Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Duan, Lingyu"'
The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse
Externí odkaz:
http://arxiv.org/abs/2410.20197
Publikováno v:
in Proceedings of the 31st ACM International Conference on Multimedia, pp. 1431-1442, 2023
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for both human
Externí odkaz:
http://arxiv.org/abs/2410.06149
Publikováno v:
MICCAI 2024
Electron microscopy (EM) imaging offers unparalleled resolution for analyzing neural tissues, crucial for uncovering the intricacies of synaptic connections and neural processes fundamental to understanding behavioral mechanisms. Recently, the founda
Externí odkaz:
http://arxiv.org/abs/2408.14114
Segmentation of surgical instruments is crucial for enhancing surgeon performance and ensuring patient safety. Conventional techniques such as binary, semantic, and instance segmentation share a common drawback: they do not accommodate the parts of i
Externí odkaz:
http://arxiv.org/abs/2408.01067
In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the system suspended when deploying new models. Therefore, backward-compat
Externí odkaz:
http://arxiv.org/abs/2108.03372
Autor:
Lin, Weiyao, He, Xiaoyi, Dai, Wenrui, See, John, Shinde, Tushar, Xiong, Hongkai, Duan, Lingyu
Publikováno v:
IEEE MultiMedia, vol. 27, no. 3, pp. 12-22, 2020
Feature coding has been recently considered to facilitate intelligent video analysis for urban computing. Instead of raw videos, extracted features in the front-end are encoded and transmitted to the back-end for further processing. In this article,
Externí odkaz:
http://arxiv.org/abs/2009.04646
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain. However, mos
Externí odkaz:
http://arxiv.org/abs/2007.09222
Fashion attribute classification is of great importance to many high-level tasks such as fashion item search, fashion trend analysis, fashion recommendation, etc. The task is challenging due to the extremely imbalanced data distribution, particularly
Externí odkaz:
http://arxiv.org/abs/1907.10839
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to hi
Externí odkaz:
http://arxiv.org/abs/1904.11245
Autor:
Chen, Kean, Li, Jianguo, Lin, Weiyao, See, John, Wang, Ji, Duan, Lingyu, Chen, Zhibo, He, Changwei, Zou, Junni
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alle
Externí odkaz:
http://arxiv.org/abs/1904.06373