Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226261750> ?p ?o ?g. }
- W4226261750 endingPage "6199" @default.
- W4226261750 startingPage "6186" @default.
- W4226261750 abstract "With the widespread use of deep learning in single object tracking task, mainstream tracking algorithms treat tracking as a combined classification and regression problem. Classification aims at locating an arbitrary target, and regression aims at estimating the corresponding bounding box. In this paper, we focus on regression and propose a novel box estimation network, which consists of a transformer encoder target pyramid guide (TPG) and transformer decoder target pyramid spread (TPS). Specifically, the transformer encoder TPG is designed to generate fine-grained prior knowledge with explicit representation for template targets. In contrast to the raw transformer encoder, we capture the visual dependence through local-global self-attention and deem the multi-scale target regions as the “local” region. Using this fine-grained prior knowledge, we design the transformer decoder TPS to spread it to the subsequent search regions with high affinity to accurately estimate the bounding boxes. Considering that self-attention fails to model information interaction across channels between the template target and search regions, we develop a channel-wise cross-attention block within the TPS as compensation. Extensive experiments on the OTB100, UAV123, NFS, VOT2020, VOT2021, LaSOT, LaSOT_ext, TrackingNet and GOT-10k benchmarks show that the proposed box estimation network outperforms most existing box estimation methods. Furthermore, our trackers based on this estimation network exhibit a competitive performance against state-of-the-art trackers." @default.
- W4226261750 created "2022-05-05" @default.
- W4226261750 creator A5026297396 @default.
- W4226261750 creator A5046335655 @default.
- W4226261750 creator A5051595025 @default.
- W4226261750 creator A5061517548 @default.
- W4226261750 creator A5064550093 @default.
- W4226261750 date "2022-09-01" @default.
- W4226261750 modified "2023-10-16" @default.
- W4226261750 title "Spreading Fine-Grained Prior Knowledge for Accurate Tracking" @default.
- W4226261750 cites W1857884451 @default.
- W4226261750 cites W1861492603 @default.
- W4226261750 cites W2089961441 @default.
- W4226261750 cites W2154889144 @default.
- W4226261750 cites W2158592639 @default.
- W4226261750 cites W2194775991 @default.
- W4226261750 cites W2470394683 @default.
- W4226261750 cites W2518013266 @default.
- W4226261750 cites W2518876086 @default.
- W4226261750 cites W2557641257 @default.
- W4226261750 cites W2565639579 @default.
- W4226261750 cites W2605173812 @default.
- W4226261750 cites W2794744029 @default.
- W4226261750 cites W2799058067 @default.
- W4226261750 cites W2883286874 @default.
- W4226261750 cites W2886904239 @default.
- W4226261750 cites W2886910176 @default.
- W4226261750 cites W2891033863 @default.
- W4226261750 cites W2898200825 @default.
- W4226261750 cites W2904531787 @default.
- W4226261750 cites W2906580494 @default.
- W4226261750 cites W2917435394 @default.
- W4226261750 cites W2937749627 @default.
- W4226261750 cites W2955747520 @default.
- W4226261750 cites W2962824803 @default.
- W4226261750 cites W2963074722 @default.
- W4226261750 cites W2963150697 @default.
- W4226261750 cites W2963420686 @default.
- W4226261750 cites W2963534981 @default.
- W4226261750 cites W2966759264 @default.
- W4226261750 cites W2979087743 @default.
- W4226261750 cites W2981461115 @default.
- W4226261750 cites W2986235162 @default.
- W4226261750 cites W2995199381 @default.
- W4226261750 cites W2998027361 @default.
- W4226261750 cites W2998434318 @default.
- W4226261750 cites W3001584168 @default.
- W4226261750 cites W3003693721 @default.
- W4226261750 cites W3018646353 @default.
- W4226261750 cites W3034552520 @default.
- W4226261750 cites W3035511673 @default.
- W4226261750 cites W3035571898 @default.
- W4226261750 cites W3035725297 @default.
- W4226261750 cites W3043157863 @default.
- W4226261750 cites W3090155371 @default.
- W4226261750 cites W3106127916 @default.
- W4226261750 cites W3108235634 @default.
- W4226261750 cites W3127756064 @default.
- W4226261750 cites W3138516171 @default.
- W4226261750 cites W3167536469 @default.
- W4226261750 cites W3167762749 @default.
- W4226261750 cites W3168663926 @default.
- W4226261750 cites W3170841864 @default.
- W4226261750 cites W3172670627 @default.
- W4226261750 cites W3203701986 @default.
- W4226261750 cites W3209993199 @default.
- W4226261750 cites W3214586131 @default.
- W4226261750 cites W4214654781 @default.
- W4226261750 cites W4214736485 @default.
- W4226261750 cites W4214759957 @default.
- W4226261750 cites W639708223 @default.
- W4226261750 doi "https://doi.org/10.1109/tcsvt.2022.3162599" @default.
- W4226261750 hasPublicationYear "2022" @default.
- W4226261750 type Work @default.
- W4226261750 citedByCount "7" @default.
- W4226261750 countsByYear W42262617502022 @default.
- W4226261750 countsByYear W42262617502023 @default.
- W4226261750 crossrefType "journal-article" @default.
- W4226261750 hasAuthorship W4226261750A5026297396 @default.
- W4226261750 hasAuthorship W4226261750A5046335655 @default.
- W4226261750 hasAuthorship W4226261750A5051595025 @default.
- W4226261750 hasAuthorship W4226261750A5061517548 @default.
- W4226261750 hasAuthorship W4226261750A5064550093 @default.
- W4226261750 hasConcept C105795698 @default.
- W4226261750 hasConcept C111919701 @default.
- W4226261750 hasConcept C115961682 @default.
- W4226261750 hasConcept C118505674 @default.
- W4226261750 hasConcept C119857082 @default.
- W4226261750 hasConcept C121332964 @default.
- W4226261750 hasConcept C147037132 @default.
- W4226261750 hasConcept C153180895 @default.
- W4226261750 hasConcept C154945302 @default.
- W4226261750 hasConcept C165801399 @default.
- W4226261750 hasConcept C2776151529 @default.
- W4226261750 hasConcept C31972630 @default.
- W4226261750 hasConcept C33923547 @default.
- W4226261750 hasConcept C41008148 @default.
- W4226261750 hasConcept C56461940 @default.