Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks
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 …
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
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 …
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
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 …
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 …
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
Language-image pre-training is an effective technique for learning powerful representations
in general domains. However, when directly turning to person representation learning, these …
in general domains. However, when directly turning to person representation learning, these …
An outlook into the future of egocentric vision
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 …
research in egocentric vision and the ever-anticipated future, where wearable computing …
Identity-seeking self-supervised representation learning for generalizable person re-identification
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 …
representation from large-scale videos without any annotation. Prior DG ReID methods …
Learning to purification for unsupervised person re-identification
Unsupervised person re-identification is a challenging and promising task in computer
vision. Nowadays unsupervised person re-identification methods have achieved great …
vision. Nowadays unsupervised person re-identification methods have achieved great …
An Overview of Text-based Person Search: Recent Advances and Future Directions
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 …
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
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 …
introduce masked image modeling (MIM) as a pre-training approach for this task. Upon …