Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Ma, Bingpeng"'
Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this paper, we propose a novel SSL setting, where unlabeled samples are drawn
Externí odkaz:
http://arxiv.org/abs/2405.20596
Autor:
Zhao, Jiahe, Hou, Ruibing, Chang, Hong, Gu, Xinqian, Ma, Bingpeng, Shan, Shiguang, Chen, Xilin
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features. However, we observe that relying solely on clothes-irrel
Externí odkaz:
http://arxiv.org/abs/2404.09507
Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by leveraging experience from \emph{related} training tasks. In this paper, we try to understand FSL by delving into two key questions: (1) How to quantify the relationsh
Externí odkaz:
http://arxiv.org/abs/2403.03535
Autor:
Wu, Ziqiang, Ma, Bingpeng
Text-based person search aims to simultaneously localize and identify the target person based on query text from uncropped scene images, which can be regarded as the unified task of person detection and text-based person retrieval task. In this work,
Externí odkaz:
http://arxiv.org/abs/2312.14834
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI,2023)
Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution, which is prone to overfitting on tail classes and underfitting on hea
Externí odkaz:
http://arxiv.org/abs/2308.13165
Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not well reconstructed as well. Although some efforts have been made to allev
Externí odkaz:
http://arxiv.org/abs/2303.05047
The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works mainly focus on modeling body shape from multi-modality information (e.g.,
Externí odkaz:
http://arxiv.org/abs/2204.06890
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-bac
Externí odkaz:
http://arxiv.org/abs/2203.11991
Publikováno v:
In Pattern Recognition December 2024 156
Autor:
Han, Zhixiong, Ma, Bingpeng
Publikováno v:
In Pattern Recognition June 2024 150