FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2965840045> ?p ?o ?g. }

• W2965840045 abstract "We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking. The key innovation of the proposed method is to perform group feature selection across both channel and spatial dimensions, thus to pinpoint the structural relevance of multi-channel features to the filtering system. In contrast to the widely used spatial regularisation or feature selection methods, to the best of our knowledge, this is the first time that channel selection has been advocated for DCF-based tracking. We demonstrate that our GFS-DCF method is able to significantly improve the performance of a DCF tracker equipped with deep neural network features. In addition, our GFS-DCF enables joint feature selection and filter learning, achieving enhanced discrimination and interpretability of the learned filters. To further improve the performance, we adaptively integrate historical information by constraining filters to be smooth across temporal frames, using an efficient low-rank approximation. By design, specific temporal-spatial-channel configurations are dynamically learned in the tracking process, highlighting the relevant features, and alleviating the performance degrading impact of less discriminative representations and reducing information redundancy. The experimental results obtained on OTB2013, OTB2015, VOT2017, VOT2018 and TrackingNet demonstrate the merits of our GFS-DCF and its superiority over the state-of-the-art trackers. The code is publicly available at https://github.com/XU-TIANYANG/GFS-DCF." @default.
• W2965840045 created "2019-08-13" @default.
• W2965840045 creator A5025299678 @default.
• W2965840045 creator A5028209738 @default.
• W2965840045 creator A5049469328 @default.
• W2965840045 creator A5087450445 @default.
• W2965840045 date "2019-07-30" @default.
• W2965840045 modified "2023-10-16" @default.
• W2965840045 title "Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking" @default.
• W2965840045 cites W161114242 @default.
• W2965840045 cites W1686810756 @default.
• W2965840045 cites W1736339626 @default.
• W2965840045 cites W1857884451 @default.
• W2965840045 cites W1892578678 @default.
• W2965840045 cites W1908905119 @default.
• W2965840045 cites W1915599933 @default.
• W2965840045 cites W1915785815 @default.
• W2965840045 cites W1937954682 @default.
• W2965840045 cites W1955514522 @default.
• W2965840045 cites W1963882359 @default.
• W2965840045 cites W1964846093 @default.
• W2965840045 cites W1997121481 @default.
• W2965840045 cites W2044986361 @default.
• W2965840045 cites W2066513826 @default.
• W2965840045 cites W2089961441 @default.
• W2965840045 cites W2097117768 @default.
• W2965840045 cites W2117539524 @default.
• W2965840045 cites W2118345389 @default.
• W2965840045 cites W2118508489 @default.
• W2965840045 cites W2118877769 @default.
• W2965840045 cites W2126302311 @default.
• W2965840045 cites W2130026429 @default.
• W2965840045 cites W2132105090 @default.
• W2965840045 cites W2138019504 @default.
• W2965840045 cites W2138265962 @default.
• W2965840045 cites W2139047213 @default.
• W2965840045 cites W2141607429 @default.
• W2965840045 cites W2154889144 @default.
• W2965840045 cites W2158592639 @default.
• W2965840045 cites W2158827467 @default.
• W2965840045 cites W2160337655 @default.
• W2965840045 cites W2161969291 @default.
• W2965840045 cites W2162349892 @default.
• W2965840045 cites W2162919312 @default.
• W2965840045 cites W2163605009 @default.
• W2965840045 cites W2164278908 @default.
• W2965840045 cites W2171447090 @default.
• W2965840045 cites W2171837816 @default.
• W2965840045 cites W2194775991 @default.
• W2965840045 cites W2211807644 @default.
• W2965840045 cites W2267551383 @default.
• W2965840045 cites W2271232908 @default.
• W2965840045 cites W2296131993 @default.
• W2965840045 cites W2339611261 @default.
• W2965840045 cites W2469175529 @default.
• W2965840045 cites W2469582947 @default.
• W2965840045 cites W2473868734 @default.
• W2965840045 cites W2474516676 @default.
• W2965840045 cites W2518013266 @default.
• W2965840045 cites W2518876086 @default.
• W2965840045 cites W2520477759 @default.
• W2965840045 cites W2548498729 @default.
• W2965840045 cites W2557641257 @default.
• W2965840045 cites W2558899534 @default.
• W2965840045 cites W2595142274 @default.
• W2965840045 cites W2599547527 @default.
• W2965840045 cites W2610871254 @default.
• W2965840045 cites W2673818281 @default.
• W2965840045 cites W2681067697 @default.
• W2965840045 cites W2740685955 @default.
• W2965840045 cites W2742165450 @default.
• W2965840045 cites W2768634781 @default.
• W2965840045 cites W2783173047 @default.
• W2965840045 cites W2784375960 @default.
• W2965840045 cites W2792162533 @default.
• W2965840045 cites W2792215676 @default.
• W2965840045 cites W2794744029 @default.
• W2965840045 cites W2796919380 @default.
• W2965840045 cites W2797812763 @default.
• W2965840045 cites W2798520605 @default.
• W2965840045 cites W2799058067 @default.
• W2965840045 cites W2886910176 @default.
• W2965840045 cites W2894682667 @default.
• W2965840045 cites W2897666265 @default.
• W2965840045 cites W2913466142 @default.
• W2965840045 cites W2916780012 @default.
• W2965840045 cites W2917435394 @default.
• W2965840045 cites W29474918 @default.
• W2965840045 cites W2962824803 @default.
• W2965840045 cites W2962864296 @default.
• W2965840045 cites W2963074722 @default.
• W2965840045 cites W2964111344 @default.
• W2965840045 cites W2964264751 @default.
• W2965840045 cites W3099014882 @default.
• W2965840045 cites W818325216 @default.
• W2965840045 doi "https://doi.org/10.48550/arxiv.1907.13242" @default.
• W2965840045 hasPublicationYear "2019" @default.
• W2965840045 type Work @default.
• W2965840045 sameAs 2965840045 @default.
• W2965840045 citedByCount "0" @default.

• next