HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Nlp Based Person Retrival On Cuhk Pedes

평가 지표

Rank-1
Rank-10
Rank-5
mAP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Rank-1
Rank-10
Rank-5
mAP
Paper TitleRepository
CADA78.3794.5891.5768.87Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval-
APTM---66.91Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
HGAN----Hierarchical Gumbel Attention Network for Text-based Person Search-
VGSG (ViT-Base)---67.91VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search-
MARS---71.71MARS: Paying more attention to visual attributes for text-based person search
PLIP-RN50----PLIP: Language-Image Pre-training for Person Representation Learning
TIPCB----TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search
SRCF----A Simple and Robust Correlation Filtering Method for Text-based Person Search
DSSL----DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
SAF----Learning Semantic-Aligned Feature Representation for Text-based Person Search
NAFS----Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
RaSa---69.38RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search-
RDE---67.56Noisy-Correspondence Learning for Text-to-Image Person Re-identification
TextReID---60.08Text-Based Person Search with Limited Data
SSAN----Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification
Filtering-WoRA(Small)---67.22From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search-
CMPM+CMPC----Deep Cross-Modal Projection Learning for Image-Text Matching-
Dual Path----Dual-Path Convolutional Image-Text Embeddings with Instance Loss
IRRA---66.13Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval-
GLA----Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association-
0 of 25 row(s) selected.