Search Results for author: Jiahuan Zhou

Found 14 papers, 2 papers with code

Make Lossy Compression Meaningful for Low-Light Images

1 code implementation24 May 2023 Shilv Cai, Liqun Chen, Sheng Zhong, Luxin Yan, Jiahuan Zhou, Xu Zou

Experimental results show that our proposed joint solution achieves a significant improvement over different combinations of existing state-of-the-art sequential ``Compress before Enhance'' or ``Enhance before Compress'' solutions for low-light images, which would make lossy low-light image compression more meaningful.

Image Compression Low-Light Image Enhancement

Learning Reconstruction-Based Remote Gaze Estimation

no code implementations CVPR 2016 Pei Yu, Jiahuan Zhou, Ying Wu

A common treatment is to use the same local reconstruction in the two spaces, i. e., the reconstruction weights in the appearance space are transferred to the gaze space for gaze reconstruction.

Gaze Estimation

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification

no code implementations ICCV 2017 Jiahuan Zhou, Pei Yu, Wei Tang, Ying Wu

In contrast to these methods, this paper advocates a different paradigm: part of the learning can be performed online but with nominal costs, so as to achieve online metric adaptation for different input probes.

Metric Learning Person Re-Identification

Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification

no code implementations CVPR 2020 Jiahuan Zhou, Bing Su, Ying Wu

Person Re-IDentification (P-RID), as an instance-level recognition problem, still remains challenging in computer vision community.

Person Re-Identification

Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection

no code implementations11 Aug 2020 Gengxing Wang, Jiahuan Zhou, Ying Wu

Recent deep learning based video synthesis approaches, in particular with applications that can forge identities such as "DeepFake", have raised great security concerns.

Anomaly Detection Data Compression +1

Unsupervised Embedding Learning from Uncertainty Momentum Modeling

no code implementations19 Jul 2021 Jiahuan Zhou, Yansong Tang, Bing Su, Ying Wu

We justify that the performance limitation is caused by the gradient vanishing on these sample outliers.

Conscious Inference for Object Detection

no code implementations27 Sep 2018 Jiahuan Zhou, Nikolaos Karianakis, Ying Wu, Gang Hua

Current Convolutional Neural Network (CNN)-based object detection models adopt strictly feedforward inference to predict the final detection results.

6D Pose Estimation using RGB Object +2

Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification

no code implementations7 Oct 2022 Zeqi Chen, Zhichao Cui, Chi Zhang, Jiahuan Zhou, Yuehu Liu

However, training two networks with a set of noisy pseudo labels reduces the complementarity of the two networks and results in label noise accumulation.

Clustering Pseudo Label +1

ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation

no code implementations29 Mar 2023 Wei Wei, Jiahuan Zhou, Hongze Li, Ying Wu

Thus, the critical data uncertainty and model uncertainty caused by noisy data can be readily quantified for improving model robustness.

A Grammatical Compositional Model for Video Action Detection

no code implementations4 Oct 2023 Zhijun Zhang, Xu Zou, Jiahuan Zhou, Sheng Zhong, Ying Wu

Analysis of human actions in videos demands understanding complex human dynamics, as well as the interaction between actors and context.

Action Detection Human Dynamics

Cannot find the paper you are looking for? You can Submit a new open access paper.