Dai Dawei

About Me

A Research group at Chongqing University of Posts and Telecommunications, China. Currently, we are focusing on the applications of vision (language)-to-language (vision). Part of the data and checkpoints are availabe at: https://huggingface.co/OpenFace-CQUPT.

Research Interests

• Deep Learning
• Large Vision-Language Model
• Computer Vision

OpenSource

• FaceCaption-15M (large-scale dataset)
• FaceCaptionHQ-4M (large-scale dataset)
• HumanCaption-10M (large-scale dataset)
• HumanCaption-HQ-311K (large-scale dataset)
• Human_LLaVA (vision-language model)
• Pathology-LLaVA (vision-language model)
• Face-MakeUp_SD1.5 (text-image model)

Part of Publications

​Journals​

1. ​Dawei Dai, Long Xu, Yutang Li. et al. Humanvlm: Foundation for human-scene vision-language model. Journal of Information Fusion, 2025 (IF=14.8) pdf ~code ~ checkpoint
2. ​Dw Dai, Yuanhui Zhang, Qianlan Yang, Long Xu, Xiaojing Shen, Shuying Xia, Guoyin Wang. PathologyVLM: A Large Vision-Language Model for Pathology Image Understanding. Artificial Intelligence Review, 2025 (IF=10.7) pdf ~ code ~ checkpoint
3. ​Dawei Dai, Fan Chen, Shuyin Xia. et al. An Adaptive Multi-Granularity Graph Representation of Image via Granular-Ball Computing. IEEE Transactions on Image Processing, 2025 (IF=10.8, ccf-A, accepted) code
4. ​Dw Dai, S Fu, Y Liu and G Wang. Vision-Language Joint Representation Learning for Sketch Less Facial Image Retrieval. Journal of Information Fusion, 2024 (IF=14.8) code
5. Wang Y, ​Dw Dai​, Liu D, et al. BTSC: Binary tree structure convolution layers for building interpretable decision‐making deep CNN. CAAI Transactions on Intelligence Technology, 2024 (IF=8.4) code
6. ​Dw Dai, Liu Y, Li Y, et al. LGRL: Local-Global Representation Learning for On-the-Fly FG-SBIR. IEEE Transactions on Big Data, 2024 (IF=7.5) code
7. Li D, ​Dw Dai​, Chen J, et al. Ensemble learning framework for image retrieval via deep hash ranking. Knowledge-Based Systems, 2023 (IF=7.2) code
8. ​Dw Dai, Li Y, Wang Y, et al. Rethinking the image feature biases exhibited by deep convolutional neural network models in image recognition. CAAI Transactions on Intelligence Technology, 2022 (IF=8.4)
9. ​Dw Dai, Xiaoyu Tang, Yingge Liu, et al. Multi-granularity Association Learning for On-the-fly Fine-grained Sketch-based Image Retrieval. Knowledge-Based Systems, 2022 (IF=7.2)
10. ​Dw Dai, Chengfu Tang, GuoyinWang, and ShuyinXia. Building Partially Understandable Convolutional Neural Networks by Differentiating Class-Related Neural Nodes. Neurocomputing, 2021 (IF=5.5)

​Conferences​

1. ​Liu Y, ​Dw Dai+, Hou X, et al. From Sparse to Complete: Semantic Understanding Based on Stroke Evolution in On-the-fly Sketch-based Image Retrieval. 34th International Joint Conference on Artificial Intelligence, 2025 (CCF-A, accepted) [code]
2. ​Dai D ​, Liu Y, Fu S, et al. Multimodal Image-Text Representation Learning for Sketch-Less Facial Image Retrieval. 2024 IEEE International Conference on Multimedia and Expo (ICME), 2024 (CCF-B, oral)
3. ​Dw Dai, Zhang Y, Xu L, et al. Pa-llava: A large language-vision assistant for human pathology image understanding. 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024 (CCF-B) code
4. Tang P, ​Dw Dai , Zou K, et al. GraphConvNet: A Dual Network Utilizing Local Features Coupled with Structural Information for Predicting Knee Osteoarthritis. 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024 (CCF-B) code
5. ​Dai D, Li Y, Wang L, et al. Sketch less face image retrieval: A new challenge. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023 (CCF-B) code

Powered by Jekyll and Minimal Light theme.