Qintai Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qintai Hu has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Bi Zeng
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
6 shared publications - Guang Feng
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, Guangdong, China; Guangdong Institute of Digital Education, Guangzhou, 510006, Guangdong, China
6 shared publications - Pengfei Wei
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China
6 shared publications - Shuping Zhao
Guangdong University of Technology, Guangzhou, China
5 shared publications - Chunlin Li
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China
4 shared publications - Jigang Wu
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China
4 shared publications
Latest Publications
- 8 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
CauDis-MRE: Towards robust multimodal relation extraction with causally disentangled counterfactual learning and mixture-of-experts
- 8 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
CauDis-MRE: Towards robust multimodal relation extraction with causally disentangled counterfactual learning and mixture-of-experts
- 17 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Dual-structured high-order bipartite graph fusion for incomplete multi-view clustering
- 17 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Dual-structured high-order bipartite graph fusion for incomplete multi-view clustering
- 9 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
NEXPRO: Multimodal negative expression prompting for open-set video-based facial expression recognition
- 9 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
NEXPRO: Multimodal negative expression prompting for open-set video-based facial expression recognition
- 24 April 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 205, 80-86
GaitPR: A high-confidence multi-granular residual attention network for gait recognition
- 24 April 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 205, 80-86
GaitPR: A high-confidence multi-granular residual attention network for gait recognition
- Open Access
- 22 April 2026
- Published by Elsevier in SSRN Electronic Journal
NEXPRO: Multimodal Negative Expression Prompting for Open-Set Video-based Facial Expression Recognition
Open-set Video-based Facial Expression Recognition (OV-FER) extends traditional V-FER to recognize known emotions while detecting unseen ones. A key challenge lies in effectively distinguishing known from unknown categories. Existing CLIP-based approaches focus primarily on positive representations. They often overlook negative semantics, which explicitly models what expressions are not. Negative semantics is crucial for establishing decision boundaries and capturing unknown patterns. However, current negative prompting methods suffer from two limitations. First, negative text prompts fail to encode negation logic due to the standard CLIP text encoder's weakness in handling negation. Second, negative visual prompts lack semantic guidance from positive expression cues, limiting their ability to represent unknown categories. To address these limitations, we propose multimodal NEgative eXpression PROmpting (NEXPRO), a novel framework that fundamentally redesigns negative prompts from both textual and visual perspectives. NEXPRO introduces three synergistic components: (1) Negation Logic Encoding (NLE), which redesigns negative text prompts and fine-tunes the CLIP text encoder to establish clear decision boundaries; (2) Expression-Guided Negative Prompt Learning (EGNPL), which leverages positive expression semantics to guide the optimization of negative visual prompts for better capturing unknown category representations; and (3) Unified Open-set Inference (UOI), which integrates affirmative and contradictory cues into a unified probability framework for robust open-set decision-making. Extensive experiments across four OV-FER tasks on MAFW and AFEW datasets demonstrate that NEXPRO achieves state-of-the-art performance, with significant improvements of +3.39% in AUROC and +2.07% in OSCR on MAFW, and +3.28% and +4.36% on AFEW, respectively, validating its effectiveness.
- 22 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessNEXPRO: Multimodal Negative Expression Prompting for Open-Set Video-based Facial Expression Recognition
Open-set Video-based Facial Expression Recognition (OV-FER) extends traditional V-FER to recognize known emotions while detecting unseen ones. A key challenge lies in effectively distinguishing known from unknown categories. Existing CLIP-based approaches focus primarily on positive representations. They often overlook negative semantics, which explicitly models what expressions are not. Negative semantics is crucial for establishing decision boundaries and capturing unknown patterns. However, current negative prompting methods suffer from two limitations. First, negative text prompts fail to encode negation logic due to the standard CLIP text encoder's weakness in handling negation. Second, negative visual prompts lack semantic guidance from positive expression cues, limiting their ability to represent unknown categories. To address these limitations, we propose multimodal NEgative eXpression PROmpting (NEXPRO), a novel framework that fundamentally redesigns negative prompts from both textual and visual perspectives. NEXPRO introduces three synergistic components: (1) Negation Logic Encoding (NLE), which redesigns negative text prompts and fine-tunes the CLIP text encoder to establish clear decision boundaries; (2) Expression-Guided Negative Prompt Learning (EGNPL), which leverages positive expression semantics to guide the optimization of negative visual prompts for better capturing unknown category representations; and (3) Unified Open-set Inference (UOI), which integrates affirmative and contradictory cues into a unified probability framework for robust open-set decision-making. Extensive experiments across four OV-FER tasks on MAFW and AFEW datasets demonstrate that NEXPRO achieves state-of-the-art performance, with significant improvements of +3.39% in AUROC and +2.07% in OSCR on MAFW, and +3.28% and +4.36% on AFEW, respectively, validating its effectiveness.
- 5 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 318
Adaptive Pseudo-labeling for Causal-driven Cross-Modal hashing
- 5 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 318
Adaptive Pseudo-labeling for Causal-driven Cross-Modal hashing
- 25 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108514
Dynamic comprehensive difficulty knowledge cells based on KAN network and stable learning for knowledge tracing
- 25 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108514
Dynamic comprehensive difficulty knowledge cells based on KAN network and stable learning for knowledge tracing
- 22 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 187
MGIPS-CL: Multimodal NER with multi-granularity interweave and implicit positive sample contrastive learning
- 22 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 187
MGIPS-CL: Multimodal NER with multi-granularity interweave and implicit positive sample contrastive learning
- Open Access
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 193754-193764
Dynamically Adaptive Multimodal Fusion Transformer for Multimodal Sentiment Analysis
To address issues such as missing modalities and information conflicts in multimodal emotion research, this study proposes a Dynamically Adaptive Multimodal Fusion Transformer (DAMFT). DAMFT effectively integrates the complementary advantages of visual, audio, and text data through a multimodal fusion mechanism. It uses linear transformations and attention mechanisms to unify and align multimodal emotions, and assesses emotional intensity by comparing the absolute values of emotions, thereby achieving emotion intensity-driven feature interaction. Based on this, it guides auxiliary modalities to generate hypermodal representations using the primary modality, realizing adaptively guided cross-modal feature information complementarity, and solving the problems of information loss and interference in multimodal sentiment analysis. Finally, extensive experiments demonstrate the excellent performance of the proposed model on multiple datasets, and ablation experiments prove the contribution of each module in the model, achieving more accurate and robust sentiment analysis performance.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 193754-193764
Open AccessDynamically Adaptive Multimodal Fusion Transformer for Multimodal Sentiment Analysis
To address issues such as missing modalities and information conflicts in multimodal emotion research, this study proposes a Dynamically Adaptive Multimodal Fusion Transformer (DAMFT). DAMFT effectively integrates the complementary advantages of visual, audio, and text data through a multimodal fusion mechanism. It uses linear transformations and attention mechanisms to unify and align multimodal emotions, and assesses emotional intensity by comparing the absolute values of emotions, thereby achieving emotion intensity-driven feature interaction. Based on this, it guides auxiliary modalities to generate hypermodal representations using the primary modality, realizing adaptively guided cross-modal feature information complementarity, and solving the problems of information loss and interference in multimodal sentiment analysis. Finally, extensive experiments demonstrate the excellent performance of the proposed model on multiple datasets, and ablation experiments prove the contribution of each module in the model, achieving more accurate and robust sentiment analysis performance.