Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002488> ?p ?o ?g. }
- W4386002488 endingPage "104797" @default.
- W4386002488 startingPage "104797" @default.
- W4386002488 abstract "Visible-infrared person re-identification (VIPR) is a task of retrieving a specific pedestrian monitored by cameras in different spectra. A dilemma of VIPR is how to reasonably use intra-modal pairs. Fully discarding intra-modal pairs causes a low utilization of training data, while using intra-modal pairs brings a danger of distracting a VIPR model's concentration on handling cross-modal pairs, harming the cross-modal similarity metric learning. For that, a high utilization mismatch amending (HUMA) triplet loss function is proposed for VIPR. The key of HUMA is the multi-modal matching regularization (MMMR), which restricts variations of distance matrices calculated from cross- and intra-modal pairs to cohere cross- and intra-modal similarity metrics, allowing for a high utilization of training data and amending the adverse distractions of intra-modal pairs. In addition, to avoid the risk of harming feature discrimination caused by MMMR preferring coherence in similarity metrics, a novel separated loss function assignment (SLFA) strategy is designed to arrange MMMR well. Experimental results show that the proposed method is superior to state-of-the-art approaches." @default.
- W4386002488 created "2023-08-20" @default.
- W4386002488 creator A5033119978 @default.
- W4386002488 creator A5035422552 @default.
- W4386002488 creator A5042344822 @default.
- W4386002488 creator A5078514263 @default.
- W4386002488 creator A5081086505 @default.
- W4386002488 creator A5081652006 @default.
- W4386002488 creator A5082068608 @default.
- W4386002488 date "2023-10-01" @default.
- W4386002488 modified "2023-10-07" @default.
- W4386002488 title "Visible-infrared person re-identification using high utilization mismatch amending triplet loss" @default.
- W4386002488 cites W2117539524 @default.
- W4386002488 cites W2591488409 @default.
- W4386002488 cites W2596603442 @default.
- W4386002488 cites W2735680049 @default.
- W4386002488 cites W2952870870 @default.
- W4386002488 cites W2963200533 @default.
- W4386002488 cites W2963521811 @default.
- W4386002488 cites W2963597983 @default.
- W4386002488 cites W2970390221 @default.
- W4386002488 cites W2979973052 @default.
- W4386002488 cites W2998633236 @default.
- W4386002488 cites W2998792609 @default.
- W4386002488 cites W3031868989 @default.
- W4386002488 cites W3033235266 @default.
- W4386002488 cites W3035673257 @default.
- W4386002488 cites W3043157863 @default.
- W4386002488 cites W3083688670 @default.
- W4386002488 cites W3094515045 @default.
- W4386002488 cites W3100507239 @default.
- W4386002488 cites W3102911434 @default.
- W4386002488 cites W3105077954 @default.
- W4386002488 cites W3106715802 @default.
- W4386002488 cites W3116221852 @default.
- W4386002488 cites W3120441777 @default.
- W4386002488 cites W3124908517 @default.
- W4386002488 cites W3126608495 @default.
- W4386002488 cites W3128498158 @default.
- W4386002488 cites W3134669182 @default.
- W4386002488 cites W3138044975 @default.
- W4386002488 cites W3155080005 @default.
- W4386002488 cites W3159593776 @default.
- W4386002488 cites W3167748304 @default.
- W4386002488 cites W3168126494 @default.
- W4386002488 cites W3195006847 @default.
- W4386002488 cites W3198713693 @default.
- W4386002488 cites W4200343840 @default.
- W4386002488 cites W4206392385 @default.
- W4386002488 cites W4210341392 @default.
- W4386002488 cites W4309769898 @default.
- W4386002488 cites W3213696333 @default.
- W4386002488 doi "https://doi.org/10.1016/j.imavis.2023.104797" @default.
- W4386002488 hasPublicationYear "2023" @default.
- W4386002488 type Work @default.
- W4386002488 citedByCount "0" @default.
- W4386002488 crossrefType "journal-article" @default.
- W4386002488 hasAuthorship W4386002488A5033119978 @default.
- W4386002488 hasAuthorship W4386002488A5035422552 @default.
- W4386002488 hasAuthorship W4386002488A5042344822 @default.
- W4386002488 hasAuthorship W4386002488A5078514263 @default.
- W4386002488 hasAuthorship W4386002488A5081086505 @default.
- W4386002488 hasAuthorship W4386002488A5081652006 @default.
- W4386002488 hasAuthorship W4386002488A5082068608 @default.
- W4386002488 hasConcept C103278499 @default.
- W4386002488 hasConcept C105795698 @default.
- W4386002488 hasConcept C11413529 @default.
- W4386002488 hasConcept C115961682 @default.
- W4386002488 hasConcept C116834253 @default.
- W4386002488 hasConcept C119857082 @default.
- W4386002488 hasConcept C127413603 @default.
- W4386002488 hasConcept C153180895 @default.
- W4386002488 hasConcept C154945302 @default.
- W4386002488 hasConcept C165064840 @default.
- W4386002488 hasConcept C176217482 @default.
- W4386002488 hasConcept C185592680 @default.
- W4386002488 hasConcept C188027245 @default.
- W4386002488 hasConcept C21547014 @default.
- W4386002488 hasConcept C2776135515 @default.
- W4386002488 hasConcept C33923547 @default.
- W4386002488 hasConcept C41008148 @default.
- W4386002488 hasConcept C59822182 @default.
- W4386002488 hasConcept C71139939 @default.
- W4386002488 hasConcept C86803240 @default.
- W4386002488 hasConceptScore W4386002488C103278499 @default.
- W4386002488 hasConceptScore W4386002488C105795698 @default.
- W4386002488 hasConceptScore W4386002488C11413529 @default.
- W4386002488 hasConceptScore W4386002488C115961682 @default.
- W4386002488 hasConceptScore W4386002488C116834253 @default.
- W4386002488 hasConceptScore W4386002488C119857082 @default.
- W4386002488 hasConceptScore W4386002488C127413603 @default.
- W4386002488 hasConceptScore W4386002488C153180895 @default.
- W4386002488 hasConceptScore W4386002488C154945302 @default.
- W4386002488 hasConceptScore W4386002488C165064840 @default.
- W4386002488 hasConceptScore W4386002488C176217482 @default.
- W4386002488 hasConceptScore W4386002488C185592680 @default.
- W4386002488 hasConceptScore W4386002488C188027245 @default.
- W4386002488 hasConceptScore W4386002488C21547014 @default.