Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks

W Chen, X Xu, J Jia, H Luo, Y Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Human-centric visual tasks have attracted increasing research attention due to their
widespread applications. In this paper, we aim to learn a general human representation from …

Combating noisy labels with sample selection by mining high-discrepancy examples

X **a, B Han, Y Zhan, J Yu, M Gong… - Proceedings of the …, 2023 - openaccess.thecvf.com
The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

Unified pre-training with pseudo texts for text-to-image person re-identification

Z Shao, X Zhang, C Ding, J Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
The pre-training task is indispensable for the text-to-image person re-identification (T2I-
ReID) task. However, there are two underlying inconsistencies between these two tasks that …

Adaptive sparse pairwise loss for object re-identification

X Zhou, Y Zhong, Z Cheng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Object re-identification (ReID) aims to find instances with the same identity as the given
probe from a large gallery. Pairwise losses play an important role in training a strong ReID …

Plip: Language-image pre-training for person representation learning

J Zuo, J Hong, F Zhang, C Yu, H Zhou, C Gao… - arxiv preprint arxiv …, 2023 - arxiv.org
Language-image pre-training is an effective technique for learning powerful representations
in general domains. However, when directly turning to person representation learning, these …

An outlook into the future of egocentric vision

C Plizzari, G Goletto, A Furnari, S Bansal… - International Journal of …, 2024 - Springer
What will the future be? We wonder! In this survey, we explore the gap between current
research in egocentric vision and the ever-anticipated future, where wearable computing …

Identity-seeking self-supervised representation learning for generalizable person re-identification

Z Dou, Z Wang, Y Li, S Wang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper aims to learn a domain-generalizable (DG) person re-identification (ReID)
representation from large-scale videos without any annotation. Prior DG ReID methods …

Learning to purification for unsupervised person re-identification

L Lan, X Teng, J Zhang, X Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Unsupervised person re-identification is a challenging and promising task in computer
vision. Nowadays unsupervised person re-identification methods have achieved great …

An Overview of Text-based Person Search: Recent Advances and Future Directions

K Niu, Y Liu, Y Long, Y Huang, L Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Due to the practical significance in smart video surveillance systems, Text-Based Person
Search (TBPS) has been one of the research hotspots recently, which refers to searching for …

Hap: Structure-aware masked image modeling for human-centric perception

J Yuan, X Zhang, H Zhou, J Wang… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Model pre-training is essential in human-centric perception. In this paper, we first
introduce masked image modeling (MIM) as a pre-training approach for this task. Upon …