My name is Hoe Jiun Tian (何俊添). I am currently second year PhD student in Nanyang Technological University, Singapore under supervision of Prof Tan Yap Peng and Prof Jiang Xudong. Previously, I did research in computer vision and deep learning under supervision of Prof Chan Chee Seng in my undergraduate study in University of Malaya,.
@inproceedings{orthohash2021,title={One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective},author={Hoe, Jiun Tian and Ng, Kam Woh and Zhang, Tianyu and Chan, Chee Seng and Song, Yi-Zhe and Xiang, Tao},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2021},}
BMVC
Unsupervised Hashing with Similarity Distribution Calibration
Kam Woh Ng, Xiatian Zhu, Jiun Tian Hoe, and
4 more authors
@inproceedings{sdc2023,title={Unsupervised Hashing with Similarity Distribution Calibration},author={Ng, Kam Woh and Zhu, Xiatian and Hoe, Jiun Tian and Chan, Chee Seng and Zhang, Tianyu and Song, Yi-Zhe and Xiang, Tao},booktitle={British Machine Vision Conference (BMVC)},year={2023},}
CVPR
InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models
@inproceedings{interactdiffusion2024,title={InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models},author={Hoe, Jiun Tian and Jiang, Xudong and Chan, Chee Seng and Tan, Yap-Peng and Hu, Weipeng},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},year={2024},abs={Large-scale text-to-image (T2I) diffusion models have showcased incredible capabilities in generating coherent images based on textual descriptions, enabling vast applications in content generation. While recent advancements have introduced control over factors such as object localization, posture, and image contours, a crucial gap remains in our ability to control the interactions between objects in the generated content. Well-controlling interactions in generated images could yield meaningful applications, such as creating realistic scenes with interacting characters. In this work, we study the problems of conditioning T2I diffusion models with Human-Object Interaction (HOI) information, consisting of a triplet label (person, action, object) and corresponding bounding boxes. We propose a pluggable interaction control model, called InteractDiffusion that extends existing pre-trained T2I diffusion models to enable them being better conditioned on interactions. Specifically, we tokenize the HOI information and learn their relationships via interaction embeddings. A conditioning self-attention layer is trained to map HOI tokens to visual tokens, thereby conditioning the visual tokens better in existing T2I diffusion models. Our model attains the ability to control the interaction and location on existing T2I diffusion models, which outperforms existing baselines by a large margin in HOI detection score, as well as fidelity in FID and KID. Project page: https://jiuntian.github.io/interactdiffusion.},}
