📰 Publications

† : Equal Contribution

GraphCFC

GraphCFC: A directed graph based cross-modal feature complementation approach for multimodal conversational emotion recognition

Jiang Li, Xiaoping Wang, Guoqing Lv, Zhigang Zeng

GraphCFC effectively extracts contextual and interactive information multimodal converesation. By employing multiple subspace extractors and a pair-wise cross-modal complementary (PairCC) strategy, GraphCFC alleviates the heterogeneity gap in multimodal fusion and extracts diverse information from multimodal dialogue graphs. GAT-MLP mitigates the over-smoothing issue in GNNs and offers a new structure for multimodal learning. By representing conversations as multimodal directed graphs and encoding various types of edges extracted from these graphs, the GAT-MLP layer is capable of precisely selecting crucial contextual and interactive information.

Journal Papers

• Jiang Li, Xiaoping Wang, Guoqing Lv, Zhigang Zeng, GraphCFC: A directed graph based cross-modal feature complementation approach for multimodal conversational emotion recognition, IEEE Transactions on Multimedia (TMM), 2023, DOI: 10.1109/TMM.2023.3260635. [JCR Q1, CAAI-A]
• Jiang Li, Xiaoping Wang, Guoqing Lv, Zhigang Zeng, GA2MIF: Graph and attention based two-stage multi-source information fusion for conversational emotion detection, IEEE Transactions on Affective Computing (TAFFC), 2023, DOI: 10.1109/TAFFC.2023.3261279. [JCR Q1, CAAI-A]
• Jiang Li, Xiaoping Wang, Yingjian Liu, Zhigang Zeng, CFN-ESA: A cross-modal fusion network with emotion-shift awareness for dialogue emotion recognition, IEEE Transactions on Affective Computing (TAFFC), 2024, DOI: 10.1109/TAFFC.2024.3389453. [JCR Q1, CAAI-A]
• Yingjian Liu†, Jiang Li†, Xiaoping Wang, Zhigang Zeng, EmotionIC: Emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation, SCIENCE CHINA Information Sciences (SCIS), 2023, DOI: 10.1007/s11432-023-3908-6. [Equal Contribution, JCR Q1, CAAI-A]
• Jiang Li, Xiaoping Wang, Zhigang Zeng, Tracing intricate cues in dialogue: Joint graph structure and sentiment dynamics for multimodal emotion recognition, In Submission, 2024. [JCR Q0, CAAI-0]
• Jiang Li, Xiaoping Wang, Guoqing Lv, Zhigang Zeng, GraphMFT: A graph network based multimodal fusion technique for emotion recognition in conversation, Neurocomputing (NEUCOM), 2023, DOI: 10.1016/j.neucom.2023.126427. [JCR Q1, CAAI-B]
• Jiang Li, Xiaoping Wang, Yingjian Liu, Zhigang Zeng, ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy, Knowledge-Based Systems (KBS), 2024, DOI: 10.1016/j.knosys.2024.111434. [JCR Q1, CAAI-B]
• Jiang Li, Xiaoping Wang, Zhigang Zeng, A dual-stream recurrence-attention network with global–local awareness for emotion recognition in textual dialog, Engineering Applications of Artificial Intelligence (EAAI), 2023, DOI: 10.1016/j.engappai.2023.107530. [JCR Q1, CAAI-C]
• Guoqing Lv†, Jiang Li†, Xiaoping Wang, Xin Zhan, Zhigang Zeng, Producing considerate responses: Progressive staged training for emotional support conversation, In Submission, 2024. [Equal Contribution, JCR Q0, CAAI-0]
• Junnan Li†, Jiang Li†, Xiaoping Wang, Xin Zhan, Zhigang Zeng, A domain generalization and residual network-based emotion recognition from physiological signals, Cyborg and Bionic Systems (CBS), 2023, DOI: 10.34133/cbsystems.0074. [Equal Contribution, JCR Q1]
• Fusheng Yu†, Jiang Li†, Xiaoping Wang, Shaojin Wu, Junjie Zhang, Zhigang Zeng, Large, complex, and realistic safety clothing and helmet detection: Dataset and method, In Submission, 2024. [Equal Contribution, JCR Q0, CAAI-0]
• Chao Yang, Xiaoping Wang, Zhanfei Chen, Jiang Li, Nan Qin, Tingwen Huang, Zhigang Zeng, A bio-inspired tactile-olfactory fusion perception system based on memristive spiking neural network, In Submission, 2024. [JCR Q0, CAAI-0]

Conference Papers

• Guoqing Lv†, Jiang Li†, Xiaoping Wang, Zhigang Zeng, InferEM: Inferring the speaker’s intention for empathetic dialogue generation, The 45th Annual Meeting of the Cognitive Science Society (CogSci 2023), 26-29 July 2023, Sydney, Australia. [Equal Contribution, CAAI-B]
• Jiang Li, Xiaoping Wang, Shanglin Lei, Zhigang Zeng, A spatio-temporal scale based affective neural network for emotion detection in conversation, 2023 China Automation Congress (CAC 2023), 17-19 November 2023, Chongqing, China. [CAA-A]
• Shanglin Lei, Xiaoping Wang, Jiang Li, Guanting Dong, Sirui Wang, EmoCog: A GNN-driven two-stage framework via multi-level cognitive information fusion for ERC, In Submission, 2024. [CAAI-0]
• Shanglin Lei, Xiaoping Wang, Guanting Dong, Jiang Li, Zhigang Zeng, Watch the speakers: A hybrid continuous attribution network for emotion recognition in conversation with emotion disentanglement, The 35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2023), 6-8 November 2023, Atlanta, USA. [CAAI-C]