Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221005406> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4221005406 endingPage "124" @default.
- W4221005406 startingPage "105" @default.
- W4221005406 abstract "Recently, the memory mechanism has been widely implemented in target tracking. However, these trackers hardly balance the stability of long-term memory with the plasticity of short-term memory through an elegant and efficient mechanism. A residual memory inference network (RMIT) is proposed to exploit the history of target states and last visual features. Specifically, RMIT consists of a base layer and a residual memory layer by synergizing short-and long-term memories. The base layer can be regarded as Discriminative Correlation Filter (DCF) reformulation that maintains the short-term memory to accommodate rapid appearance changes. The residual memory layer can extend residual learning from the spatial domain to the Spatio-temporal domain via ConvLSTM to obtain long-term memory of the target appearance. To avoid model degradation due to sample imbalance, we introduce a weighted gradient harmonized loss to improve the discrimination of the tracker. Then, response scores can be served as a basis of the adaptive learning strategy to ensure the reliability of memory updates. The proposed method performs favorably and has been extensively validated on six benchmark datasets, including OTB-50/100, TC-128, UAV-123, and VOT-2016/2018 against several advanced methods." @default.
- W4221005406 created "2022-04-03" @default.
- W4221005406 creator A5005591242 @default.
- W4221005406 creator A5010077240 @default.
- W4221005406 creator A5020559625 @default.
- W4221005406 creator A5030841645 @default.
- W4221005406 creator A5059591925 @default.
- W4221005406 date "2022-06-01" @default.
- W4221005406 modified "2023-09-26" @default.
- W4221005406 title "Residual memory inference network for regression tracking with weighted gradient harmonized loss" @default.
- W4221005406 cites W1915785815 @default.
- W4221005406 cites W2034938692 @default.
- W4221005406 cites W2154889144 @default.
- W4221005406 cites W2158592639 @default.
- W4221005406 cites W2317058546 @default.
- W4221005406 cites W2343187456 @default.
- W4221005406 cites W2518876086 @default.
- W4221005406 cites W2556197365 @default.
- W4221005406 cites W2735270199 @default.
- W4221005406 cites W2740685955 @default.
- W4221005406 cites W2897666265 @default.
- W4221005406 cites W2958731371 @default.
- W4221005406 cites W2962997029 @default.
- W4221005406 cites W2963113370 @default.
- W4221005406 cites W2963471260 @default.
- W4221005406 cites W2964111344 @default.
- W4221005406 cites W2975183808 @default.
- W4221005406 cites W2999346003 @default.
- W4221005406 cites W3009274836 @default.
- W4221005406 cites W3172712741 @default.
- W4221005406 doi "https://doi.org/10.1016/j.ins.2022.03.047" @default.
- W4221005406 hasPublicationYear "2022" @default.
- W4221005406 type Work @default.
- W4221005406 citedByCount "6" @default.
- W4221005406 countsByYear W42210054062022 @default.
- W4221005406 countsByYear W42210054062023 @default.
- W4221005406 crossrefType "journal-article" @default.
- W4221005406 hasAuthorship W4221005406A5005591242 @default.
- W4221005406 hasAuthorship W4221005406A5010077240 @default.
- W4221005406 hasAuthorship W4221005406A5020559625 @default.
- W4221005406 hasAuthorship W4221005406A5030841645 @default.
- W4221005406 hasAuthorship W4221005406A5059591925 @default.
- W4221005406 hasConcept C108583219 @default.
- W4221005406 hasConcept C112972136 @default.
- W4221005406 hasConcept C11413529 @default.
- W4221005406 hasConcept C119857082 @default.
- W4221005406 hasConcept C13280743 @default.
- W4221005406 hasConcept C153180895 @default.
- W4221005406 hasConcept C154945302 @default.
- W4221005406 hasConcept C155512373 @default.
- W4221005406 hasConcept C185798385 @default.
- W4221005406 hasConcept C205649164 @default.
- W4221005406 hasConcept C2776214188 @default.
- W4221005406 hasConcept C41008148 @default.
- W4221005406 hasConcept C97931131 @default.
- W4221005406 hasConceptScore W4221005406C108583219 @default.
- W4221005406 hasConceptScore W4221005406C112972136 @default.
- W4221005406 hasConceptScore W4221005406C11413529 @default.
- W4221005406 hasConceptScore W4221005406C119857082 @default.
- W4221005406 hasConceptScore W4221005406C13280743 @default.
- W4221005406 hasConceptScore W4221005406C153180895 @default.
- W4221005406 hasConceptScore W4221005406C154945302 @default.
- W4221005406 hasConceptScore W4221005406C155512373 @default.
- W4221005406 hasConceptScore W4221005406C185798385 @default.
- W4221005406 hasConceptScore W4221005406C205649164 @default.
- W4221005406 hasConceptScore W4221005406C2776214188 @default.
- W4221005406 hasConceptScore W4221005406C41008148 @default.
- W4221005406 hasConceptScore W4221005406C97931131 @default.
- W4221005406 hasLocation W42210054061 @default.
- W4221005406 hasOpenAccess W4221005406 @default.
- W4221005406 hasPrimaryLocation W42210054061 @default.
- W4221005406 hasRelatedWork W1972656095 @default.
- W4221005406 hasRelatedWork W2024160000 @default.
- W4221005406 hasRelatedWork W2061273563 @default.
- W4221005406 hasRelatedWork W2285052147 @default.
- W4221005406 hasRelatedWork W2729514902 @default.
- W4221005406 hasRelatedWork W2743258233 @default.
- W4221005406 hasRelatedWork W2773500201 @default.
- W4221005406 hasRelatedWork W2998168123 @default.
- W4221005406 hasRelatedWork W4287995534 @default.
- W4221005406 hasRelatedWork W4380075502 @default.
- W4221005406 hasVolume "597" @default.
- W4221005406 isParatext "false" @default.
- W4221005406 isRetracted "false" @default.
- W4221005406 workType "article" @default.