no code implementations • 28 Mar 2024 • Yuhong He, Yongqi Zhang, Shizhu He, Jun Wan
This approach eliminates the need for entity annotation and increases the transparency of the MDG process by explicitly generating the intermediate reasoning chain.
no code implementations • 21 Mar 2024 • Ajian Liu, Shuai Xue, Jianwen Gan, Jun Wan, Yanyan Liang, Jiankang Deng, Sergio Escalera, Zhen Lei
Specifically, we propose a novel Class Free Prompt Learning (CFPL) paradigm for DG FAS, which utilizes two lightweight transformers, namely Content Q-Former (CQF) and Style Q-Former (SQF), to learn the different semantic prompts conditioned on content and style features by using a set of learnable query vectors, respectively.
no code implementations • 19 Mar 2024 • Zhigang Chen, Benjia Zhou, Jun Li, Jun Wan, Zhen Lei, Ning Jiang, Quan Lu, Guoqing Zhao
Although some approaches work towards gloss-free SLT through jointly training the visual encoder and translation network, these efforts still suffer from poor performance and inefficient use of the powerful Large Language Model (LLM).
2 code implementations • 6 Feb 2024 • Yichen Shi, Yuhao Gao, Yingxin Lai, Hongyang Wang, Jun Feng, Lei He, Jun Wan, Changsheng chen, Zitong Yu, Xiaochun Cao
For the face forgery detection task, we evaluate GAN-based and diffusion-based data with both visual and acoustic modalities.
no code implementations • 31 Jan 2024 • Hao Fang, Ajian Liu, Haocheng Yuan, Junze Zheng, Dingheng Zeng, Yanhong Liu, Jiankang Deng, Sergio Escalera, Xiaoming Liu, Jun Wan, Zhen Lei
These three modules seamlessly form a robust unified attack detection framework.
no code implementations • 31 Jan 2024 • Hao Tan, Zichang Tan, Jun Li, Jun Wan, Zhen Lei
In contrast to the unidirectional fusion in previous works, we introduce a Dual-Modal Attention (DMA) that enables bidirectional interaction between textual and visual features, yielding context-aware label representations and semantic-related visual representations, which are subsequently used to calculate similarities and generate final predictions for all labels.
1 code implementation • 11 Dec 2023 • Hao Tan, Jun Li, Yizhuang Zhou, Jun Wan, Zhen Lei, Xiangyu Zhang
We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly.
no code implementations • 5 Dec 2023 • Tianshun Han, Shengnan Gui, Yiqing Huang, Baihui Li, Lijian Liu, Benjia Zhou, Ning Jiang, Quan Lu, Ruicong Zhi, Yanyan Liang, Du Zhang, Jun Wan
The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder.
1 code implementation • ICCV 2023 • Benjia Zhou, Zhigang Chen, Albert Clapés, Jun Wan, Yanyan Liang, Sergio Escalera, Zhen Lei, Du Zhang
Many previous methods employ an intermediate representation, i. e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT).
Ranked #1 on Gloss-free Sign Language Translation on PHOENIX14T
Gloss-free Sign Language Translation Self-Supervised Learning +3
no code implementations • 19 Jul 2023 • Zenghao Bao, Zichang Tan, Jun Li, Jun Wan, Xibo Ma, Zhen Lei
Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation.
no code implementations • 29 Jun 2023 • Zichang Tan, Jun Li, Jinhao Du, Jun Wan, Zhen Lei, Guodong Guo
To achieve the collaborative learning in long-tailed learning, the balanced online distillation is proposed to force the consistent predictions among different experts and augmented copies, which reduces the learning uncertainties.
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 • 15 Apr 2023 • Hao Fang, Ajian Liu, Jun Wan, Sergio Escalera, Hugo Jair Escalante, Zhen Lei
Based on this dataset and protocol-$3$ for evaluating the robustness of the algorithm under quality changes, we organized a face presentation attack detection challenge in surveillance scenarios.
1 code implementation • 12 Apr 2023 • Dong Wang, Jia Guo, Qiqi Shao, Haochi He, Zhian Chen, Chuanbao Xiao, Ajian Liu, Sergio Escalera, Hugo Jair Escalante, Zhen Lei, Jun Wan, Jiankang Deng
Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop.
no code implementations • 14 Mar 2023 • Jun Wan, Jun Liu, Jie zhou, Zhihui Lai, Linlin Shen, Hang Sun, Ping Xiong, Wenwen Min
Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results.
no code implementations • 12 Jan 2023 • Kunchi Li, Jun Wan, Shan Yu
Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data learning between the learned and new classes because of the limited storage memory.
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 • 16 Nov 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang
Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i. e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i. e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i. e., the high similarity between multimodal representations caused to insufficient late fusion.
Ranked #2 on Action Recognition on NTU RGB+D
no code implementations • 7 Oct 2022 • Hanshen Xiao, Jun Wan, Srinivas Devadas
We also introduce a refined gradient clipping method, which can further sharpen the privacy loss in private learning when combined with ModelMix.
no code implementations • 29 Sep 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang
To achieve these two purposes, we propose a novel data-centric ViT training framework to dynamically measure the ``difficulty'' of training samples and generate ``effective'' samples for models at different training stages.
1 code implementation • CVPR 2022 • Jun Li, Zichang Tan, Jun Wan, Zhen Lei, Guodong Guo
NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively.
