Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172670194> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3172670194 abstract "Existing deep trackers typically use offline-learned backbone networks for feature extraction across various online tracking tasks. However, for unseen objects, offline-learned representations are still limited due to the lack of adaptation. In this paper, we propose a Meta-Graph Adaptation Network (MGA-Net) to adapt backbones of deep trackers to specific online tracking tasks in a meta-learning fashion. Our MGA-Net is composed of a gradient embedding module (GEM) and a filter adaptation module (FAM). GEM takes gradients as an adaptation signal, and applies graph-message propagation to learn smoothed low-dimensional gradient embeddings. FAM utilizes both the learned gradient embeddings and the target exemplar to adapt the filter weights for the specific tracking task. MGA-Net can be end-to-end trained in an offline meta-learning way, and runs completely feed-forward for testing, thus enabling highly-efficient online tracking. We show that MGA-Net is generic and demonstrate its effectiveness in both template matching and correlation filter tracking frameworks." @default.
- W3172670194 created "2021-06-22" @default.
- W3172670194 creator A5062279616 @default.
- W3172670194 creator A5065680386 @default.
- W3172670194 date "2021-07-05" @default.
- W3172670194 modified "2023-10-18" @default.
- W3172670194 title "Meta-Graph Adaptation for Visual Object Tracking" @default.
- W3172670194 cites W1857884451 @default.
- W3172670194 cites W2089961441 @default.
- W3172670194 cites W2117539524 @default.
- W3172670194 cites W2154889144 @default.
- W3172670194 cites W2158592639 @default.
- W3172670194 cites W2214352687 @default.
- W3172670194 cites W2473868734 @default.
- W3172670194 cites W2557641257 @default.
- W3172670194 cites W2558899534 @default.
- W3172670194 cites W2599547527 @default.
- W3172670194 cites W2740685955 @default.
- W3172670194 cites W2742165450 @default.
- W3172670194 cites W2799058067 @default.
- W3172670194 cites W2894176037 @default.
- W3172670194 cites W2962824803 @default.
- W3172670194 cites W2963227409 @default.
- W3172670194 cites W2963471260 @default.
- W3172670194 cites W2963499285 @default.
- W3172670194 cites W2963534981 @default.
- W3172670194 cites W2964111344 @default.
- W3172670194 cites W2981352030 @default.
- W3172670194 cites W2987460522 @default.
- W3172670194 cites W2989688045 @default.
- W3172670194 doi "https://doi.org/10.1109/icme51207.2021.9428441" @default.
- W3172670194 hasPublicationYear "2021" @default.
- W3172670194 type Work @default.
- W3172670194 sameAs 3172670194 @default.
- W3172670194 citedByCount "2" @default.
- W3172670194 countsByYear W31726701942022 @default.
- W3172670194 countsByYear W31726701942023 @default.
- W3172670194 crossrefType "proceedings-article" @default.
- W3172670194 hasAuthorship W3172670194A5062279616 @default.
- W3172670194 hasAuthorship W3172670194A5065680386 @default.
- W3172670194 hasConcept C106131492 @default.
- W3172670194 hasConcept C119857082 @default.
- W3172670194 hasConcept C120665830 @default.
- W3172670194 hasConcept C121332964 @default.
- W3172670194 hasConcept C132525143 @default.
- W3172670194 hasConcept C139807058 @default.
- W3172670194 hasConcept C153180895 @default.
- W3172670194 hasConcept C154945302 @default.
- W3172670194 hasConcept C15744967 @default.
- W3172670194 hasConcept C19417346 @default.
- W3172670194 hasConcept C202474056 @default.
- W3172670194 hasConcept C2775936607 @default.
- W3172670194 hasConcept C2781238097 @default.
- W3172670194 hasConcept C31972630 @default.
- W3172670194 hasConcept C41008148 @default.
- W3172670194 hasConcept C41608201 @default.
- W3172670194 hasConcept C52622490 @default.
- W3172670194 hasConcept C56461940 @default.
- W3172670194 hasConcept C57501372 @default.
- W3172670194 hasConcept C75564084 @default.
- W3172670194 hasConcept C80444323 @default.
- W3172670194 hasConceptScore W3172670194C106131492 @default.
- W3172670194 hasConceptScore W3172670194C119857082 @default.
- W3172670194 hasConceptScore W3172670194C120665830 @default.
- W3172670194 hasConceptScore W3172670194C121332964 @default.
- W3172670194 hasConceptScore W3172670194C132525143 @default.
- W3172670194 hasConceptScore W3172670194C139807058 @default.
- W3172670194 hasConceptScore W3172670194C153180895 @default.
- W3172670194 hasConceptScore W3172670194C154945302 @default.
- W3172670194 hasConceptScore W3172670194C15744967 @default.
- W3172670194 hasConceptScore W3172670194C19417346 @default.
- W3172670194 hasConceptScore W3172670194C202474056 @default.
- W3172670194 hasConceptScore W3172670194C2775936607 @default.
- W3172670194 hasConceptScore W3172670194C2781238097 @default.
- W3172670194 hasConceptScore W3172670194C31972630 @default.
- W3172670194 hasConceptScore W3172670194C41008148 @default.
- W3172670194 hasConceptScore W3172670194C41608201 @default.
- W3172670194 hasConceptScore W3172670194C52622490 @default.
- W3172670194 hasConceptScore W3172670194C56461940 @default.
- W3172670194 hasConceptScore W3172670194C57501372 @default.
- W3172670194 hasConceptScore W3172670194C75564084 @default.
- W3172670194 hasConceptScore W3172670194C80444323 @default.
- W3172670194 hasLocation W31726701941 @default.
- W3172670194 hasOpenAccess W3172670194 @default.
- W3172670194 hasPrimaryLocation W31726701941 @default.
- W3172670194 hasRelatedWork W1578117154 @default.
- W3172670194 hasRelatedWork W2013820100 @default.
- W3172670194 hasRelatedWork W2274330372 @default.
- W3172670194 hasRelatedWork W2396101943 @default.
- W3172670194 hasRelatedWork W2512938793 @default.
- W3172670194 hasRelatedWork W2583890343 @default.
- W3172670194 hasRelatedWork W2592297120 @default.
- W3172670194 hasRelatedWork W2791920075 @default.
- W3172670194 hasRelatedWork W3036550512 @default.
- W3172670194 hasRelatedWork W4315474202 @default.
- W3172670194 isParatext "false" @default.
- W3172670194 isRetracted "false" @default.
- W3172670194 magId "3172670194" @default.
- W3172670194 workType "article" @default.