Dr Yang Zhao

Dr Yang Zhao

she/her

Applied AI & Computer Vision
Multimodal Learning
Research Scientist

Yang Zhao

About Me

I am a passionate Applied AI & Computer Vision & Multimodal Learning Research Scientist with over 9 years of research and development experience. I have a proven track record for solving challenging real-world computer vision and AI tasks. I have worked with many domain experts to understand their real-world problems and develop the most appropriate solutions. My research lies broadly in computer vision and AI, with a particular focus on developing vision-language models, multimodal learning methods, and foundation model techniques that can be applied to real-world challenges across disciplines. My current interests include AI for sustainable agriculture, AI for health, and AI for cultural heritage and digital humanities.

Previously Lecturer at La Trobe University, Research Fellow at the Australian Institute for Machine Learning (University of Adelaide), and PhD in AI. Published over 40 peer-reviewed publications, including at premier venues such as TPAMI, ICCV, ICLR, EMNLP, and AAAI.

I am always open to interdisciplinary collaboration and currently supervise Honours, Master’s, and Doctoral students.

Recent News

  • [Oct 2026] I’m honoured to share that I’ve been selected as a finalist for the Data Science / AI Pioneer Award at the 2026 Women of Colour in STEM Awards.
  • [Jan 2026] One paper “VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery” has been accepted to ICLR 2026.
  • [Jan 2026] One paper “VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery” has been accepted to EACL 2026.
  • [July 2025] One paper “PresentAgent: Multimodal Agent for Presentation Video Generation” has been accepted to EMNLP 2025.
  • [July 2025] One paper “PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection” has been accepted to ECAI 2025 (spotlight).
  • [July 2025] One paper “Contrastive Lie Algebra Learning for Ultra-Fine-Grained Visual Categorization” has been accepted to MM 2025.
  • [June 2025] One paper “Advancing federated domain generalization in ophthalmology: Vision enhancement and consistency assurance for multicenter fundus image segmentation” has been accepted to Pattern Recognition.
  • [June 2025] One paper “CIT: Rethinking class-incremental semantic segmentation with a Class Independent Transformation” has been accepted to Pattern Recognition.
  • [March 2025] One paper “MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule” has been accepted to ICME 2025.
Older news
  • [Dec. 2024] Received SCEMS Early Career Researcher Award 2024 at La Trobe University.
  • [Nov. 2024] Received Australian Pattern Recognition Society (APRS) Early Career Researcher Award 2024 at DICTA 2024.
  • [Nov. 2024] Invited talk “Landmark Detection and Medical Applications” at DICTA 2024.
  • [Oct. 2024] One paper “MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection” has been accepted to BIBM 2024 (Oral).
  • [July 2024] One paper titled “Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion” has been accepted to BMVC 2024.
  • [April 2024] One paper titled “Artificial Intelligence to Automate Assessment of Ocular and Periocular Measurements” has been accepted to European Journal of Ophthalmology.
  • [Feb. 2024] One paper titled “A Landmark-based Approach for Instability Prediction in Distal Radius Fractures” has been accepted to IEEE ISBI 2024.
  • [Jan. 2024] One paper titled “Facial and Mandibular Landmark Tracking with Habitual Head Posture Estimation using Linear and Fiducial Markers” has been accepted to Healthcare Technology Letters.
  • [Jan. 2024] One paper titled “Self-Supervised Lie Algebra Representation Learning via Optimal Canonical Metric” has been accepted to IEEE TNNLS.
  • [Jan. 2024] One paper titled “Occluded Person Retrieval with Hierarchical Feature Optimization” has been accepted to IEEE FG 2024 (Oral) (best reviewed papers).
  • [Aug. 2023] I joined CSIT, La Trobe University as a continuing Lecturer (Assistant Professor).
  • [Feb. 2023] One paper titled “Normal periocular anthropometric measurements in an Australian population” has been accepted to International Ophthalmology.
  • [Nov. 2022] One paper “Learning Deep Asymmetric Tolerant Part Representation” accepted in IEEE TAI.
  • [Oct. 2022] One paper “Mix-ViT: Mixing Attentive Vision Transformer for Ultra-Fine-Grained Visual Categorization” accepted in Pattern Recognition.
  • [Aug. 2022] One paper “Gait-Assisted Video Person Retrieval” accepted in IEEE TCSVT.
  • [Apr. 2022] One paper “SPARE: Self-Supervised Part Erasing for Ultra-Fine-Grained Visual Categorization” accepted in Pattern Recognition.
  • [Apr. 2022] One paper “RB-Net: Training Highly Accurate and Efficient Binary Neural Networks with Reshaped Point-wise Convolution and Balanced Activation” accepted in IEEE TCSVT.
  • [Feb. 2022] I joined AIML, The University of Adelaide as a Machine Learning Orthopaedic Research Fellow.
  • [Sept. 2021] One paper “EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation” accepted in DICTA 2021.
  • [Aug. 2021] One paper “Learning Discriminative Region Representation for Person Retrieval” accepted in Pattern Recognition.
  • [Jul. 2021] One paper “Benchmark Platform for Ultra-Fine-Grained Visual Categorization Beyond Human Performance” accepted in ICCV 2021.
  • [May 2021] One paper “MaskCOV: A Random Mask Covariance Network for Ultra-Fine-Grained Visual Categorization” accepted in Pattern Recognition.
  • [Mar. 2021] One paper “Learning Deep Part-Aware Embedding for Person Retrieval” accepted in Pattern Recognition.
  • [Feb. 2020] One paper “Deep high-resolution representation learning for visual recognition” accepted in IEEE TPAMI.
  • [Nov. 2019] One paper “MobileFAN: transferring deep hidden representation for face alignment” accepted in Pattern Recognition.
  • [Nov. 2019] One paper “Patchy Image Structure Classification Using Multi-Orientation Region Transform” accepted in AAAI 2020.
  • [Apr. 2019] One paper “High-resolution representations for labeling pixels and regions” published in arXiv.
  • [Mar. 2018] I went to The University of Adelaide.
  • [Feb. 2018] I enrolled in Griffith University.

Contact