Ying Sha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ying Sha has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
Yuxue Hu
8 shared publicationsDongyu Su
6 shared publicationsGuixin Su
6 shared publications- Tongguan Wang
Huazhong Agricultural University, Wuhan, China
5 shared publications Mingmin Wu
College of Informatics, Huazhong Agricultural University, Wuhan, China
4 shared publications- Tongguan Wang
College of Informatics Huazhong Agricultural University Wuhan China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-736
Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-736
Open AccessSemantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
- 6 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
BIG-TM: Bridging Individual Guidance with Trifusion MoPoE for Chinese memes understanding
- 6 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
BIG-TM: Bridging Individual Guidance with Trifusion MoPoE for Chinese memes understanding
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4635-4646
Beyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4635-4646
Open AccessBeyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3776-3787
MePe: Rethinking Multimodal Chinese Idiom Reading Comprehension from a Metaphorical Perspective
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3776-3787
Open AccessMePe: Rethinking Multimodal Chinese Idiom Reading Comprehension from a Metaphorical Perspective
- 19 July 2025
- Published by Springer Nature
- p. 307-318
GEETI: Graph Embedding-Enhanced Textual Inversion for Chinese Harmful Meme Detection and Identification
- 19 July 2025
- Published by Springer Nature
- p. 307-318
GEETI: Graph Embedding-Enhanced Textual Inversion for Chinese Harmful Meme Detection and Identification
- 24 June 2025
- Published by Springer Nature
- p. 342-356
Capturing Multivariate Long-Range Dependencies: Hypergraph Contrastive Learning for Evidence-Aware Fake News Detection
- 24 June 2025
- Published by Springer Nature
- p. 342-356
Capturing Multivariate Long-Range Dependencies: Hypergraph Contrastive Learning for Evidence-Aware Fake News Detection
- 2 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 319
RCLMuFN: Relational context learning and multiplex fusion network for multimodal sarcasm detection
- 2 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 319
RCLMuFN: Relational context learning and multiplex fusion network for multimodal sarcasm detection
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (24) , 25398-25406
McHirc: A Multimodal Benchmark for Chinese Idiom Reading Comprehension
The performance of various tasks of natural language processing has greatly improved with the emergence of large language models. However, there is still much room for improvement in understanding certain specific linguistic phenomena, such as Chinese idioms, which are usually composed of four characters. Chinese idioms are difficult to understand due to semantic gaps between their literal and actual meanings. Researchers have proposed the Chinese idiom reading comprehension task to examine the ability of large language models to represent and understand Chinese idioms. The task requires choosing the correct Chinese idiom from a list of candidates to complete the sentence. The current research mainly focuses on text-based idiom comprehension. Nevertheless, there are many idiom application scenarios that combine images and text, and we believe that the corresponding images are beneficial for the model's understanding of the idioms. Therefore, to address the above problems, we first construct a large-scale Multimodal Chinese Idiom Reading Comprehension dataset (MChIRC), which contains a total of 44,433 image-text pairs covering 2,926 idioms. Then, we propose a Dual-Contrastive Idiom Graph Network (DCIGN), which employs a dual-contrastive learning module to align the text and image features corresponding to the same Chinese idiom at both coarse and fine levels, while utilizing a graph structure to capture the semantic relationships between idiom candidates. Finally, we use a cross-attention module to fuse multimodal features with graph features of candidate idioms to predict correct answers. The authoritativeness of MChIRC and the effectiveness of DCIGN are demonstrated through a variety of experiments, which provides a new benchmark for the multimodal Chinese idiom reading comprehension task.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (24) , 25398-25406
Open AccessMcHirc: A Multimodal Benchmark for Chinese Idiom Reading Comprehension
The performance of various tasks of natural language processing has greatly improved with the emergence of large language models. However, there is still much room for improvement in understanding certain specific linguistic phenomena, such as Chinese idioms, which are usually composed of four characters. Chinese idioms are difficult to understand due to semantic gaps between their literal and actual meanings. Researchers have proposed the Chinese idiom reading comprehension task to examine the ability of large language models to represent and understand Chinese idioms. The task requires choosing the correct Chinese idiom from a list of candidates to complete the sentence. The current research mainly focuses on text-based idiom comprehension. Nevertheless, there are many idiom application scenarios that combine images and text, and we believe that the corresponding images are beneficial for the model's understanding of the idioms. Therefore, to address the above problems, we first construct a large-scale Multimodal Chinese Idiom Reading Comprehension dataset (MChIRC), which contains a total of 44,433 image-text pairs covering 2,926 idioms. Then, we propose a Dual-Contrastive Idiom Graph Network (DCIGN), which employs a dual-contrastive learning module to align the text and image features corresponding to the same Chinese idiom at both coarse and fine levels, while utilizing a graph structure to capture the semantic relationships between idiom candidates. Finally, we use a cross-attention module to fuse multimodal features with graph features of candidate idioms to predict correct answers. The authoritativeness of MChIRC and the effectiveness of DCIGN are demonstrated through a variety of experiments, which provides a new benchmark for the multimodal Chinese idiom reading comprehension task.
