Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214759957> ?p ?o ?g. }
- W4214759957 abstract "In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects directly. The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing, thus largely simplifying existing tracking pipelines. The proposed tracker achieves state-of-the-art performance on multiple challenging short-term and long-term benchmarks, while running at real-time speed, being 6× faster than Siam R-CNN [54]. Code and models are open-sourced at https://github.com/researchmm/Stark." @default.
- W4214759957 created "2022-03-02" @default.
- W4214759957 creator A5003702273 @default.
- W4214759957 creator A5006986293 @default.
- W4214759957 creator A5031978434 @default.
- W4214759957 creator A5072029041 @default.
- W4214759957 creator A5080495327 @default.
- W4214759957 date "2021-10-01" @default.
- W4214759957 modified "2023-10-17" @default.
- W4214759957 title "Learning Spatio-Temporal Transformer for Visual Tracking" @default.
- W4214759957 cites W1857884451 @default.
- W4214759957 cites W1915785815 @default.
- W4214759957 cites W2139047213 @default.
- W4214759957 cites W2158592639 @default.
- W4214759957 cites W2194775991 @default.
- W4214759957 cites W2222512263 @default.
- W4214759957 cites W2557641257 @default.
- W4214759957 cites W2558899534 @default.
- W4214759957 cites W2605173812 @default.
- W4214759957 cites W2767302379 @default.
- W4214759957 cites W2799058067 @default.
- W4214759957 cites W2888456413 @default.
- W4214759957 cites W2891033863 @default.
- W4214759957 cites W2947624463 @default.
- W4214759957 cites W2962766617 @default.
- W4214759957 cites W2962824803 @default.
- W4214759957 cites W2963227409 @default.
- W4214759957 cites W2963471260 @default.
- W4214759957 cites W2963534981 @default.
- W4214759957 cites W2964423614 @default.
- W4214759957 cites W2966759264 @default.
- W4214759957 cites W2985509612 @default.
- W4214759957 cites W2987460522 @default.
- W4214759957 cites W2989688045 @default.
- W4214759957 cites W2990205821 @default.
- W4214759957 cites W2997896013 @default.
- W4214759957 cites W2998027361 @default.
- W4214759957 cites W2998434318 @default.
- W4214759957 cites W3001584168 @default.
- W4214759957 cites W3034297219 @default.
- W4214759957 cites W3034617042 @default.
- W4214759957 cites W3035211844 @default.
- W4214759957 cites W3035257046 @default.
- W4214759957 cites W3035453691 @default.
- W4214759957 cites W3035473155 @default.
- W4214759957 cites W3035511673 @default.
- W4214759957 cites W3035571898 @default.
- W4214759957 cites W3035672751 @default.
- W4214759957 cites W3035725297 @default.
- W4214759957 cites W3104158266 @default.
- W4214759957 cites W3173344965 @default.
- W4214759957 cites W3214586131 @default.
- W4214759957 doi "https://doi.org/10.1109/iccv48922.2021.01028" @default.
- W4214759957 hasPublicationYear "2021" @default.
- W4214759957 type Work @default.
- W4214759957 citedByCount "227" @default.
- W4214759957 countsByYear W42147599572021 @default.
- W4214759957 countsByYear W42147599572022 @default.
- W4214759957 countsByYear W42147599572023 @default.
- W4214759957 crossrefType "proceedings-article" @default.
- W4214759957 hasAuthorship W4214759957A5003702273 @default.
- W4214759957 hasAuthorship W4214759957A5006986293 @default.
- W4214759957 hasAuthorship W4214759957A5031978434 @default.
- W4214759957 hasAuthorship W4214759957A5072029041 @default.
- W4214759957 hasAuthorship W4214759957A5080495327 @default.
- W4214759957 hasBestOaLocation W42147599572 @default.
- W4214759957 hasConcept C111919701 @default.
- W4214759957 hasConcept C115961682 @default.
- W4214759957 hasConcept C118505674 @default.
- W4214759957 hasConcept C121332964 @default.
- W4214759957 hasConcept C147037132 @default.
- W4214759957 hasConcept C153180895 @default.
- W4214759957 hasConcept C154945302 @default.
- W4214759957 hasConcept C165801399 @default.
- W4214759957 hasConcept C2780008327 @default.
- W4214759957 hasConcept C31972630 @default.
- W4214759957 hasConcept C41008148 @default.
- W4214759957 hasConcept C41608201 @default.
- W4214759957 hasConcept C62520636 @default.
- W4214759957 hasConcept C66322947 @default.
- W4214759957 hasConcept C81363708 @default.
- W4214759957 hasConceptScore W4214759957C111919701 @default.
- W4214759957 hasConceptScore W4214759957C115961682 @default.
- W4214759957 hasConceptScore W4214759957C118505674 @default.
- W4214759957 hasConceptScore W4214759957C121332964 @default.
- W4214759957 hasConceptScore W4214759957C147037132 @default.
- W4214759957 hasConceptScore W4214759957C153180895 @default.
- W4214759957 hasConceptScore W4214759957C154945302 @default.
- W4214759957 hasConceptScore W4214759957C165801399 @default.
- W4214759957 hasConceptScore W4214759957C2780008327 @default.
- W4214759957 hasConceptScore W4214759957C31972630 @default.
- W4214759957 hasConceptScore W4214759957C41008148 @default.
- W4214759957 hasConceptScore W4214759957C41608201 @default.
- W4214759957 hasConceptScore W4214759957C62520636 @default.
- W4214759957 hasConceptScore W4214759957C66322947 @default.
- W4214759957 hasConceptScore W4214759957C81363708 @default.
- W4214759957 hasFunder F4320321001 @default.
- W4214759957 hasLocation W42147599571 @default.
- W4214759957 hasLocation W42147599572 @default.
- W4214759957 hasOpenAccess W4214759957 @default.