I graduated with a Master of Science degree in computer vision and machine learning from the Australian National University in 2021. Currently, I am pursuing a Ph.D. at the Australian National University’s College of Engineering and Computer Science in Canberra, ACT, Australia, with a focus on computer vision and machine learning. My research aims to explore and advance the intersection of computer vision and natural language processing, particularly in the context of Vision Large Language Models (VLLMs). I have developed a Set-of-Vision prompting (SoV) approach to enhance zero-shot emotion recognition by integrating spatial information, such as facial landmarks and bounding boxes, to improve face detection accuracy and emotion categorization. This work has the potential to significantly improve emotion recognition systems in natural environments, opening up new avenues for VLLMs in real-world applications.
🔥 News
- 2024.11: 🎉🎉 The paper titled "Visual Prompting in LLMs for Enhancing Emotion Recognition" has been published in EMNLP 2024.
- 2024.06: 🎉🎉 The paper titled "LLDif: Diffusion Models for Low-light Emotion Recognition" has been published in ICPR 2024.
📝 Publications
Visual Prompting in LLMs for Enhancing Emotion Recognition
Qixuan Zhang, Zhifeng Wang, Dylan Zhang, Wenjia Niu, Sabrina Caldwell, Tom Gedeon, Yang Liu, Zhenyue Qin, EMNLP 2024
- Proposed Set-of-Vision (SoV) prompting approach for enhancing facial expression recognition in Vision-Language Large Models (VLLMs).
LLDif: Diffusion Models for Low-light Emotion Recognition
Zhifeng Wang, Kaihao Zhang & Ramesh Sankaranarayana, ICPR 2024
DM-HAP: Diffusion model for accurate hand pose prediction
Zhifeng Wang, Kaihao Zhang , Ramesh Sankaranarayana, Neurocomputing 2024
LRDif: Diffusion Models for Under-Display Camera Emotion Recognition
Zhifeng Wang, Kaihao Zhang , Ramesh Sankaranarayana, ICIP 2024
Htnet for micro-expression recognition
Zhifeng Wang, Kaihao Zhang , Ramesh Sankaranarayana, Neurocomputing 2023
- Geometric-Aware Facial Landmark Emotion Recognition, Qixuan Zhang, Zhifeng Wang , Yang Liu, Zhenyue Qin, Kaihao Zhang, Tom Gedeon, CSECS 2023
- Authentic Emotion Mapping: Benchmarking Facial Expressions in Real News, Qixuan Zhang, Zhifeng Wang , Yang Liu, Zhenyue Qin, Kaihao Zhang, Sabrina Caldwell, Tom Gedeon,
📖 Educations
- 2022.03 - 2025.01 (now), Ph.D. at the Australian National University’s College of Engineering and Computer Science in Canberra, ACT, Australia.
- 2020.02 - 2022.02,M.S. degree in computer vision and machine learning from the Australian National University.
💬 Invited Talks
- 2024.10, SoV Prompting: Enhancing Vision Large Language Models for Zero-Shot Emotion Recognition with Spatial Visual Prompts, in ANU AI Talk
- 2024.06, A diffusion-based framework for enhancing facial expression recognition in extremely low-light environments through label-aware embeddings and transformer networks, ANU HDR Talk
- 2023.04, A diffusion-based framework leveraging transformers for robust facial expression recognition under under-display camera (UDC) challenges.
- 2022.04, A novel approach for micro-expression recognition leveraging local and global facial feature interactions to enhance performance.