Xing Xiaofen

  • Title

    Associate Professor, Doctoral Supervisor and postgraduate Supervisor,School of future technology

  • Email

    hannan@scut.edu.cn

  • Honor

    Principal Investigator of the Key Project of the National Natural Science Foundation of China Joint Fund (Brain-like Emotional Computing) from 2019 to 202

Admission Programs/Majors

  • MEng: 1) Electronic Information

  • MS:1)Intelligent Science and Technology

  • Ph.D: 1) Electronic Information; 2) Intelligent Science and Technology;

Personal Profile

Xing Xiaofen, a master's supervisor, was a key participant in the National Natural Science Foundation of China's Joint Fund Key Project (Brain-Inspired Affective Computing) from 2019 to 2022. In recent years, we have been focusing on cross-media sentiment computing based on deep learning, covering images, expressions, speech, natural language understanding and dialogue. And 3D virtual avatar interaction, etc. He/She has undertaken one National Natural Science Foundation of China Youth Project and three other science and technology plans including the Guangdong Provincial Key Research and Development Artificial Intelligence Special Project. We have established close cooperative relationships with leading AI enterprises and unicorn companies, and participated as a key member in the construction of one school-enterprise joint laboratory. More than 20 articles have been published in well-known journals and conferences in the field of artificial intelligence. I was nominated for the Best Paper Award at the renowned image processing conference ICIP and was shortlisted for the ACM MM authoritative emotion competition paper report twice. Two textbooks have been published.

Research Interests

  • Cross-media sentiment computing, covering images, expressions, speech, natural language understanding and dialogue

Representative Research Achievements

  • Yanxiong Li, Qisheng Huang, Xiaofen Xing, Xiangmin Xu:Low-complexity speaker embedding module with feature segmentation, transformation and reconstruction for few-shot speaker identification. Expert Syst. Appl. 280: 127542 (2025)

  • Weiquan Fan, Xiangmin Xu, Fang Liu, Xiaofen Xing:Multimodal speech emotion recognition via dynamic multilevel contrastive loss under local enhancement network. Expert Syst. Appl. 281: 127669 (2025)

  • Weiying Xue, Qi Liu, Yuxiao Wang, Zhenao Wei, Xiaofen Xing, Xiangmin Xu:Towards zero-shot human-object interaction detection via vision-language integration. Neural Networks 187: 107348 (2025)

  • Weiquan Fan, Xiangmin Xu, Guohua Zhou, Xiaofang Deng, Xiaofen Xing:Coordination Attention based Transformers with bidirectional contrastive loss for multimodal speech emotion recognition. Speech Commun. 169: 103198 (2025)

  • Yuanbo Fang, Xiaofen Xing, Zhaojie Chu, Yifeng Du, Xiangmin Xu:Individual-Aware Attention Modulation for Unseen Speaker Emotion Recognition. IEEE Trans. Affect. Comput. 16(2): 1205-1218 (2025)

  • Tianlei Wang, Zeliang Li, Ying Xu, Yikui Zhai, Xiaofen Xing, Kailing Guo, Pasquale Coscia, Angelo Genovese, Vincenzo Piuri, Fabio Scotti:

  • CLIP-Vision Guided Few-Shot Metal Surface Defect Recognition. IEEE Trans. Ind. Informatics 21(5): 4273-4284 (2025)

  • Zhaojie Chu, Kailing Guo, Xiaofen Xing, Pengsheng Liu, Bolun Cai, Xiangmin Xu:DCPTalk: Speech-Driven 3D Face Animation With Personalized Facial Dynamic Coupling Properties. IEEE Trans. Multim. 27: 4427-4440 (2025)

  • Kailing Guo, Zhenquan Lin, Canyang Chen, Xiaofen Xing, Fang Liu, Xiangmin Xu:Compact Model Training by Low-Rank Projection With Energy Transfer. IEEE Trans. Neural Networks Learn. Syst. 36(4): 6708-6722 (2025)

  • Wenyu Tao, Xiaofen Xing, Yirong Chen, Linyi Huang, Xiangmin Xu:TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documents. ACL (Findings) 2025: 356-371

  • Haojie Xie, Yirong Chen, Xiaofen Xing, Jingkai Lin, Xiangmin Xu:PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling. ACL (1) 2025: 1081-1115

  • Rui Liu, Xiaofen Xing, Zheng Lian, Haizhou Li, Björn W. Schuller, Haolin Zuo:MEIJU - The 1st Multimodal Emotion and Intent Joint Understanding Challenge. ICASSP 2025: 1-2

  • Rongjin Li, Weibin Zhang, Dongpeng Chen, Jintao Kang, Xiaofen Xing:SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition. ICASSP 2025: 1-5

  • Jingyuan Xing, Shuaiqi Chen, Xiangmin Xu, Xiaofen Xing:DecoupledSynth: Enhancing Zero-Shot Text-to-Speech Via Factors Decoupling. ICASSP 2025: 1-5

  • Zhaojin Chen, Sijin Yu, Xuejiao Li, Huirong Lei, Jiyu Qian, Yingxue Yao, Zicong Zheng, Guodong Liang, Xiaofen Xing, Xin Zhang, Chengfang Xu:SSS: Signature-Sequence-Statistical Model for Exploring the Impact of Prenatal Depression on Newborns' Brain Using FNIRS. ISBI 2025: 1-4

  • Xiangyu Li, Yawen Zeng, Xiaofen Xing, Jin Xu, Xiangmin Xu:HedgeAgents: A Balanced-aware Multi-agent Financial Trading System. WWW (Companion Volume) 2025: 296-305

  • Xiangyu Li, Yawen Zeng, Xiaofen Xing, Jin Xu, Xiangmin Xu:HedgeAgents: A Balanced-aware Multi-agent Financial Trading System. CoRR abs/2502.13165 (2025)

  • Rongjin Li, Weibin Zhang, Dongpeng Chen, Jintao Kang, Xiaofen Xing:SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition. CoRR abs/2504.16441 (2025)

  • Yufeng Wang, Jinwu Hu, Ziteng Huang, Kunyang Lin, Zitian Zhang, Peihao Chen, Yu Hu, Qianyue Wang, Zhuliang Yu, Bin Sun, Xiaofen Xing, Qingfang Zheng, Mingkui Tan:Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance. CoRR abs/2505.12334 (2025)

  • Yuanbo Fang, Haoze Sun, Jun Liu, Tao Zhang, Zenan Zhou, Weipeng Chen, Xiaofen Xing, Xiangmin Xu:

  • S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models. CoRR abs/2505.14438 (2025)

  • Jialong Mai, Xiaofen Xing, Yawei Li, Zhipeng Li, Jingyuan Xing, Xiangmin Xu:Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation. CoRR abs/2507.09076 (2025)

  • Sijin Yu, Zijiao Chen, Wenxuan Wu, Shengxian Chen, Zhongliang Liu, Jingxin Nie, Xiaofen Xing, Xiangmin Xu, Xin Zhang:From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure. CoRR abs/2507.16389 (2025)