Chenxu Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chenxu Zhao has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Zhen Lei
Chinese Academy of Sciences
7 shared publications - Anyang Su
Mininglamp Technology, Beijing, China
5 shared publications - Minghui Wu
Mininglamp
5 shared publications - Tianyu Fu
Mininglamp Technology, Beijing, China
5 shared publications - Zitong Yu
Great Bay University, Dongguan, China
4 shared publications - Anyang Su
Mininglamp Technology
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11613-11622
Learning Explainable Video Saliency Prediction from Reasoning-Annotated Eye-Tracking Supervision
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11613-11622
Open AccessLearning Explainable Video Saliency Prediction from Reasoning-Annotated Eye-Tracking Supervision
- 8 November 2026
- Published by Springer Nature
- p. 204-216
Learning to See Before Reasoning: Attention-Warmup On-Policy Distillation for Multimodal Reasoning
- 8 November 2026
- Published by Springer Nature
- p. 204-216
Learning to See Before Reasoning: Attention-Warmup On-Policy Distillation for Multimodal Reasoning
- 2 October 2026
- Published by Springer Nature
- p. 240-258
Dive Into the Implicit Biases of Low-Rank Vision-Language Alignment
- 2 October 2026
- Published by Springer Nature
- p. 240-258
Dive Into the Implicit Biases of Low-Rank Vision-Language Alignment
- 9 September 2026
- Published by Springer Nature
- p. 507-524
WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation
- 9 September 2026
- Published by Springer Nature
- p. 507-524
WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8174-8183
PRE-MAP: Personalized Reinforced Eye-tracking Multimodal LLM for High-Resolution Multi-Attribute Point Prediction
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8174-8183
Open AccessPRE-MAP: Personalized Reinforced Eye-tracking Multimodal LLM for High-Resolution Multi-Attribute Point Prediction
- Open Access
- 28 December 2024
- Published by Springer Nature in Data Science and Engineering
- Vol. 10 (1) , 12-23
DTIA: Disruptive Text-Image Alignment for Countering Text-to-Image Diffusion Model Personalization
Personalized content synthesis technologies based on diffusion models have achieved significant breakthroughs, allowing for the creation of specific images from just a few reference photos. However, when these technologies are used to create fake news or unsettling content targeting individuals, they pose a substantial risk to society. To address this issue, current methods generate adversarial samples by adversarially maximizing the training loss, thus disrupting any personalized generation model trained with these samples. However, these methods are not efficient and do not fully consider the intrinsic mechanisms of successful personalization attacks. In this paper, we introduce an innovative Disruptive Text-Image Alignment (DTIA) framework. Based on the analysis that existing methods succeed in their attacks due to an overfitting of text to noise, which results in inaccurate face information matching, we have designed a Text-Image Mis-Match Attack framework. This framework aims to disrupt the model’s learning of associations between input faces and specific texts, thereby reducing unnecessary computational load. We also studied how the choice of timestep in diffusion models affects adversarial attacks and proposed a step schedule strategy to enhance algorithm efficiency. Extensive experiments on facial benchmarks have demonstrated that our DTIA framework not only disrupts personalized generation models but also significantly improves model efficiency.
- 28 December 2024
- Published by Springer Nature in Data Science and Engineering
- Vol. 10 (1) , 12-23
Open AccessDTIA: Disruptive Text-Image Alignment for Countering Text-to-Image Diffusion Model Personalization
Personalized content synthesis technologies based on diffusion models have achieved significant breakthroughs, allowing for the creation of specific images from just a few reference photos. However, when these technologies are used to create fake news or unsettling content targeting individuals, they pose a substantial risk to society. To address this issue, current methods generate adversarial samples by adversarially maximizing the training loss, thus disrupting any personalized generation model trained with these samples. However, these methods are not efficient and do not fully consider the intrinsic mechanisms of successful personalization attacks. In this paper, we introduce an innovative Disruptive Text-Image Alignment (DTIA) framework. Based on the analysis that existing methods succeed in their attacks due to an overfitting of text to noise, which results in inaccurate face information matching, we have designed a Text-Image Mis-Match Attack framework. This framework aims to disrupt the model’s learning of associations between input faces and specific texts, thereby reducing unnecessary computational load. We also studied how the choice of timestep in diffusion models affects adversarial attacks and proposed a step schedule strategy to enhance algorithm efficiency. Extensive experiments on facial benchmarks have demonstrated that our DTIA framework not only disrupts personalized generation models but also significantly improves model efficiency.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7316-7325
Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding
Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Video Subjective Multi-modal Evaluation dataset, namely Video-SME. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on Video-SME and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/mininglamp-MLLM/HMLLM
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7316-7325
Open AccessHypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding
Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Video Subjective Multi-modal Evaluation dataset, namely Video-SME. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on Video-SME and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/mininglamp-MLLM/HMLLM
- 10 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5330-5345
CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing
- 10 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5330-5345
CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing
- 30 December 2023
- Published by Springer Nature
- p. 209-238
Face Presentation Attack Detection
- Open Access
Searching for Alignment in Face Recognition
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has attracted little attention. In this paper, we first explore and highlight the effects of different alignment templates on face recognition. Then, for the first time, we try to search for the optimal template automatically. We construct a well-defined searching space by decomposing the template searching into the crop size and vertical shift, and propose an efficient method Face Alignment Policy Search (FAPS). Besides, a well-designed benchmark is proposed to evaluate the searched policy. Experiments on our proposed benchmark validate the effectiveness of our method to improve face recognition performance.
Open AccessSearching for Alignment in Face Recognition
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has attracted little attention. In this paper, we first explore and highlight the effects of different alignment templates on face recognition. Then, for the first time, we try to search for the optimal template automatically. We construct a well-defined searching space by decomposing the template searching into the crop size and vertical shift, and propose an efficient method Face Alignment Policy Search (FAPS). Besides, a well-designed benchmark is proposed to evaluate the searched policy. Experiments on our proposed benchmark validate the effectiveness of our method to improve face recognition performance.