Anyang Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anyang Su has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Chenxu Zhao
Mininglamp Technology, Beijing, China
5 shared publications - Huiying Li
Jilin University, College of Computer Science and Technology, No. 2699 Qianjin Street, Changchun, Jilin province, 130012, China; Jilin University, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, No. 2699 Qianjin Street, Changchun, Jilin province, 130012, China
5 shared publications - Minghui Wu
Mininglamp
5 shared publications - Tianyu Fu
Mininglamp Technology, Beijing, China
5 shared publications - Ping Jiang
Mininglamp
3 shared publications - Beiping Tan
Mininglamp Technology, Beijing, China
2 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
- 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
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-9
ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection
Unsupervised industrial anomaly detection methods can identify product defects in industrial images using only normal samples for training. Existing approaches perform well on public industrial image datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains. To tackle this issue, this paper presents a two-stage training strategy, called ToCoAD. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive learning. This approach enables the model to progressively learn the distribution of anomalies specific to industrial datasets, effectively enhancing its generalizability to various types of anomalies. Extensive experiments are conducted to demonstrate the effectiveness of our proposed two-stage training strategy, and our model produces competitive performance, achieving pixel-level AUROC scores of 98.21%, 98.43% and 97.70% on MVTec AD, VisA and BTAD respectively.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-9
ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection
Unsupervised industrial anomaly detection methods can identify product defects in industrial images using only normal samples for training. Existing approaches perform well on public industrial image datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains. To tackle this issue, this paper presents a two-stage training strategy, called ToCoAD. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive learning. This approach enables the model to progressively learn the distribution of anomalies specific to industrial datasets, effectively enhancing its generalizability to various types of anomalies. Extensive experiments are conducted to demonstrate the effectiveness of our proposed two-stage training strategy, and our model produces competitive performance, achieving pixel-level AUROC scores of 98.21%, 98.43% and 97.70% on MVTec AD, VisA and BTAD respectively.
- 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
- 13 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (2) , 198-202
Identification and Grading of Maize Drought on RGB Images of UAV Based on Improved U-Net
A prerequisite for solving many agricultural problems is to accurately estimate the area affected by crop disasters and its severity rating. In this letter, we propose a pipeline to segment the drought area and distinguish the severity rating of the maize on RGB images accessed by an unmanned aerial vehicle (UAV) through a semantic segmentation method based on deep learning. First, the ground truth is created through expert evaluation and visual interpretation with the aid of the Normalized Difference Vegetation Index (NDVI). The neural network structure that was used is based on U-Net. Some structural and parameter improvements on U-net were made using SE-ResNeXt-50 as the backbone with the atrous spatial pyramid pooling (ASPP) module. By using RGB images as the input of the neural network for training, the final trained network can work on RGB images captured by a consumer UAV. The experimental results showed that our pipeline achieved an F1-score of 0.9034 and a Jaccard index of 0.8287 on the test set.
- 13 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (2) , 198-202
Identification and Grading of Maize Drought on RGB Images of UAV Based on Improved U-Net
A prerequisite for solving many agricultural problems is to accurately estimate the area affected by crop disasters and its severity rating. In this letter, we propose a pipeline to segment the drought area and distinguish the severity rating of the maize on RGB images accessed by an unmanned aerial vehicle (UAV) through a semantic segmentation method based on deep learning. First, the ground truth is created through expert evaluation and visual interpretation with the aid of the Normalized Difference Vegetation Index (NDVI). The neural network structure that was used is based on U-Net. Some structural and parameter improvements on U-net were made using SE-ResNeXt-50 as the backbone with the atrous spatial pyramid pooling (ASPP) module. By using RGB images as the input of the neural network for training, the final trained network can work on RGB images captured by a consumer UAV. The experimental results showed that our pipeline achieved an F1-score of 0.9034 and a Jaccard index of 0.8287 on the test set.
- Open Access
- 30 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 24808-24818
Color Space Transformation and Multi-Class Weighted Loss for Adhesive White Blood Cell Segmentation
White blood cells (WBCs) are the cells of immune system, protecting against infective diseases and invasion of viruses and bacteria. Their aberrant number, both abnormal increase and decrease, is a sign of an ongoing pathology, a precise evaluation of their number is of the utmost importance as the first step of assessing a potential disease. In blood cell microscopic images, since red blood cells and platelets are similar in color with WBCs, and WBCs are partially adhesive, WBC segmentation for counting is often not resulting in a good performance. Therefore, in this work, a color space transformation is proposed to filter out red blood cells and platelets, which is transforming the blood cell microscopic images of patients with acute lymphoblastic leukemia from RGB color space to HSV to detect and extract WBCs. For precisely segmenting adhesive WBCs in extraction results, we set cell border to the third class, in addition to foreground and background. A weighted cross-entropy loss function based on class weight and distance transformation weight enhanced U-Net to learn cell border features. Our results showed that the method proposed in this paper for WBC segmentation using the data set ALL_IDB1 could achieve an accuracy of 97.92%.