Ranked #5 on Long-tail Learning on CIFAR-10-LT (ρ=50)
no code implementations • 14 Feb 2022 • Beihang Song, Jing Li, Shan Xue, Jun Chang, Jia Wu, Jun Wan, Tianpeng Liu
In this study, we developed a single-stage rotating object detector via two points with a solar corona heatmap (ROTP) to detect oriented objects.
no code implementations • 29 Jan 2022 • Yunfang Fu, Qiuqi Ruan, Ziyan Luo, Gaoyun An, Yi Jin, Jun Wan
In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed.
3D Facial Expression Recognition Dimensionality Reduction +1
no code implementations • 23 Dec 2021 • Jun Wan, Hui Xi, Jie zhou, Zhihui Lai, Witold Pedrycz, Xu Wang, Hang Sun
We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved.
1 code implementation • CVPR 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang, Du Zhang, Zhen Lei, Hao Li, Rong Jin
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors.
Ranked #1 on Hand Gesture Recognition on NVGesture
no code implementations • 25 Oct 2021 • Zenghao Bao, Zichang Tan, Yu Zhu, Jun Wan, Xibo Ma, Zhen Lei, Guodong Guo
To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on.
no code implementations • 16 Aug 2021 • Ajian Liu, Chenxu Zhao, Zitong Yu, Anyang Su, Xing Liu, Zijian Kong, Jun Wan, Sergio Escalera, Hugo Jair Escalante, Zhen Lei, Guodong Guo
The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers.
no code implementations • 24 Jun 2021 • Sergio Escalera, Marti Soler, Stephane Ayache, Umut Guclu, Jun Wan, Meysam Madadi, Xavier Baro, Hugo Jair Escalante, Isabelle Guyon
Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence.
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).
1 code implementation • 10 Feb 2021 • Benjia Zhou, Yunan Li, Jun Wan
Meanwhile, a more adaptive architecture-searched network structure can also perform better than the block-fixed ones like Resnet since it increases the diversity of features in different stages of the network better.
1 code implementation • 23 Jan 2021 • Can Gao, Jie Zhoua, Duoqian Miao, Xiaodong Yue, Jun Wan
Attribute reduction is one of the most important research topics in the theory of rough sets, and many rough sets-based attribute reduction methods have thus been presented.
no code implementations • 22 Dec 2020 • Xianxu Hou, Xiaokang Zhang, Linlin Shen, Zhihui Lai, Jun Wan
Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lacks of control over the generation process in order to achieve semantic face editing.
1 code implementation • 9 Dec 2020 • Jun Wan, Zhihui Lai, Jing Li, Jie zhou, Can Gao
Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance.
no code implementations • International Journal of Computer Vision 2020 • Yunan Li, Jun Wan, Qiguang Miao, Sergio Escalera, Huijuan Fang, Huizhou Chen, Xiangda Qi, Guodong Guo
First impressions strongly influence social interactions, having a high impact in the personal and professional life.
no code implementations • 16 Nov 2020 • Yongqi Zhang, HUI ZHANG, Quanming Yao, Jun Wan
Thus, inspired by the observation that classifier is more robust to noisy labels while representation is much more fragile, and by the recent advances of self-supervised representation learning (SSRL) technologies, we design a new method, i. e., CS$^3$NL, to obtain representation by SSRL without labels and train the classifier directly with noisy labels.
no code implementations • 16 Nov 2020 • Jun Wan, Zhihui Lai, Linlin Shen, Jie zhou, Can Gao, Gang Xiao, Xianxu Hou
Moreover, a novel cross-order cross-semantic (COCS) regularizer is designed to drive the network to learn cross-order cross-semantic features from different activation for facial landmark detection.
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 • 17 Oct 2020 • Jun Wan, Zhihui Lai, Jun Liu, Jie zhou, Can Gao
Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments.
Ranked #7 on Face Alignment on AFLW-19
no code implementations • 25 Aug 2020 • Jinheng Xie, Jun Wan, Linlin Shen, Zhihui Lai
Although current face alignment algorithms have obtained pretty good performances at predicting the location of facial landmarks, huge challenges remain for faces with severe occlusion and large pose variations, etc.
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 • 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.
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.
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)
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.
2 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.
no code implementations • 19 Nov 2018 • Yunxiao Qin, Chenxu Zhao, Zezheng Wang, Junliang Xing, Jun Wan, Zhen Lei
The method RAML aims to give the Meta learner the ability of leveraging the past learned knowledge to reduce the dimension of the original input data by expressing it into high representations, and help the Meta learner to perform well.
1 code implementation • 13 Nov 2018 • Zezheng Wang, Chenxu Zhao, Yunxiao Qin, Qiusheng Zhou, Guo-Jun Qi, Jun Wan, Zhen Lei
Face anti-spoofing is significant to the security of face recognition systems.
no code implementations • 5 Dec 2017 • Pichao Wang, Wanqing Li, Jun Wan, Philip Ogunbona, Xinwang Liu
Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities.
no code implementations • 31 Oct 2017 • Pichao Wang, Wanqing Li, Philip Ogunbona, Jun Wan, Sergio Escalera
Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data.
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 • 17 Oct 2013 • Hugo Jair Escalante, Isabelle Guyon, Vassilis Athitsos, Pat Jangyodsuk, Jun Wan
In the considered scenario a single training-video is available for each gesture to be recognized, which limits the application of traditional techniques (e. g., HMMs).