Xin Wang
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
Xin Wang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Neng Gao
Institute of Information Engineering, Chinese Academy of Sciences
4 shared publications- Daren Zha
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
3 shared publications - Xiaobo Guo
Institute of Information Engineering, Chinese Academy of Sciences
3 shared publications - Bokun Wang
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publications Daren Zha
Chinese Academy of Sciences
2 shared publicationsJi Xiang
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publications
Latest Publications
- 19 July 2026
- Published by Springer Nature
- p. 86-96
RGate-MNER: Budgeted Coarse-to-Fine Visual Evidence Gating for Multimodal Named Entity Recognition
- 19 July 2026
- Published by Springer Nature
- p. 86-96
RGate-MNER: Budgeted Coarse-to-Fine Visual Evidence Gating for Multimodal Named Entity Recognition
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-594
EventPuzzle: A Benchmark for Multi-Perspective Event Prediction Based on Event Arguments
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-594
Open AccessEventPuzzle: A Benchmark for Multi-Perspective Event Prediction Based on Event Arguments
- 22 July 2025
- Published by Springer Nature
- p. 225-239
TCAN: Triple Context-Aware Network for Multi-modal Conversational Emotion Recognition
- 22 July 2025
- Published by Springer Nature
- p. 225-239
TCAN: Triple Context-Aware Network for Multi-modal Conversational Emotion Recognition
- 11 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 817-821
Tongue Features Detection Based on YOLOX and Attention Mechanism
Tongue diagnosis is a kind of Traditional Chinese Medicine (TCM) diagnosis, which is one of the key elements of “Inspection Diagnosis of TCM”. According to TCM, the tongue is closely related to the internal organs, and when the body suffers from various diseases, it will affect the endocrine function, blood composition, nerve conduction, and digestive function. Therefore, the tongue diagnosis can effectively identify whether a patient is suffering from a disease or not, and provide a medical basis for TCM diagnosis. In this paper, we propose a fusion model based on the YOLOX model and attention mechanism, which can effectively identify three pathological features of the tongue image of kidney disease: Teeth-printed tongue, Wrinkled tongue, and Greasy-fur tongue. The experimental results showed that the overall recognition of the 3 features by this fusion model was significantly improved. The overall mAP value was 91.95%, including 0.85 for the Teeth-printed tongue, 0.96 for the Wrinkled tongue, and 0.95 for the Greasy-fur tongue. Therefore, the fusion model based on the YOLOX model and attention mechanism proposed in this paper can assist physicians in quickly identifying whether a patient has kidney disease by the three types of kidney disease tongue features, which have a certain significance for the prevention and treatment of kidney disease.
- 11 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 817-821
Tongue Features Detection Based on YOLOX and Attention Mechanism
Tongue diagnosis is a kind of Traditional Chinese Medicine (TCM) diagnosis, which is one of the key elements of “Inspection Diagnosis of TCM”. According to TCM, the tongue is closely related to the internal organs, and when the body suffers from various diseases, it will affect the endocrine function, blood composition, nerve conduction, and digestive function. Therefore, the tongue diagnosis can effectively identify whether a patient is suffering from a disease or not, and provide a medical basis for TCM diagnosis. In this paper, we propose a fusion model based on the YOLOX model and attention mechanism, which can effectively identify three pathological features of the tongue image of kidney disease: Teeth-printed tongue, Wrinkled tongue, and Greasy-fur tongue. The experimental results showed that the overall recognition of the 3 features by this fusion model was significantly improved. The overall mAP value was 91.95%, including 0.85 for the Teeth-printed tongue, 0.96 for the Wrinkled tongue, and 0.95 for the Greasy-fur tongue. Therefore, the fusion model based on the YOLOX model and attention mechanism proposed in this paper can assist physicians in quickly identifying whether a patient has kidney disease by the three types of kidney disease tongue features, which have a certain significance for the prevention and treatment of kidney disease.
