the consistencies.
no code implementations • CVPR 2021 • Xiangyu Zhu, Hao Wang, Hongyan Fei, Zhen Lei, Stan Z. Li
Detecting digital face manipulation has attracted extensive attention due to fake media's potential harms to the public.
no code implementations • 3 Nov 2020 • Zitong Yu, Jun Wan, Yunxiao Qin, Xiaobai Li, Stan Z. Li, Guoying Zhao
Face anti-spoofing (FAS) plays a vital role in securing face recognition systems.
no code implementations • 28 Oct 2020 • Stan Z. Li, Zelin Zang, Lirong Wu
The LGP constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training.
1 code implementation • 7 Oct 2020 • Siyuan Li, Haitao Lin, Zelin Zang, Lirong Wu, Jun Xia, Stan Z. Li
Dimension reduction (DR) aims to learn low-dimensional representations of high-dimensional data with the preservation of essential information.
no code implementations • 28 Sep 2020 • Lirong Wu, Zicheng Liu, Zelin Zang, Jun Xia, Siyuan Li, Stan Z. Li
To overcome the problem that clusteringoriented losses may deteriorate the geometric structure of embeddings in the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally.
1 code implementation • 24 Sep 2020 • Zhangyang Gao, Haitao Lin, Stan Z. Li
GDT jointly considers the local and global structures of data samples: firstly forming local clusters based on a density growing process with a strategy for properly noise handling as well as cluster boundary detection; and then estimating a GDT from relationship between local clusters in terms of a connectivity measure, givingglobal topological graph.
3 code implementations • ECCV 2020 • Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, Stan Z. Li
Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.
Ranked #1 on 3D Face Reconstruction on Florence (Mean NME metric)
1 code implementation • 21 Sep 2020 • Lirong Wu, Zicheng Liu, Zelin Zang, Jun Xia, Siyuan Li, Stan Z. Li
Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space.
1 code implementation • 21 Aug 2020 • Zitong Yu, Benjia Zhou, Jun Wan, Pichao Wang, Haoyu Chen, Xin Liu, Stan Z. Li, Guoying Zhao
Gesture recognition has attracted considerable attention owing to its great potential in applications.
no code implementations • 26 Jul 2020 • Chubin Zhuang, Zhen Lei, Stan Z. Li
Although the anchor-based detectors have taken a big step forward in pedestrian detection, the overall performance of algorithm still needs further improvement for practical applications, \emph{e. g.}, a good trade-off between the accuracy and efficiency.
2 code implementations • 15 Jun 2020 • Stan Z. Li, Zelin Zang, Lirong Wu
We propose a novel framework, called Markov-Lipschitz deep learning (MLDL), to tackle geometric deterioration caused by collapse, twisting, or crossing in vector-based neural network transformations for manifold-based representation learning and manifold data generation.
no code implementations • 23 Apr 2020 • Ajian Liu, Xuan Li, Jun Wan, Sergio Escalera, Hugo Jair Escalante, Meysam Madadi, Yi Jin, Zhuoyuan Wu, Xiaogang Yu, Zichang Tan, Qi Yuan, Ruikun Yang, Benjia Zhou, Guodong Guo, Stan Z. Li
Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing.
7 code implementations • CVPR 2020 • Jianzhu Guo, Xiangyu Zhu, Chenxu Zhao, Dong Cao, Zhen Lei, Stan Z. Li
Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization.
no code implementations • 11 Mar 2020 • Ajian Li, Zichang Tan, Xuan Li, Jun Wan, Sergio Escalera, Guodong Guo, Stan Z. Li
Ethnic bias has proven to negatively affect the performance of face recognition systems, and it remains an open research problem in face anti-spoofing.
11 code implementations • CVPR 2020 • Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li
In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.
Ranked #37 on Object Detection on COCO-O
no code implementations • 5 Dec 2019 • Ajian Liu, Zichang Tan, Xuan Li, Jun Wan, Sergio Escalera, Guodong Guo, Stan Z. Li
Regardless of the usage of deep learning and handcrafted methods, the dynamic information from videos and the effect of cross-ethnicity are rarely considered in face anti-spoofing.
no code implementations • 25 Sep 2019 • Shifeng Zhang, Yiliang Xie, Jun Wan, Hansheng Xia, Stan Z. Li, Guodong Guo
To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild.
