FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015686580> ?p ?o ?g. }

• W3015686580 endingPage "5556" @default.
• W3015686580 startingPage "5542" @default.
• W3015686580 abstract "Description-based person re-identification (Re-id) is an important task in video surveillance that requires discriminative cross-modal representations to distinguish different people. It is difficult to directly measure the similarity between images and descriptions due to the modality heterogeneity (the cross-modal problem). And all samples belonging to a single category (the fine-grained problem) makes this task even harder than the conventional image-description matching task. In this paper, we propose a Multi-granularity Image-text Alignments (MIA) model to alleviate the cross-modal fine-grained problem for better similarity evaluation in description-based person Re-id. Specifically, three different granularities, i.e., global-global, global-local and local-local alignments are carried out hierarchically. Firstly, the global-global alignment in the Global Contrast (GC) module is for matching the global contexts of images and descriptions. Secondly, the global-local alignment employs the potential relations between local components and global contexts to highlight the distinguishable components while eliminating the uninvolved ones adaptively in the Relation-guided Global-local Alignment (RGA) module. Thirdly, as for the local-local alignment, we match visual human parts with noun phrases in the Bi-directional Fine-grained Matching (BFM) module. The whole network combining multiple granularities can be end-to-end trained without complex pre-processing. To address the difficulties in training the combination of multiple granularities, an effective step training strategy is proposed to train these granularities step-by-step. Extensive experiments and analysis have shown that our method obtains the state-of-the-art performance on the CUHK-PEDES dataset and outperforms the previous methods by a significant margin." @default.
• W3015686580 created "2020-04-17" @default.
• W3015686580 creator A5008455605 @default.
• W3015686580 creator A5022374886 @default.
• W3015686580 creator A5086664647 @default.
• W3015686580 creator A5087818121 @default.
• W3015686580 date "2020-01-01" @default.
• W3015686580 modified "2023-10-17" @default.
• W3015686580 title "Improving Description-Based Person Re-Identification by Multi-Granularity Image-Text Alignments" @default.
• W3015686580 cites W1895577753 @default.
• W3015686580 cites W1931639407 @default.
• W3015686580 cites W1982925187 @default.
• W3015686580 cites W2004284939 @default.
• W3015686580 cites W2048820076 @default.
• W3015686580 cites W2114701396 @default.
• W3015686580 cites W2117539524 @default.
• W3015686580 cites W2154642173 @default.
• W3015686580 cites W2194775991 @default.
• W3015686580 cites W2398118205 @default.
• W3015686580 cites W2467139031 @default.
• W3015686580 cites W2481240925 @default.
• W3015686580 cites W2546696630 @default.
• W3015686580 cites W2552579943 @default.
• W3015686580 cites W2563399268 @default.
• W3015686580 cites W2575842049 @default.
• W3015686580 cites W2591669147 @default.
• W3015686580 cites W2615416569 @default.
• W3015686580 cites W2724213014 @default.
• W3015686580 cites W2738760914 @default.
• W3015686580 cites W2745461083 @default.
• W3015686580 cites W2751525844 @default.
• W3015686580 cites W2798429327 @default.
• W3015686580 cites W2798775284 @default.
• W3015686580 cites W2801814609 @default.
• W3015686580 cites W2885709146 @default.
• W3015686580 cites W2894786240 @default.
• W3015686580 cites W2962964995 @default.
• W3015686580 cites W2963084599 @default.
• W3015686580 cites W2963438548 @default.
• W3015686580 cites W2963449390 @default.
• W3015686580 cites W2963637710 @default.
• W3015686580 cites W2963656855 @default.
• W3015686580 cites W2963686907 @default.
• W3015686580 cites W2963882743 @default.
• W3015686580 cites W2964120214 @default.
• W3015686580 cites W2964199361 @default.
• W3015686580 cites W2964304299 @default.
• W3015686580 cites W2964345214 @default.
• W3015686580 cites W3099899804 @default.
• W3015686580 cites W3100506510 @default.
• W3015686580 cites W4245267204 @default.
• W3015686580 doi "https://doi.org/10.1109/tip.2020.2984883" @default.
• W3015686580 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32275593" @default.
• W3015686580 hasPublicationYear "2020" @default.
• W3015686580 type Work @default.
• W3015686580 sameAs 3015686580 @default.
• W3015686580 citedByCount "63" @default.
• W3015686580 countsByYear W30156865802019 @default.
• W3015686580 countsByYear W30156865802020 @default.
• W3015686580 countsByYear W30156865802021 @default.
• W3015686580 countsByYear W30156865802022 @default.
• W3015686580 countsByYear W30156865802023 @default.
• W3015686580 crossrefType "journal-article" @default.
• W3015686580 hasAuthorship W3015686580A5008455605 @default.
• W3015686580 hasAuthorship W3015686580A5022374886 @default.
• W3015686580 hasAuthorship W3015686580A5086664647 @default.
• W3015686580 hasAuthorship W3015686580A5087818121 @default.
• W3015686580 hasBestOaLocation W30156865802 @default.
• W3015686580 hasConcept C103278499 @default.
• W3015686580 hasConcept C104317684 @default.
• W3015686580 hasConcept C105795698 @default.
• W3015686580 hasConcept C111919701 @default.
• W3015686580 hasConcept C115961682 @default.
• W3015686580 hasConcept C116834253 @default.
• W3015686580 hasConcept C153180895 @default.
• W3015686580 hasConcept C154945302 @default.
• W3015686580 hasConcept C162324750 @default.
• W3015686580 hasConcept C165064840 @default.
• W3015686580 hasConcept C167625842 @default.
• W3015686580 hasConcept C177774035 @default.
• W3015686580 hasConcept C185592680 @default.
• W3015686580 hasConcept C187736073 @default.
• W3015686580 hasConcept C188027245 @default.
• W3015686580 hasConcept C2780226545 @default.
• W3015686580 hasConcept C2780451532 @default.
• W3015686580 hasConcept C33923547 @default.
• W3015686580 hasConcept C41008148 @default.
• W3015686580 hasConcept C45484198 @default.
• W3015686580 hasConcept C55493867 @default.
• W3015686580 hasConcept C59822182 @default.
• W3015686580 hasConcept C71139939 @default.
• W3015686580 hasConcept C72802188 @default.
• W3015686580 hasConcept C86803240 @default.
• W3015686580 hasConcept C97931131 @default.
• W3015686580 hasConceptScore W3015686580C103278499 @default.
• W3015686580 hasConceptScore W3015686580C104317684 @default.
• W3015686580 hasConceptScore W3015686580C105795698 @default.
• W3015686580 hasConceptScore W3015686580C111919701 @default.

• next