- Open Access
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 310-318
Multi-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning
Zero shot learning aims to recognize objects whose instances may not be covered by the training data. To generalize knowledge from seen classes to the novel ones, semantic space is built to embed knowledge from various views into multi-modal semantic embeddings. Existing semantic embeddings neglect the relationships between classes which are essential to transfer knowledge between classes. Moreover, existing zero shot learning models ignore the complementarity between semantic embeddings from different modalities. To tackle these problems, in this work, we resort to graph theory to explicitly model the interdependence between classes and then obtain new modal semantic embeddings. Furthermore, we pioneer to propose a multi-level fusion model to effectively combine knowledge encoded in multi-modal semantic embeddings together. By the virtue of subsequent fusion block, the results of multi-level fusion can be furtherly enriched and fused. Experiments show that our model could achieve promising results on various datasets. Ablation study suggests that our method is well suited for zero shot learning.
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 310-318
Open AccessMulti-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning
Zero shot learning aims to recognize objects whose instances may not be covered by the training data. To generalize knowledge from seen classes to the novel ones, semantic space is built to embed knowledge from various views into multi-modal semantic embeddings. Existing semantic embeddings neglect the relationships between classes which are essential to transfer knowledge between classes. Moreover, existing zero shot learning models ignore the complementarity between semantic embeddings from different modalities. To tackle these problems, in this work, we resort to graph theory to explicitly model the interdependence between classes and then obtain new modal semantic embeddings. Furthermore, we pioneer to propose a multi-level fusion model to effectively combine knowledge encoded in multi-modal semantic embeddings together. By the virtue of subsequent fusion block, the results of multi-level fusion can be furtherly enriched and fused. Experiments show that our model could achieve promising results on various datasets. Ablation study suggests that our method is well suited for zero shot learning.
- 8 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Path and Floor Detection in Outdoor Environments for Fall Prevention of the Visually Impaired Population
According to the world report in 2019 about vision health presented by the World Health Organization (WHO), there are 2.2 billion people in the world with some kind of visual impairment. Furthermore, in a recent National Health Interview Survey report, 25.5 million adult Americans 18 and older reported experiencing vision loss. Of these 25.5 million American adults, 15.3 million women and 10.1 million men report experiencing significant vision loss. As a result, this population is constantly at risk of a fall and its consequences. This paper presents the first module of our fall prevention system for visually impaired people. The module corresponds to a system of floor and path recognition in outdoor environments. At the core of the system is a Mask R-CNN trained with around 40.000 outdoor images. The proposed approach has reached a performance in a combination of training and testing of 92%, using a combined set of indoor and outdoor environment images.
- 8 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Path and Floor Detection in Outdoor Environments for Fall Prevention of the Visually Impaired Population
According to the world report in 2019 about vision health presented by the World Health Organization (WHO), there are 2.2 billion people in the world with some kind of visual impairment. Furthermore, in a recent National Health Interview Survey report, 25.5 million adult Americans 18 and older reported experiencing vision loss. Of these 25.5 million American adults, 15.3 million women and 10.1 million men report experiencing significant vision loss. As a result, this population is constantly at risk of a fall and its consequences. This paper presents the first module of our fall prevention system for visually impaired people. The module corresponds to a system of floor and path recognition in outdoor environments. At the core of the system is a Mask R-CNN trained with around 40.000 outdoor images. The proposed approach has reached a performance in a combination of training and testing of 92%, using a combined set of indoor and outdoor environment images.
- 5 December 2021
- Published by Springer Nature
- p. 200-211
Efficient, Low-Cost, Real-Time Video Super-Resolution Network
- 5 December 2021
- Published by Springer Nature
- p. 200-211
Efficient, Low-Cost, Real-Time Video Super-Resolution Network
- 18 October 2020
- Published by Springer Nature
- p. 286-301
TransMVG: Knowledge Graph Embedding Based on Multiple-Valued Gates
- 18 October 2020
- Published by Springer Nature
- p. 286-301
TransMVG: Knowledge Graph Embedding Based on Multiple-Valued Gates
- 9 December 2019
- Published by Springer Nature
- p. 3-14
STNet: A Style Transformation Network for Deep Image Steganography
- 9 December 2019
- Published by Springer Nature
- p. 3-14
STNet: A Style Transformation Network for Deep Image Steganography