Search Results for author: Jun Wan

Found 55 papers, 13 papers with code

AI Competitions and Benchmarks: Dataset Development

no code implementations15 Apr 2024 Romain Egele, Julio C. S. Jacques Junior, Jan N. van Rijn, Isabelle Guyon, Xavier Baró, Albert Clapés, Prasanna Balaprakash, Sergio Escalera, Thomas Moeslund, Jun Wan

Initially, we develop the tasks involved in dataset development and offer insights into their effective management (including requirements, design, implementation, evaluation, distribution, and maintenance).

Management

Unified Physical-Digital Attack Detection Challenge

no code implementations9 Apr 2024 Haocheng Yuan, Ajian Liu, Junze Zheng, Jun Wan, Jiankang Deng, Sergio Escalera, Hugo Jair Escalante, Isabelle Guyon, Zhen Lei

Based on this dataset, we organized a Unified Physical-Digital Face Attack Detection Challenge to boost the research in Unified Attack Detections.

Face Anti-Spoofing Face Recognition

BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation

no code implementations28 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.

Dialogue Generation Language Modelling +1

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

no code implementations21 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.

Domain Generalization Face Anti-Spoofing

Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation

no code implementations19 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).

Gloss-free Sign Language Translation Language Modelling +3

PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition

no code implementations31 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.

Representation Learning

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

1 code implementation11 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.

Domain Generalization

Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining

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).

Gloss-free Sign Language Translation Self-Supervised Learning +3

General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone

no code implementations19 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.

Age Estimation MORPH

NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition

no code implementations29 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.

Surveillance Face Presentation Attack Detection Challenge

no code implementations15 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.

Face Anti-Spoofing Face Presentation Attack Detection +1

Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results

1 code implementation12 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.

Face Anti-Spoofing Face Recognition

Precise Facial Landmark Detection by Reference Heatmap Transformer

no code implementations14 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.

Facial Landmark Detection

Effective Decision Boundary Learning for Class Incremental Learning

no code implementations12 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.

Class Incremental Learning Incremental Learning +1

Surveillance Face Anti-spoofing

no code implementations3 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.

Contrastive Learning Face Anti-Spoofing +2

A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition

1 code implementation16 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.

Action Recognition Data Augmentation +2

Differentially Private Deep Learning with ModelMix

no code implementations7 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.

Effective Vision Transformer Training: A Data-Centric Perspective

no code implementations29 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.

Nested Collaborative Learning for Long-Tailed Visual Recognition

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.

Image Classification Long-tail Learning

Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap

no code implementations14 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.

Object object-detection +2

2D+3D facial expression recognition via embedded tensor manifold regularization

no code implementations29 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

Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network

no code implementations23 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.

Facial Landmark Detection

LAE : Long-tailed Age Estimation

no code implementations25 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.

Age Estimation Data Augmentation +1

ChaLearn Looking at People: Inpainting and Denoising challenges

no code implementations24 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.

Denoising Pose Estimation

Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition

1 code implementation10 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.

Gesture Recognition Neural Architecture Search

Granular conditional entropy-based attribute reduction for partially labeled data with proxy labels

1 code implementation23 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.

Attribute

GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing

no code implementations22 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.

Attribute Image Generation

Robust Facial Landmark Detection by Multi-order Multi-constraint Deep Networks

1 code implementation9 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.

Facial Landmark Detection regression

Combining Self-Supervised and Supervised Learning with Noisy Labels

no code implementations16 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.

Learning with noisy labels Representation Learning +1

Robust Facial Landmark Detection by Cross-order Cross-semantic Deep Network

no code implementations16 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.

Facial Landmark Detection

Robust Face Alignment by Multi-order High-precision Hourglass Network

no code implementations17 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.

Face Alignment regression +2

Think about boundary: Fusing multi-level boundary information for landmark heatmap regression

no code implementations25 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.

Face Alignment regression

Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review

no code implementations23 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.

Face Anti-Spoofing Face Recognition

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

no code implementations11 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.

Face Anti-Spoofing Face Recognition

Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing

no code implementations5 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.

Face Anti-Spoofing

WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild

no code implementations25 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)

Object Detection Pedestrian Detection

CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing

no code implementations28 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.

Face Anti-Spoofing Face Recognition

ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition

no code implementations29 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.

Gesture Recognition

A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing

3 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.

Face Anti-Spoofing Face Recognition

Representation based and Attention augmented Meta learning

no code implementations19 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.

Few-Shot Learning

Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition

no code implementations5 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.

Action Recognition Temporal Action Localization

RGB-D-based Human Motion Recognition with Deep Learning: A Survey

no code implementations31 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.

Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition

no code implementations21 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.

Gesture Recognition

Principal motion components for gesture recognition using a single-example

no code implementations17 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).

Gesture Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.