no code implementations • 19 Sep 2024 • Chenyu Wang, Shuo Yan, Yixuan Chen, Yujiang Wang, Mingzhi Dong, Xiaochen Yang, Dongsheng Li, Robert P. Dick, Qin Lv, Fan Yang, Tun Lu, Ning Gu, Li Shang
Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames.
no code implementations • NeurIPS 2023 • Yubin Shi, Yixuan Chen, Mingzhi Dong, Xiaochen Yang, Dongsheng Li, Yujiang Wang, Robert P. Dick, Qin Lv, Yingying Zhao, Fan Yang, Tun Lu, Ning Gu, Li Shang
To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$.
no code implementations • 5 May 2023 • Yujiang Wang, Anshul Thakur, Mingzhi Dong, Pingchuan Ma, Stavros Petridis, Li Shang, Tingting Zhu, David A. Clifton
The prevalence of artificial intelligence (AI) has envisioned an era of healthcare democratisation that promises every stakeholder a new and better way of life.
no code implementations • 24 Mar 2022 • Yujiang Wang, Mingzhi Dong, Jie Shen, Yiming Luo, Yiming Lin, Pingchuan Ma, Stavros Petridis, Maja Pantic
We also investigate face clustering in egocentric videos, a fast-emerging field that has not been studied yet in works related to face clustering.
Ranked #1 on Face Clustering on EasyCom
1 code implementation • 24 Jan 2022 • Yingying Zhao, Yuhu Chang, Yutian Lu, Yujiang Wang, Mingzhi Dong, Qin Lv, Robert P. Dick, Fan Yang, Tun Lu, Ning Gu, Li Shang
Experimental studies with 20 participants demonstrate that, thanks to the emotionship awareness, EMOShip not only achieves superior emotion recognition accuracy over existing methods (80. 2% vs. 69. 4%), but also provides a valuable understanding of the cause of emotions.
no code implementations • ICLR 2022 • Yixuan Chen, Yubin Shi, Dongsheng Li, Yujiang Wang, Mingzhi Dong, Yingying Zhao, Robert Dick, Qin Lv, Fan Yang, Li Shang
The feature space of deep models is inherently compositional.
no code implementations • 3 May 2021 • Yuhu Chang, Yingying Zhao, Mingzhi Dong, Yujiang Wang, Yutian Lu, Qin Lv, Robert P. Dick, Tun Lu, Ning Gu, Li Shang
MemX captures human visual attention on the fly, analyzes the salient visual content, and records moments of personal interest in the form of compact video snippets.
no code implementations • 9 Apr 2021 • Yingying Zhao, Mingzhi Dong, Yujiang Wang, Da Feng, Qin Lv, Robert P. Dick, Dongsheng Li, Tun Lu, Ning Gu, Li Shang
By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency.
1 code implementation • NeurIPS 2020 • Mingzhi Dong, Xiaochen Yang, Rui Zhu, Yujiang Wang, Jing-Hao Xue
Metric learning aims to learn a distance measure that can benefit distance-based methods such as the nearest neighbour (NN) classifier.
1 code implementation • 10 Jun 2020 • Xiaochen Yang, Yiwen Guo, Mingzhi Dong, Jing-Hao Xue
Many existing methods consider maximizing or at least constraining a distance margin in the feature space that separates similar and dissimilar pairs of instances to guarantee their generalization ability.
1 code implementation • 5 Jun 2020 • Yujiang Wang, Mingzhi Dong, Jie Shen, Yiming Lin, Maja Pantic
Introducing LI mechanisms improves the convolutional filter's sensitivity to semantic object boundaries.
no code implementations • CVPR 2020 • Yujiang Wang, Mingzhi Dong, Jie Shen, Yang Wu, Shiyang Cheng, Maja Pantic
To the best of our knowledge, this is the first work to use reinforcement learning for online key-frame decision in dynamic video segmentation, and also the first work on its application on face videos.
no code implementations • ICLR 2018 • Kunkun Pang, Mingzhi Dong, Yang Wu, Timothy Hospedales
In contrast to this body of research, we propose to treat active learning algorithm design as a meta-learning problem and learn the best criterion from data.
no code implementations • 9 Feb 2018 • Mingzhi Dong, Xiaochen Yang, Yang Wu, Jing-Hao Xue
In this paper, we propose the Lipschitz margin ratio and a new metric learning framework for classification through maximizing the ratio.
no code implementations • 9 Feb 2018 • Mingzhi Dong, Yujiang Wang, Xiaochen Yang, Jing-Hao Xue
The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data.