Dr. Tao He is currently a Deputy Researcher (equivalent to Associate Professor) at the Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China (UESTC). Prior to joining UESTC, he was a Research Fellow at Monash University, Australia. He received his Ph.D. in Computer Science from Monash University in 2022, under the supervision of Associate Professor Yuan-Fang Li, with co-supervision by Professor Lianli Gao. He obtained his M.S. degree in Computer Science from UESTC in 2018 under the supervision of Professor Jingkuan Song, and his B.S. degree in Computer Science from Northeast Normal University (NENU) in 2015. Dr. Tao's research interests lie in the field of computer vision/multimodal learning, with a particular focus on scene graph generation, human-object interaction detection and image retrieval.

Accepting highly self-motivated Ph.D students.

Recent News

• Two papers accepted to ICCV 2025 on Panoptic Scene Graph Generation and Incomplete Multimodal Learning.
• One paper accepted to CVPR 2025 on Visual Emotion Recognition.
• Two papers accepted to ICASSP 2025 on Audio-to-Intent Recognition.
• Two papers accepted to ACM MM 2024 on scene graph generation and model compression.
• One paper accepted to TIP 2023 on scene graph generation.
• One paper accepted to TIP 2022 on unbiased scene graph generation.
• One paper accepted to ECCV 2022 on open-vocabulary scene graph generation.
• Starting my postdoc in the Vision and Language group from Feb. 2022.
• One paper accepted to TNNLS 2021 on network embedding.
• One paper accepted to ICCV 2021 on Human-Ojbect interaction with scene graphs.

Selected Publications

• Xin Hu, Ke Qin, Guiduo Duan, Ming Li, Yuan-Fang Li, Tao He*. SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning. ICCV 2025.
• Ruiting Dai, Chenxi Li, Yandong Yan, Lisi Mo, Ke Qin, Tao He*. Unbiased Missing-modality Multimodal Learning. ICCV 2025.
• Wen Yin, Yong Wang, Guiduo Duan, Dongyang Zhang, Xin Hu, Yuan-Fang Li, Tao He*. Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition. CVPR 2025. [code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li. Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection. TIP 2023. [code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li. State-aware Compositional Learning towards Unbiased Training for Scene Graph Generation. TIP 2022. [code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li. Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning. ECCV 2022. [code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li. Exploiting Scene Graphs for Human-Object Interaction Detection. ICCV 2021.[code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li.Semisupervised Network Embedding With Differentiable Deep Quantization. TNNLS 2021. [code] [paper]  
• Jingkuan Song, Tao He, Lianli Gao, Alan Hanjalic, Hengtao Shen. Unified Binary Generative Adversarial Network for Image Retrieval and Compression. IJCV 2020.[code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Xing Wang, Ke Huang, Yuan-Fang Li. Sneq: Semi-supervised Attributed Network Embedding with Attention-based Quantisation. AAAI 2020.[code] [paper]  
• Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, Yuan-Fang Li. Learning from the scene and borrowing from the rich: Tackling the long tail in scene graph generation. IJCAI 2020.[code] [paper]  

Acadamic Service

• As a reviewer for conferences: CVPR, ECCV, ICCV, CVPR, AAAI, ACMMM, CIKM
• As a reviewer for journals: TIP, TNNLS, TPAMI, IJCV etc.