Ranked #3 on Object Detection on WiderPerson (mMR metric)
1 code implementation • 24 Sep 2019 • Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou
Head and human detection have been rapidly improved with the development of deep convolutional neural networks.
no code implementations • 15 Sep 2019 • Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou
Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians.
no code implementations • 10 Sep 2019 • Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li
To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification.
no code implementations • 28 Aug 2019 • Shifeng Zhang, Ajian Liu, Jun Wan, Yanyan Liang, Guogong Guo, Sergio Escalera, Hugo Jair Escalante, Stan Z. Li
To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities.
no code implementations • 29 Jul 2019 • Jun Wan, Chi Lin, Longyin Wen, Yunan Li, Qiguang Miao, Sergio Escalera, Gholamreza Anbarjafari, Isabelle Guyon, Guodong Guo, Stan Z. Li
The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world.
no code implementations • 19 Feb 2019 • Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jian-Feng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
no code implementations • 20 Jan 2019 • Shifeng Zhang, Rui Zhu, Xiaobo Wang, Hailin Shi, Tianyu Fu, Shuo Wang, Tao Mei, Stan Z. Li
With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years.
3 code implementations • 2 Jan 2019 • Jianzhu Guo, Xiangyu Zhu, Jinchuan Xiao, Zhen Lei, Genxun Wan, Stan Z. Li
Specifically, we consider a printed photo as a flat surface and mesh it into a 3D object, which is then randomly bent and rotated in 3D space.
Ranked #1 on Face Anti-Spoofing on CASIA-MFSD
4 code implementations • CVPR 2019 • Shifeng Zhang, Xiaobo Wang, Ajian Liu, Chenxu Zhao, Jun Wan, Sergio Escalera, Hailin Shi, Zezheng Wang, Stan Z. Li
To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities.
3 code implementations • 7 Sep 2018 • Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou
In particular, the SRN consists of two modules: the Selective Two-step Classification (STC) module and the Selective Two-step Regression (STR) module.
Ranked #1 on Face Detection on PASCAL Face
no code implementations • ECCV 2018 • Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li
Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other.
Ranked #10 on Pedestrian Detection on Caltech (using extra training data)
no code implementations • 8 Jun 2018 • Xiangyu Zhu, Hao liu, Zhen Lei, Hailin Shi, Fan Yang, Dong Yi, Guo-Jun Qi, Stan Z. Li
In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition.
2 code implementations • 4 Jun 2018 • Jianzhu Guo, Xiangyu Zhu, Zhen Lei, Stan Z. Li
A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods.
no code implementations • 10 May 2018 • Xiaobo Wang, Shifeng Zhang, Zhen Lei, Si Liu, Xiaojie Guo, Stan Z. Li
On the other hand, the learned classifier of softmax loss is weak.
2 code implementations • 2 Apr 2018 • Xiangyu Zhu, Xiaoming Liu, Zhen Lei, Stan Z. Li
In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.
Ranked #3 on Face Alignment on AFLW
12 code implementations • CVPR 2018 • Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li
For object detection, the two-stage approach (e. g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e. g., SSD) has the advantage of high efficiency.
Ranked #175 on Object Detection on COCO test-dev
no code implementations • ICCV 2017 • Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S3FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces.
3 code implementations • 17 Aug 2017 • Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S$^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces.
Ranked #2 on Face Detection on PASCAL Face
10 code implementations • 17 Aug 2017 • Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li
The MSCL aims at enriching the receptive fields and discretizing anchors over different layers to handle faces of various scales.
Ranked #3 on Face Detection on PASCAL Face
no code implementations • 7 Jul 2017 • Yang Yang, Shengcai Liao, Zhen Lei, Stan Z. Li
Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe.
no code implementations • CVPR 2017 • Xiaobo Wang, Xiaojie Guo, Zhen Lei, Changqing Zhang, Stan Z. Li
Multi-view subspace clustering aims to partition a set of multi-source data into their underlying groups.
1 code implementation • 9 May 2017 • Haibo Jin, Xiaobo Wang, Shengcai Liao, Stan Z. Li
However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows.
no code implementations • 21 Nov 2016 • Jiali Duan, Shuai Zhou, Jun Wan, Xiaoyuan Guo, Stan Z. Li
Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited.
no code implementations • 1 Nov 2016 • Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Wei-Shi Zheng, Stan Z. Li
From this point of view, selecting suitable positive i. e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations.
no code implementations • 9 May 2016 • Hailin Shi, Xiangyu Zhu, Zhen Lei, Shengcai Liao, Stan Z. Li
Deep neural networks usually benefit from unsupervised pre-training, e. g. auto-encoders.
1 code implementation • CVPR 2016 • Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li
They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories.
no code implementations • ICCV 2015 • Shengcai Liao, Stan Z. Li
We argue that the PSD constraint provides a useful regularization to smooth the solution of the metric, and hence the learned metric is more robust than without the PSD constraint.
no code implementations • ICCV 2015 • Xiaobo Wang, Xiaojie Guo, Stan Z. Li
In this paper, we present a novel semi-supervised dictionary learning method, which uses the informative coding vectors of both labeled and unlabeled data, and adaptively emphasizes the high confidence coding vectors of unlabeled data to enhance the dictionary discriminative capability simultaneously.
no code implementations • 24 Nov 2015 • Hailin Shi, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Yang Yang, Stan Z. Li
In this paper, we propose a novel CNN-based method to learn a discriminative metric with good robustness to the over-fitting problem in person re-identification.
no code implementations • CVPR 2016 • Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, Stan Z. Li
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community.
