Zequn Zeng

About Me

I am a Ph.D. student at Xidian University and advised by Prof. Bo Chen. My long-term research goal is to build an explainable multi-modality cognition system in which machines can reason, make logical decisions, and generate content like humans.

Research Interests

My current research lies in multi-modality understanding and generation. My research areas involve:

Image-to-text understanding: visual captioning, VQA, prompt learning in vision-and-language models
Text-to-image synthesizing: image editing, visual diffusion models
Knowledge-aware machine learning: retrieval-augmented generation, knowledge-enhancement

News

[Mar. 2024] Our paper about memory-augmented image captioning is accepted to CVPR 20241
[July. 2023] Our paper about multi-Label image classification is accepted to ICCV 2023!
[Mar. 2023] Our paper about zero-shot image captioning is accepted to CVPR 2023!
[Feb. 2022] Our paper about image paragraphing is accepted to IJCV 2022!

Publications

CVPR

MeaCap: Memory-Augmented Zero-shot Image Captioning

Zequn Zeng, Yan Xie, Hao Zhang, Chiyu Chen, Bo Chen

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

PDF Code
ICCV

PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification

Miaoge Li, Dongsheng Wang, Xinyang Liu, Zequn Zeng, Ruiying Lu, Bo Chen

International Conference on Computer Vision (ICCV), 2023.

PDF Code
CVPR

ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing

Zequn Zeng, Hao Zhang, Zhengjue Wang, Ruiying Lu, Dongsheng Wang, Bo Chen

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

PDF Code
IJCV

Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning

Dandan Guo, Ruiying Lu, Bo Chen, Zequn Zeng, Mingyuan Zhou

International Journal of Computer Vision(IJCV), 2022.

PDF Code

About Me

Research Interests

News

Publications

Services

Conference Reviewers

Journal Reviewers