- 30 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 24808-24818
Open AccessColor Space Transformation and Multi-Class Weighted Loss for Adhesive White Blood Cell Segmentation
White blood cells (WBCs) are the cells of immune system, protecting against infective diseases and invasion of viruses and bacteria. Their aberrant number, both abnormal increase and decrease, is a sign of an ongoing pathology, a precise evaluation of their number is of the utmost importance as the first step of assessing a potential disease. In blood cell microscopic images, since red blood cells and platelets are similar in color with WBCs, and WBCs are partially adhesive, WBC segmentation for counting is often not resulting in a good performance. Therefore, in this work, a color space transformation is proposed to filter out red blood cells and platelets, which is transforming the blood cell microscopic images of patients with acute lymphoblastic leukemia from RGB color space to HSV to detect and extract WBCs. For precisely segmenting adhesive WBCs in extraction results, we set cell border to the third class, in addition to foreground and background. A weighted cross-entropy loss function based on class weight and distance transformation weight enhanced U-Net to learn cell border features. Our results showed that the method proposed in this paper for WBC segmentation using the data set ALL_IDB1 could achieve an accuracy of 97.92%.
- Open Access
- 29 November 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-10
Promising Hybrid Graphene-Silver Nanowire Composite Electrode for Flexible Organic Light-Emitting Diodes
Thanks to its high transparency, high carrier mobility, and thermal conductivity, graphene is often used as transparent conductive electrode (TCE) in optoelectronic devices. However, the low carrier concentration and high resistance caused by vacancy defects, grain boundaries, and superposed folds in typical graphene films limit its application. In this study, we propose a method to increase both the conductivity and carrier concentration in single-layer graphene (SLG) by blending it with silver nanowires (AgNWs). AgNWs provide connections between grain boundaries of graphene to improve charge-carrier transport. The AgNWs in this study can reduce the resistance of SLG from 650 Ω/◻ to 27 Ω/◻ yet still maintain a transmittance of 86.7% (at 550 nm). Flexible organic light-emitting diode, with a maximum 15000 cd m−2 luminance was successfully fabricated using such graphene and AgNWs composite transparent electrodes.
- 29 November 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-10
Open AccessPromising Hybrid Graphene-Silver Nanowire Composite Electrode for Flexible Organic Light-Emitting Diodes
Thanks to its high transparency, high carrier mobility, and thermal conductivity, graphene is often used as transparent conductive electrode (TCE) in optoelectronic devices. However, the low carrier concentration and high resistance caused by vacancy defects, grain boundaries, and superposed folds in typical graphene films limit its application. In this study, we propose a method to increase both the conductivity and carrier concentration in single-layer graphene (SLG) by blending it with silver nanowires (AgNWs). AgNWs provide connections between grain boundaries of graphene to improve charge-carrier transport. The AgNWs in this study can reduce the resistance of SLG from 650 Ω/◻ to 27 Ω/◻ yet still maintain a transmittance of 86.7% (at 550 nm). Flexible organic light-emitting diode, with a maximum 15000 cd m−2 luminance was successfully fabricated using such graphene and AgNWs composite transparent electrodes.
- Open Access
- 1 October 2019
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 13 (04) , 1-15
Bisupervised network with pyramid pooling module for land cover classification of satellite remote sensing imagery
The Journal of Applied Remote Sensing (JARS) is an online journal that optimizes the communication of concepts, information, and progress within the remote sensing community to improve the societal benefit for monitoring and management of natural disasters, weather forecasting, agricultural and urban land-use planning, environmental quality monitoring, ecological restoration, and numerous other commercial and scientific applications.
- 1 October 2019
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 13 (04) , 1-15
Open AccessBisupervised network with pyramid pooling module for land cover classification of satellite remote sensing imagery
The Journal of Applied Remote Sensing (JARS) is an online journal that optimizes the communication of concepts, information, and progress within the remote sensing community to improve the societal benefit for monitoring and management of natural disasters, weather forecasting, agricultural and urban land-use planning, environmental quality monitoring, ecological restoration, and numerous other commercial and scientific applications.