activity
20172024
most citedDeep Learning for Person Re-identification: A Survey and Outlook

119 citations · 390 across the 17 of their papers we have counts for

collaborators
Showing 2023Show all

6 papers · 1 filter

cs.CV2023

Rotation Invariant Transformer for Recognizing Object in UAVs

Shuoyi Chen, Mang Ye, Bo Du

Recognizing a target of interest from the UAVs is much more challenging than the existing object re-identification tasks across multiple city cameras. The images taken by the UAVs…

cs.LG2023★ 5 cited

Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning

Wenke Huang, Mang Ye, Zekun Shi +1

Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data. Model heteroge…

cs.CV2023★ 1 cited

An Empirical Study of CLIP for Text-based Person Search

Min Cao, Yang Bai, Ziyin Zeng +2

Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large c…

cs.LG2023★ 19 cited

Heterogeneous Federated Learning: State-of-the-art and Research Challenges

Mang Ye, Xiuwen Fang, Bo Du +2

Federated learning (FL) has drawn increasing attention owing to its potential use in large-scale industrial applications. Existing federated learning works mainly focus on model ho…

cs.CV2023★ 21 cited

Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution

Wuxuan Shi, Mang Ye, Bo Du

Color-guided depth super-resolution (DSR) is an encouraging paradigm that enhances a low-resolution (LR) depth map guided by an extra high-resolution (HR) RGB image from the same s…

cs.CV2023★ 15 cited

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Ding Jiang, Mang Ye

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual mo…