no code implementations • ECCV 2020 • Yi Huang, Fan Wang, Adams Wai-Kin Kong, Kwok-Yan Lam
The experiments show that the universal patches are able to mislead the detector with greater probabilities.
1 code implementation • 10 Mar 2024 • Shilin Lu, Zilan Wang, Leyang Li, Yanzhu Liu, Adams Wai-Kin Kong
In this paper, we introduce MACE, a finetuning framework for the task of mass concept erasure.
1 code implementation • ICCV 2023 • Shilin Lu, Yanzhu Liu, Adams Wai-Kin Kong
In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for cross-domain image-guided composition.
1 code implementation • ICCV 2023 • Xiaobao Guo, Nithish Muthuchamy Selvaraj, Zitong Yu, Adams Wai-Kin Kong, Bingquan Shen, Alex Kot
Despite this, deception detection research is hindered by the lack of high-quality deception datasets, as well as the difficulties of learning multimodal features effectively.
no code implementations • CVPR 2023 • Fan Wang, Adams Wai-Kin Kong
Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models.
no code implementations • 11 Feb 2023 • Zhaoxu Li, Zitong Yu, Nithish Muthuchamy Selvaraj, Xiaobao Guo, Bingquan Shen, Adams Wai-Kin Kong, Alex Kot
Detecting deception by human behaviors is vital in many fields such as custom security and multimedia anti-fraud.
no code implementations • 9 Nov 2022 • Yew Lee Tan, Ernest Yu Kai Chew, Adams Wai-Kin Kong, Jung-jae Kim, Joo Hwee Lim
To generate the portmanteau feature, a non-linear input pipeline with a block matrix initialization is presented.
no code implementations • 9 Nov 2022 • Yew Lee Tan, Adams Wai-Kin Kong, Jung-jae Kim
PTIE is a transformer model that can process multiple patch resolutions and decode in both the original and reverse character orders.
1 code implementation • 27 Jun 2022 • Zechen Wang, Liangzhen Zheng, Sheng Wang, Mingzhi Lin, Zhihao Wang, Adams Wai-Kin Kong, Yuguang Mu, Yanjie Wei, Weifeng Li
In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF.
2 code implementations • ICLR 2022 • Yi Huang, Adams Wai-Kin Kong
The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community.
no code implementations • 15 May 2022 • Fan Wang, Adams Wai-Kin Kong
In this paper, we first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness.
1 code implementation • 28 May 2019 • Wojciech Michal Matkowski, Krzysztof Matkowski, Adams Wai-Kin Kong, Cory Lloyd Hall
In digital and multimedia forensics, identification of child sexual offenders based on digital evidence images is highly challenging due to the fact that the offender's face or other obvious characteristics such as tattoos are occluded, covered, or not visible at all.