no code implementations • 21 May 2024 • Yi Cheng, Ziwei Xu, Dongyun Lin, Harry Cheng, Yongkang Wong, Ying Sun, Joo Hwee Lim, Mohan Kankanhalli
To address these challenges, we propose a knowledge-enhanced iterative refinement framework for visual content generation.
no code implementations • 30 Apr 2024 • Dongyun Lin, Yi Cheng, Shangbo Mao, Aiyuan Guo, Yiqun Li
Specifically, leveraging the descriptor which is effective for zero-shot inference to guide the tuning of the aggregated descriptor under the few-shot training can significantly improve the few-shot learning efficacy.
no code implementations • 25 Jul 2023 • Yi Cheng, Hehe Fan, Dongyun Lin, Ying Sun, Mohan Kankanhalli, Joo-Hwee Lim
The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions.
no code implementations • 20 Jul 2023 • Dongyun Lin, Yi Cheng, Aiyuan Guo, Shangbo Mao, Yiqun Li
With deep features extracted from point clouds and multi-view images, we design two types of feature aggregation modules, namely the In-Modality Aggregation Module (IMAM) and the Cross-Modality Aggregation Module (CMAM), for effective feature fusion.
no code implementations • 13 Jul 2023 • Yi Cheng, Ziwei Xu, Fen Fang, Dongyun Lin, Hehe Fan, Yongkang Wong, Ying Sun, Mohan Kankanhalli
Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.
no code implementations • 29 Jan 2023 • Yi Cheng, Dongyun Lin, Fen Fang, Hao Xuan Woon, Qianli Xu, Ying Sun
In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022.
no code implementations • 18 Jul 2020 • Dongyun Lin, Yiqun Li, Shudong Xie, Tin Lay Nwe, Sheng Dong
One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images.
no code implementations • 18 Jul 2020 • Dongyun Lin, Yanpeng Cao, Wenbing Zhu, Yiqun Li
In industrial inspection tasks, it is common to capture abundant defect-free image samples but very limited anomalous ones.