FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384472182> ?p ?o ?g. }

• W4384472182 endingPage "106761" @default.
• W4384472182 startingPage "106761" @default.
• W4384472182 abstract "Person re-identification identifies pedestrians by analyzing image information from surveillance videos. However, it faces challenges like occlusion, changing lighting, and costly annotation. Thus, it is often performed in a few-shot environment with limited images. In response to the problem of insufficient available pedestrian images in person re-identification, a few-shot person re-identification method based on feature set augmentation and metric fusion is proposed. In this work, firstly, a feature augmentation method is introduced into the feature embedding module. This method introduces multi-head self-attention in different feature extraction layers and spatial attention in feature fusion of different feature extraction layers, which can extract more diverse and discriminative pedestrian features. Secondly, a dual metric method combining Euclidean and cosine distance is proposed in the metric module to comprehensively measure the absolute spatial distance and directional difference of pedestrian features. In this way, the reliability of pedestrian similarity measurement is improved. Then, pedestrian feature similarity scores are obtained separately using the dual metric and relation metric methods. Finally, the combined metric score is obtained by weighted fusion, and the combined metric score is used to construct the joint loss to realize the overall optimization and training of the network. Experimental results on three small datasets, Market-mini, Duke-mini, and MSMT17-mini, show that the proposed method significantly improves recognition performance compared to other few-shot learning algorithms. Specifically, in scenarios 5-way 1-shot and 5-way 5-shot, the average recognition accuracies are 92.54% and 96.99%, 87.93% and 96.08%, and 71.68% and 84.51%, respectively." @default.
• W4384472182 created "2023-07-17" @default.
• W4384472182 creator A5001937247 @default.
• W4384472182 creator A5006056360 @default.
• W4384472182 creator A5023674155 @default.
• W4384472182 creator A5036700596 @default.
• W4384472182 creator A5080609124 @default.
• W4384472182 date "2023-10-01" @default.
• W4384472182 modified "2023-10-12" @default.
• W4384472182 title "Few-shot person re-identification based on Feature Set Augmentation and Metric Fusion" @default.
• W4384472182 cites W1973207880 @default.
• W4384472182 cites W2553179860 @default.
• W4384472182 cites W2905292968 @default.
• W4384472182 cites W2913231171 @default.
• W4384472182 cites W2947319827 @default.
• W4384472182 cites W2949879676 @default.
• W4384472182 cites W2953214814 @default.
• W4384472182 cites W2962799101 @default.
• W4384472182 cites W2963845150 @default.
• W4384472182 cites W2964105864 @default.
• W4384472182 cites W3009761962 @default.
• W4384472182 cites W3107763055 @default.
• W4384472182 cites W3163106894 @default.
• W4384472182 cites W3176341011 @default.
• W4384472182 cites W4285162920 @default.
• W4384472182 cites W4295677973 @default.
• W4384472182 cites W4312500832 @default.
• W4384472182 cites W4312935555 @default.
• W4384472182 cites W4313010934 @default.
• W4384472182 cites W4361299603 @default.
• W4384472182 cites W4362519925 @default.
• W4384472182 cites W4367841023 @default.
• W4384472182 cites W4376272248 @default.
• W4384472182 cites W4381517675 @default.
• W4384472182 doi "https://doi.org/10.1016/j.engappai.2023.106761" @default.
• W4384472182 hasPublicationYear "2023" @default.
• W4384472182 type Work @default.
• W4384472182 citedByCount "0" @default.
• W4384472182 crossrefType "journal-article" @default.
• W4384472182 hasAuthorship W4384472182A5001937247 @default.
• W4384472182 hasAuthorship W4384472182A5006056360 @default.
• W4384472182 hasAuthorship W4384472182A5023674155 @default.
• W4384472182 hasAuthorship W4384472182A5036700596 @default.
• W4384472182 hasAuthorship W4384472182A5080609124 @default.
• W4384472182 hasConcept C103278499 @default.
• W4384472182 hasConcept C115961682 @default.
• W4384472182 hasConcept C116834253 @default.
• W4384472182 hasConcept C120174047 @default.
• W4384472182 hasConcept C127413603 @default.
• W4384472182 hasConcept C138885662 @default.
• W4384472182 hasConcept C153180895 @default.
• W4384472182 hasConcept C154945302 @default.
• W4384472182 hasConcept C162324750 @default.
• W4384472182 hasConcept C176217482 @default.
• W4384472182 hasConcept C177264268 @default.
• W4384472182 hasConcept C199360897 @default.
• W4384472182 hasConcept C21547014 @default.
• W4384472182 hasConcept C22212356 @default.
• W4384472182 hasConcept C2776401178 @default.
• W4384472182 hasConcept C2777113093 @default.
• W4384472182 hasConcept C2780156472 @default.
• W4384472182 hasConcept C2780762811 @default.
• W4384472182 hasConcept C31972630 @default.
• W4384472182 hasConcept C41008148 @default.
• W4384472182 hasConcept C41895202 @default.
• W4384472182 hasConcept C52622490 @default.
• W4384472182 hasConcept C59822182 @default.
• W4384472182 hasConcept C86803240 @default.
• W4384472182 hasConcept C97931131 @default.
• W4384472182 hasConceptScore W4384472182C103278499 @default.
• W4384472182 hasConceptScore W4384472182C115961682 @default.
• W4384472182 hasConceptScore W4384472182C116834253 @default.
• W4384472182 hasConceptScore W4384472182C120174047 @default.
• W4384472182 hasConceptScore W4384472182C127413603 @default.
• W4384472182 hasConceptScore W4384472182C138885662 @default.
• W4384472182 hasConceptScore W4384472182C153180895 @default.
• W4384472182 hasConceptScore W4384472182C154945302 @default.
• W4384472182 hasConceptScore W4384472182C162324750 @default.
• W4384472182 hasConceptScore W4384472182C176217482 @default.
• W4384472182 hasConceptScore W4384472182C177264268 @default.
• W4384472182 hasConceptScore W4384472182C199360897 @default.
• W4384472182 hasConceptScore W4384472182C21547014 @default.
• W4384472182 hasConceptScore W4384472182C22212356 @default.
• W4384472182 hasConceptScore W4384472182C2776401178 @default.
• W4384472182 hasConceptScore W4384472182C2777113093 @default.
• W4384472182 hasConceptScore W4384472182C2780156472 @default.
• W4384472182 hasConceptScore W4384472182C2780762811 @default.
• W4384472182 hasConceptScore W4384472182C31972630 @default.
• W4384472182 hasConceptScore W4384472182C41008148 @default.
• W4384472182 hasConceptScore W4384472182C41895202 @default.
• W4384472182 hasConceptScore W4384472182C52622490 @default.
• W4384472182 hasConceptScore W4384472182C59822182 @default.
• W4384472182 hasConceptScore W4384472182C86803240 @default.
• W4384472182 hasConceptScore W4384472182C97931131 @default.
• W4384472182 hasFunder F4320321001 @default.
• W4384472182 hasFunder F4320324174 @default.
• W4384472182 hasLocation W43844721821 @default.
• W4384472182 hasOpenAccess W4384472182 @default.

• next