- Open Access
Keyword-Oriented Multimodal Modeling for Euphemism Identification
Euphemism identification deciphers the true meaning of euphemisms, such as linking "weed" (euphemism) to "marijuana" (target keyword) in illicit texts, aiding content moderation and combating underground markets. While existing methods are primarily text-based, the rise of social media highlights the need for multimodal analysis, incorporating text, images, and audio. However, the lack of multimodal datasets for euphemisms limits further research. To address this, we regard euphemisms and their corresponding target keywords as keywords and first introduce a keyword-oriented multimodal corpus of euphemisms (KOM-Euph), involving three datasets (Drug, Weapon, and Sexuality), including text, images, and speech. We further propose a keyword-oriented multimodal euphemism identification method (KOM-EI), which uses cross-modal feature alignment and dynamic fusion modules to explicitly utilize the visual and audio features of the keywords for efficient euphemism identification. Extensive experiments demonstrate that KOM-EI outperforms state-of-the-art models and large language models, and show the importance of our multimodal datasets.
Open AccessKeyword-Oriented Multimodal Modeling for Euphemism Identification
Euphemism identification deciphers the true meaning of euphemisms, such as linking "weed" (euphemism) to "marijuana" (target keyword) in illicit texts, aiding content moderation and combating underground markets. While existing methods are primarily text-based, the rise of social media highlights the need for multimodal analysis, incorporating text, images, and audio. However, the lack of multimodal datasets for euphemisms limits further research. To address this, we regard euphemisms and their corresponding target keywords as keywords and first introduce a keyword-oriented multimodal corpus of euphemisms (KOM-Euph), involving three datasets (Drug, Weapon, and Sexuality), including text, images, and speech. We further propose a keyword-oriented multimodal euphemism identification method (KOM-EI), which uses cross-modal feature alignment and dynamic fusion modules to explicitly utilize the visual and audio features of the keywords for efficient euphemism identification. Extensive experiments demonstrate that KOM-EI outperforms state-of-the-art models and large language models, and show the importance of our multimodal datasets.
- Open Access
RCLMuFN: Relational Context Learning and Multiplex Fusion Network for Multimodal Sarcasm Detection
Sarcasm typically conveys emotions of contempt or criticism by expressing a meaning that is contrary to the speaker's true intent. Accurate detection of sarcasm aids in identifying and filtering undesirable information on the Internet, thereby reducing malicious defamation and rumor-mongering. Nonetheless, the task of automatic sarcasm detection remains highly challenging for machines, as it critically depends on intricate factors such as relational context. Most existing multimodal sarcasm detection methods focus on introducing graph structures to establish entity relationships between text and images while neglecting to learn the relational context between text and images, which is crucial evidence for understanding the meaning of sarcasm. In addition, the meaning of sarcasm changes with the evolution of different contexts, but existing methods may not be accurate in modeling such dynamic changes, limiting the generalization ability of the models. To address the above issues, we propose a relational context learning and multiplex fusion network (RCLMuFN) for multimodal sarcasm detection. Firstly, we employ four feature extractors to comprehensively extract features from raw text and images, aiming to excavate potential features that may have been previously overlooked. Secondly, we utilize the relational context learning module to learn the contextual information of text and images and capture the dynamic properties through shallow and deep interactions. Finally, we employ a multiplex feature fusion module to enhance the generalization of the model by penetratingly integrating multimodal features derived from various interaction contexts. Extensive experiments on two multimodal sarcasm detection datasets show that our proposed method achieves state-of-the-art performance.
Open AccessRCLMuFN: Relational Context Learning and Multiplex Fusion Network for Multimodal Sarcasm Detection
Sarcasm typically conveys emotions of contempt or criticism by expressing a meaning that is contrary to the speaker's true intent. Accurate detection of sarcasm aids in identifying and filtering undesirable information on the Internet, thereby reducing malicious defamation and rumor-mongering. Nonetheless, the task of automatic sarcasm detection remains highly challenging for machines, as it critically depends on intricate factors such as relational context. Most existing multimodal sarcasm detection methods focus on introducing graph structures to establish entity relationships between text and images while neglecting to learn the relational context between text and images, which is crucial evidence for understanding the meaning of sarcasm. In addition, the meaning of sarcasm changes with the evolution of different contexts, but existing methods may not be accurate in modeling such dynamic changes, limiting the generalization ability of the models. To address the above issues, we propose a relational context learning and multiplex fusion network (RCLMuFN) for multimodal sarcasm detection. Firstly, we employ four feature extractors to comprehensively extract features from raw text and images, aiming to excavate potential features that may have been previously overlooked. Secondly, we utilize the relational context learning module to learn the contextual information of text and images and capture the dynamic properties through shallow and deep interactions. Finally, we employ a multiplex feature fusion module to enhance the generalization of the model by penetratingly integrating multimodal features derived from various interaction contexts. Extensive experiments on two multimodal sarcasm detection datasets show that our proposed method achieves state-of-the-art performance.