14 papers with code • 2 benchmarks • 7 datasets
Person Search is a task which aims at matching a specific person among a great number of whole scene images.
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates.
Ranked #4 on Person Re-Identification on CUHK03
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #3 on Person Search on CUHK-SYSU
Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions.
Ranked #5 on Text based Person Retrieval on CUHK-PEDES
The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features.
The results demonstrate that deep re-ID systems are vulnerable to our physical attacks.