default author photo

Xiaofei Zhu

Chongqing University of Technology (CQUT)

SCHOLARLY PAPERS

5

DOWNLOADS

189

TOTAL CITATIONS

1

Scholarly Papers (5)

1.

Cross-Modality Multiband Differential Conditional Diffusion for Multimodal Emotion Recognition in Conversation

Number of pages: 12 Posted: 29 Dec 2025
Xiaofei Zhu, Yang Jiang, Xiaoyang Liu and Yihao Zhang
Chongqing University of Technology (CQUT), affiliation not provided to SSRN, affiliation not provided to SSRN and affiliation not provided to SSRN
Downloads 57 (1,020,567)

Abstract:

Loading...

Multimodal emotion recognition, Diffusion model, Discrete Wavelet Transform, Emotion Analysis

2.

Conditional Graph Diffusion with Granular-ball Representation for Multimodal Recommendation

Number of pages: 12 Posted: 25 Oct 2025
Xiaofei Zhu and Ling Tan
Chongqing University of Technology (CQUT) and affiliation not provided to SSRN
Downloads 46 (1,145,425)

Abstract:

Loading...

Multimodal recommendation, Granular-ball Computing, Conditional Diffusion Model, Graph Neural Network

3.

DHKD: A Debiased Hierarchical Knowledge Distillation for Multimodal Emotion Recognition in Conversation

Number of pages: 15 Posted: 22 Dec 2025
Chongqing University of Technology (CQUT), Wenzhou Kean University, Fuzhou University and Chongqing University of Technology (CQUT)
Downloads 42 (1,222,651)

Abstract:

Loading...

Multimodal Fusion, Knowledge Distillation, Emotion Recognition

4.

CM-CGNS: Cross-Modal Clustering-Guided Negative Sampling for Self-Supervised Joint Learning from Medical Images and Reports

Number of pages: 12 Posted: 21 Jan 2026
affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, Chongqing University of Technology (CQUT), Chongqing Medical University, University of Leicester - School of Computing and Mathematical Sciences and Southwest University
Downloads 31 (1,318,317)

Abstract:

Loading...

Clustering-guided negative sampling, Contrastive Learning, Masked image reconstruction, Multimodal self-supervised learning

5.

CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation

Number of pages: 16 Posted: 22 Dec 2025
Xiaofei Zhu, Jiawei Cheng and Kunyang Huang
Chongqing University of Technology (CQUT), Chongqing University of Technology (CQUT) and Wenzhou Kean University
Downloads 13 (1,518,554)
Citation 1

Abstract:

Loading...

Emotion Recognition, Multimodal Representation Learning, Multimodal Information Fusion