Ranked #3 on 3D Face Reconstruction on Florence
no code implementations • CVPR 2015 • Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, Stan Z. Li
Pose and expression normalization is a crucial step to recover the canonical view of faces under arbitrary conditions, so as to improve the face recognition performance.
no code implementations • CVPR 2015 • Junjie Yan, Yinan Yu, Xiangyu Zhu, Zhen Lei, Stan Z. Li
Object detection is always conducted by object proposal generation and classification sequentially.
no code implementations • CVPR 2015 • Longyin Wen, Dawei Du, Zhen Lei, Stan Z. Li, Ming-Hsuan Yang
We present a novel Joint Online Tracking and Segmentation (JOTS) algorithm which integrates the multi-part tracking and segmentation into a unified energy optimization framework to handle the video segmentation task.
1 code implementation • ICCV 2015 • Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li
With the combination of CNN features and boosting forest, CCF benefits from the richer capacity in feature representation compared with channel features, as well as lower cost in computation and storage compared with end-to-end CNN methods.
no code implementations • 9 Apr 2015 • Guosheng Hu, Yongxin Yang, Dong Yi, Josef Kittler, William Christmas, Stan Z. Li, Timothy Hospedales
In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible.
15 code implementations • 28 Nov 2014 • Dong Yi, Zhen Lei, Shengcai Liao, Stan Z. Li
The current situation in the field of face recognition is that data is more important than algorithm.
4 code implementations • 24 Aug 2014 • Jianwei Yang, Zhen Lei, Stan Z. Li
Moreover, the nets trained using combined data from two datasets have less biases between two datasets.
Ranked #2 on Face Anti-Spoofing on CASIA-MFSD
2 code implementations • 6 Aug 2014 • Shengcai Liao, Anil K. Jain, Stan Z. Li
First, a new image feature called Normalized Pixel Difference (NPD) is proposed.
Ranked #6 on Face Detection on PASCAL Face
no code implementations • 5 Aug 2014 • Shengcai Liao, Zhipeng Mo, Jianqing Zhu, Yang Hu, Stan Z. Li
Person re-identification is becoming a hot research for developing both machine learning algorithms and video surveillance applications.
no code implementations • 18 Jul 2014 • Dong Yi, Zhen Lei, Stan Z. Li
Compared to existing researches, a more practical setting is studied in the experiments that is training and test on different datasets (cross dataset person re-identification).
no code implementations • 15 Jul 2014 • Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li
Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones.
Ranked #37 on Face Detection on WIDER Face (Medium)
1 code implementation • CVPR 2015 • Shengcai Liao, Yang Hu, Xiangyu Zhu, Stan Z. Li
In this paper, we propose an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA).
Ranked #88 on Person Re-Identification on DukeMTMC-reID
no code implementations • 5 Jun 2014 • Dong Yi, Zhen Lei, Shengcai Liao, Stan Z. Li
For NIR-VIS problem, we produce new state-of-the-art performance on the CASIA HFB and NIR-VIS 2. 0 databases.
no code implementations • CVPR 2014 • Longyin Wen, Wenbo Li, Junjie Yan, Zhen Lei, Dong Yi, Stan Z. Li
Multi-target tracking is an interesting but challenging task in computer vision field.
no code implementations • CVPR 2014 • Menglong Yang, Yiguang Liu, Longyin Wen, Zhisheng You, Stan Z. Li
Mutual occlusions among targets can cause track loss or target position deviation, because the observation likelihood of an occluded target may vanish even when we have the estimated location of the target.
no code implementations • CVPR 2014 • Junjie Yan, Zhen Lei, Longyin Wen, Stan Z. Li
Three prohibitive steps in cascade version of DPM are accelerated, including 2D correlation between root filter and feature map, cascade part pruning and HOG feature extraction.
no code implementations • CVPR 2013 • Junjie Yan, Xucong Zhang, Zhen Lei, Shengcai Liao, Stan Z. Li
The model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background.
no code implementations • CVPR 2013 • Dong Yi, Zhen Lei, Stan Z. Li
In this paper, we propose a novel method for pose robust face recognition towards practical applications, which is fast, pose robust and can work well under unconstrained environments.
no code implementations • 28 Feb 2013 • Dong Yi, Zhen Lei, Yang Hu, Stan Z. Li
However, the use of this method is very generic and not limited in face recognition, which can be easily generalized to other biometrics as a post-processing module.