Matches in SemOpenAlex for { <https://semopenalex.org/work/W4368351340> ?p ?o ?g. }
- W4368351340 endingPage "101816" @default.
- W4368351340 startingPage "101816" @default.
- W4368351340 abstract "RGBT tracking has received more and more attention in recent years, and in this paper, we propose a multi-task auxiliary learning framework for RGBT tracking. Specifically, we simplify the tracking task to an instance classification task and make it the primary task of the framework. We designed three auxiliary tasks and used a hard-parameter sharing approach to jointly train multiple tasks, hoping that the primary task would benefit from them. The three auxiliary tasks are contrastive instance discrimination, one-shot instance segmentation, and instance semantic matching. The contrastive instance discrimination method promotes the classification process of the primary task by constraining the features in the representation space. One-shot instance segmentation trains the network in a weakly supervised way to focus on more fine-grained features. In addition, in order to make the network pay more attention to the invariant features of instance target during tracking, we introduce a semantic matching task to alleviate the model drift problem caused by time change. Based on the results on three RGBT tracking benchmarks, the proposed framework is not inferior to the state-of-the-art trackers." @default.
- W4368351340 created "2023-05-05" @default.
- W4368351340 creator A5042643626 @default.
- W4368351340 creator A5048453574 @default.
- W4368351340 creator A5083897854 @default.
- W4368351340 date "2023-09-01" @default.
- W4368351340 modified "2023-09-27" @default.
- W4368351340 title "Multi-modal multi-task feature fusion for RGBT tracking" @default.
- W4368351340 cites W1536680647 @default.
- W4368351340 cites W1857884451 @default.
- W4368351340 cites W2527415613 @default.
- W4368351340 cites W2746791238 @default.
- W4368351340 cites W2765667535 @default.
- W4368351340 cites W2798441115 @default.
- W4368351340 cites W2886904239 @default.
- W4368351340 cites W2888456413 @default.
- W4368351340 cites W2896228140 @default.
- W4368351340 cites W2962858109 @default.
- W4368351340 cites W2962989965 @default.
- W4368351340 cites W2963150697 @default.
- W4368351340 cites W2963877604 @default.
- W4368351340 cites W2963905288 @default.
- W4368351340 cites W2996575194 @default.
- W4368351340 cites W2997131652 @default.
- W4368351340 cites W2998756268 @default.
- W4368351340 cites W3001584168 @default.
- W4368351340 cites W3002567850 @default.
- W4368351340 cites W3012425959 @default.
- W4368351340 cites W3033502887 @default.
- W4368351340 cites W3034727271 @default.
- W4368351340 cites W3035020406 @default.
- W4368351340 cites W3042609801 @default.
- W4368351340 cites W3099681648 @default.
- W4368351340 cites W3132864630 @default.
- W4368351340 cites W3171106688 @default.
- W4368351340 cites W3173785487 @default.
- W4368351340 cites W3176463841 @default.
- W4368351340 cites W3180169285 @default.
- W4368351340 cites W3183904268 @default.
- W4368351340 cites W4226126595 @default.
- W4368351340 cites W4250482878 @default.
- W4368351340 cites W4312668764 @default.
- W4368351340 cites W4312766345 @default.
- W4368351340 cites W4312821902 @default.
- W4368351340 cites W4313180545 @default.
- W4368351340 cites W4319301146 @default.
- W4368351340 doi "https://doi.org/10.1016/j.inffus.2023.101816" @default.
- W4368351340 hasPublicationYear "2023" @default.
- W4368351340 type Work @default.
- W4368351340 citedByCount "0" @default.
- W4368351340 crossrefType "journal-article" @default.
- W4368351340 hasAuthorship W4368351340A5042643626 @default.
- W4368351340 hasAuthorship W4368351340A5048453574 @default.
- W4368351340 hasAuthorship W4368351340A5083897854 @default.
- W4368351340 hasConcept C105795698 @default.
- W4368351340 hasConcept C111919701 @default.
- W4368351340 hasConcept C119857082 @default.
- W4368351340 hasConcept C120665830 @default.
- W4368351340 hasConcept C121332964 @default.
- W4368351340 hasConcept C138885662 @default.
- W4368351340 hasConcept C153180895 @default.
- W4368351340 hasConcept C154945302 @default.
- W4368351340 hasConcept C162324750 @default.
- W4368351340 hasConcept C165064840 @default.
- W4368351340 hasConcept C185592680 @default.
- W4368351340 hasConcept C187736073 @default.
- W4368351340 hasConcept C188027245 @default.
- W4368351340 hasConcept C192209626 @default.
- W4368351340 hasConcept C2776401178 @default.
- W4368351340 hasConcept C2780451532 @default.
- W4368351340 hasConcept C33923547 @default.
- W4368351340 hasConcept C41008148 @default.
- W4368351340 hasConcept C41895202 @default.
- W4368351340 hasConcept C56461940 @default.
- W4368351340 hasConcept C57501372 @default.
- W4368351340 hasConcept C71139939 @default.
- W4368351340 hasConcept C89600930 @default.
- W4368351340 hasConcept C98045186 @default.
- W4368351340 hasConceptScore W4368351340C105795698 @default.
- W4368351340 hasConceptScore W4368351340C111919701 @default.
- W4368351340 hasConceptScore W4368351340C119857082 @default.
- W4368351340 hasConceptScore W4368351340C120665830 @default.
- W4368351340 hasConceptScore W4368351340C121332964 @default.
- W4368351340 hasConceptScore W4368351340C138885662 @default.
- W4368351340 hasConceptScore W4368351340C153180895 @default.
- W4368351340 hasConceptScore W4368351340C154945302 @default.
- W4368351340 hasConceptScore W4368351340C162324750 @default.
- W4368351340 hasConceptScore W4368351340C165064840 @default.
- W4368351340 hasConceptScore W4368351340C185592680 @default.
- W4368351340 hasConceptScore W4368351340C187736073 @default.
- W4368351340 hasConceptScore W4368351340C188027245 @default.
- W4368351340 hasConceptScore W4368351340C192209626 @default.
- W4368351340 hasConceptScore W4368351340C2776401178 @default.
- W4368351340 hasConceptScore W4368351340C2780451532 @default.
- W4368351340 hasConceptScore W4368351340C33923547 @default.
- W4368351340 hasConceptScore W4368351340C41008148 @default.
- W4368351340 hasConceptScore W4368351340C41895202 @default.
- W4368351340 hasConceptScore W4368351340C56461940 @default.