FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950268230> ?p ?o ?g. }

• W2950268230 endingPage "107" @default.
• W2950268230 startingPage "96" @default.
• W2950268230 abstract "Classification-based tracking strategies often face more challenges from intra-class discrimination than from inter-class separability. Even for deep convolutional neural networks that have been widely proven to be effective in various vision tasks, their intra-class discriminative capability is still limited by the weakness of softmax loss, especially for targets not seen in the training dataset. By taking intrinsic attributes of training samples into account, in this paper, we propose a position-sensitive loss coupled with softmax loss to achieve intra-class compactness and inter-class explicitness. Particularly, two additive margins are introduced to encode the position attribute for decision boundary maximization, which is also utilized with the proposed loss to supervise the fine-tuned features on the pre-trained model. With the nearest neighbor ranking measurement in the feature embedding domain, the whole scheme is able to reach an optimized balance between the feature-level inter-class semantic separability and instance-level intra-class relative distance ranking. We evaluate the proposed work on different popular benchmarks, and experimental results demonstrate that our tracking strategy performs favorably against most of the state-of-the-art trackers in the comparison of accuracy and robustness." @default.
• W2950268230 created "2019-06-27" @default.
• W2950268230 creator A5003953585 @default.
• W2950268230 creator A5014604035 @default.
• W2950268230 creator A5063044952 @default.
• W2950268230 creator A5034734528 @default.
• W2950268230 date "2020-01-01" @default.
• W2950268230 modified "2023-10-16" @default.
• W2950268230 title "Deep Position-Sensitive Tracking" @default.
• W2950268230 cites W134197611 @default.
• W2950268230 cites W1857884451 @default.
• W2950268230 cites W1904671147 @default.
• W2950268230 cites W2001785244 @default.
• W2950268230 cites W2036150645 @default.
• W2950268230 cites W2089961441 @default.
• W2950268230 cites W2108215708 @default.
• W2950268230 cites W2108598243 @default.
• W2950268230 cites W2126302311 @default.
• W2950268230 cites W2154889144 @default.
• W2950268230 cites W2155893237 @default.
• W2950268230 cites W2158592639 @default.
• W2950268230 cites W2158827467 @default.
• W2950268230 cites W2214352687 @default.
• W2950268230 cites W2244956674 @default.
• W2950268230 cites W2408241409 @default.
• W2950268230 cites W2424629859 @default.
• W2950268230 cites W2467570466 @default.
• W2950268230 cites W2469582947 @default.
• W2950268230 cites W2473868734 @default.
• W2950268230 cites W2520477759 @default.
• W2950268230 cites W2520774990 @default.
• W2950268230 cites W2531380228 @default.
• W2950268230 cites W2556108308 @default.
• W2950268230 cites W2556867313 @default.
• W2950268230 cites W2557641257 @default.
• W2950268230 cites W2561630963 @default.
• W2950268230 cites W2603203130 @default.
• W2950268230 cites W2618530766 @default.
• W2950268230 cites W2738318237 @default.
• W2950268230 cites W2740685955 @default.
• W2950268230 cites W2767302379 @default.
• W2950268230 cites W2770465446 @default.
• W2950268230 cites W2790928014 @default.
• W2950268230 cites W2794744029 @default.
• W2950268230 cites W2799058067 @default.
• W2950268230 cites W2807832475 @default.
• W2950268230 cites W2883108970 @default.
• W2950268230 cites W2886910176 @default.
• W2950268230 cites W2891969803 @default.
• W2950268230 cites W2894176037 @default.
• W2950268230 cites W2897666265 @default.
• W2950268230 cites W2963249584 @default.
• W2950268230 cites W2964099559 @default.
• W2950268230 cites W2964111344 @default.
• W2950268230 cites W2964242925 @default.
• W2950268230 cites W3098217967 @default.
• W2950268230 cites W3102624093 @default.
• W2950268230 cites W3104636655 @default.
• W2950268230 cites W3125612102 @default.
• W2950268230 doi "https://doi.org/10.1109/tmm.2019.2922125" @default.
• W2950268230 hasPublicationYear "2020" @default.
• W2950268230 type Work @default.
• W2950268230 sameAs 2950268230 @default.
• W2950268230 citedByCount "8" @default.
• W2950268230 countsByYear W29502682302020 @default.
• W2950268230 countsByYear W29502682302021 @default.
• W2950268230 countsByYear W29502682302022 @default.
• W2950268230 countsByYear W29502682302023 @default.
• W2950268230 crossrefType "journal-article" @default.
• W2950268230 hasAuthorship W2950268230A5003953585 @default.
• W2950268230 hasAuthorship W2950268230A5014604035 @default.
• W2950268230 hasAuthorship W2950268230A5034734528 @default.
• W2950268230 hasAuthorship W2950268230A5063044952 @default.
• W2950268230 hasConcept C104317684 @default.
• W2950268230 hasConcept C119857082 @default.
• W2950268230 hasConcept C12267149 @default.
• W2950268230 hasConcept C138885662 @default.
• W2950268230 hasConcept C153180895 @default.
• W2950268230 hasConcept C154945302 @default.
• W2950268230 hasConcept C185592680 @default.
• W2950268230 hasConcept C188441871 @default.
• W2950268230 hasConcept C199360897 @default.
• W2950268230 hasConcept C2776401178 @default.
• W2950268230 hasConcept C2781289151 @default.
• W2950268230 hasConcept C41008148 @default.
• W2950268230 hasConcept C41608201 @default.
• W2950268230 hasConcept C41895202 @default.
• W2950268230 hasConcept C42023084 @default.
• W2950268230 hasConcept C46686674 @default.
• W2950268230 hasConcept C52622490 @default.
• W2950268230 hasConcept C55493867 @default.
• W2950268230 hasConcept C63479239 @default.
• W2950268230 hasConcept C73752529 @default.
• W2950268230 hasConcept C81363708 @default.
• W2950268230 hasConcept C97931131 @default.
• W2950268230 hasConceptScore W2950268230C104317684 @default.
• W2950268230 hasConceptScore W2950268230C119857082 @default.
• W2950268230 hasConceptScore W2950268230C12267149 @default.

• next