Tianhong Dai
Research Teaching Resources
profile photo

Tianhong Dai

Lecturer (Assistant Professor)
University of Aberdeen, United Kingdom
   

I am now a Lecturer in the Department of Computing Science at University of Aberdeen. My research interests are focused on deep reinforcement learning (DRL) and its applications to robotics manipulation, video games and medical/microscopy images (e.g., axon tracking). In addition, I am also interested in the research of computational photography, such as high dynamic range (HDR) imaging.

Before I joined University of Aberdeen, I finished my Ph.D. degree and worked as a Research Associate at Imperial College London, under the supervison of Prof. Anil Anthony Bharath. Prior to that, I received an M.Sc. in Communication and Signal Processing from Imperial College London in 2016 and a B.Eng. (Hons.) in Electronic and Communication Engineering from University of Liverpool in 2015. I also had two research internships in Tencent AI Lab/Robotics X (Supervisor: Dr. Meng Fang) and Huawei Noah’s Ark Lab, London (Supervisor: Dr. Shanxin Yuan), respectively. Currently, I'm the reviewer of several conferences and journals, such as AAAI, TNNLS, ToG, Cognitive Computation, etc.

News

  • [02-2024] One paper is accepted to CVPR 2024.
  • [01-2024] One paper is accepted to ICRA 2024.
  • [12-2023] One paper is accepted to ICASSP 2024.
  • [11-2023] One paper is accepted to CVIU 2023.
  • [06-2023] One paper is accepted to IROS 2023.
  • [01-2023] One paper is accepted to IEEE T-ASE.
  • [11-2022] I joined the University of Aberdeen as a Lecturer in Computing Science.
  • [07-2022] I passed my PhD viva successfully.

Publications

(* denotes equal contributions)
  • PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation
    Xinqiao Zhao, Ziqian Yang, Tianhong Dai, Bingfeng Zhang, Jimin Xiao
    IEEE/CVF Computer Vision and Pattern Recognition Conference, 2024
    [ Paper | Code ]
  • Cross Domain Policy Transfer with Effect Cycle-Consistency
    Ruiqi Zhu, Tianhong Dai, Oya Celiktutan
    IEEE International Conference on Robotics and Automation, 2024
    [ Paper | Code ]
  • Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
    Wangyu Wu, Tianhong Dai, Xiaowei Huang, Fei Ma, Jimin Xiao
    International Conference on Acoustics, Speech and Signal Processing, 2024
    [ Paper | Code ]
  • Wavelet-Based Network For High Dynamic Range Imaging
    Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan
    Computer Vision and Image Understanding, 2023
    [ Paper | Code ]
  • Learning to Solve Tasks with Exploring Prior Behaviours
    Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang, Oya Celiktutan
    IEEE International Conference on Intelligent Robots and Systems, 2023
    [ Paper | Code ]
  • Deep Reinforcement Learning for Real-time Assembly Planning in Robot-based Prefabricated Construction
    Aiyu Zhu*, Tianhong Dai*, Gangyan Xu*, Pieter Pauwels, Bauke de Vries, Meng Fang
    IEEE Transactions on Automation Science and Engineering, 2023
    [ Paper | Code ]
  • Progressive Multi-Scale Fusion Network For RGB-D Salient Object Detection
    Guangyu Ren, Yanchun Xie, Tianhong Dai, Tania Stathaki
    Computer Vision and Image Understanding, 2022
    [ Paper | Code ]
  • Machine Learning to Support Visual Auditing of Home-based Lateral Flow Immunoassay Self-Test Results for SARS-CoV-2 Antibodies
    Nathan Wong, Sepehr Meshkinfamfard, Valérian Turbé, Mathew Whitaker, Maya Moshe, Alessia bardanzellu, Tianhong Dai, Eduardo Pignatelli, Wendy Barclay, Ara Darzi, Paul Elliott, Helen Ward, Reiko Tanaka, Graham Cooke, Rachel McKendry, Christina Atchison, Anil Anthony Bharath
    Communications Medicine (Nature), 2022
    [ Paper | Code ]
  • LevDoom: A Benchmark for Generalization on Level Difficulty in Reinforcement Learning
    Tristan Tomilin, Tianhong Dai, Mykola Pechenizkiy, Meng Fang
    IEEE Conference on Games, 2022
    [ Paper | Code ]
  • Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
    Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra, Feryal Behbahani, Anil Anthony Bharath
    Neurocomputing, 2022
    [ Paper | Code ]
  • Adaptive Intra-Group Aggregation for Co-Saliency Detection
    Guangyu Ren*, Tianhong Dai*, Tania Stathaki
    International Conference on Acoustics, Speech and Signal Processing, 2022
    [ Paper | Code ]
  • Diversity-Augmented Intrinsic Motivation for Deep Reinforcement Learning
    Tianhong Dai, Yali Du, Meng Fang, Anil Anthony Bharath
    Neurocomputing, 2021
    [ Paper | Code ]
  • Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
    Tianhong Dai, Hengyan Liu, Kai Arulkumaran, Guangyu Ren, Anil Anthony Bharath
    Pacific Rim International Conference on Artificial Intelligence, 2021
    [ Paper | Code ]
  • Coupled Network for Robust Pedestrian Detection with Gated Multi-layer Feature Extraction and Deformable Occlusion Handling
    Tianrui Liu, Wenhan Luo, Lin Ma, Jun-Jie Huang, Tania Stathaki, Tianhong Dai
    IEEE Transactions on Imaging Processing, 2020
    [ Paper ]
  • Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
    Tianrui Liu, Jun-Jie Huang, Tianhong Dai, Guangyu Ren, Tania Stathaki
    International Conference on Acoustics, Speech and Signal Processing, 2020
    [ Paper ]
  • Episodic Self-Imitation Learning with Hindsight
    Tianhong Dai, Hengyan Liu, Anil Anthony Bharath
    Electronics, Special Issue on Deep Reinforcement Learning: Methods and Applications, 2020
    [ Paper | Code ]
  • LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
    Yali Du, Lei Han, Meng Fang, Tianhong Dai, Ji Liu, Dacheng Tao
    Advances in Neural Information Processing Systems, 2019
    [ Paper | Code ]
  • A Maximum Entropy Deep Reinforcement Learning Neural Tracker
    Shafa Balaram, Kai Arulkumaran, Tianhong Dai, Anil Anthony Bharath
    International Workshop on Machine Learning in Medical Imaging (Conjunction with MICCAI), 2019
    [ Paper | Code ]
  • Deep Reinforcement Learning for Subpixel Neural Tracking
    Tianhong Dai, Magda Dubois, Kai Arulkumaran, Jonathan Campbell, Cher Bass, Benjamin Billot, Fatmatulzehra Uslu, Vincenzo de Paola, Claudia Clopath, and Anil Anthony Bharath
    International Conference on Medical Imaging with Deep Learning (Spotlight), 2019
    [ Paper | Code ]
  • Image Synthesis with a Convolutional Capsule Generative Adversarial Network
    Cher Bass, Tianhong Dai, Benjamin Billot, Kai Arulkumaran, Antonia Creswell, Claudia Clopath, Vincenzo de Paola, Anil Anthony Bharath
    International Conference on Medical Imaging with Deep Learning (Oral), 2019
    [ Paper | Code ]