FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205084906> ?p ?o ?g. }

• W3205084906 endingPage "3879" @default.
• W3205084906 startingPage "3866" @default.
• W3205084906 abstract "Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>http://vipl.ict.ac.cn/resources/codes/code/SANet_code.zip</uri> ." @default.
• W3205084906 created "2021-10-25" @default.
• W3205084906 creator A5029499523 @default.
• W3205084906 creator A5037306106 @default.
• W3205084906 creator A5037786771 @default.
• W3205084906 creator A5041045297 @default.
• W3205084906 creator A5050297728 @default.
• W3205084906 creator A5079473059 @default.
• W3205084906 date "2022-06-01" @default.
• W3205084906 modified "2023-10-06" @default.
• W3205084906 title "SANet: Statistic Attention Network for Video-Based Person Re-Identification" @default.
• W3205084906 cites W2097117768 @default.
• W3205084906 cites W2108598243 @default.
• W3205084906 cites W2135442311 @default.
• W3205084906 cites W2183341477 @default.
• W3205084906 cites W2194775991 @default.
• W3205084906 cites W2204750386 @default.
• W3205084906 cites W2240887954 @default.
• W3205084906 cites W2302255633 @default.
• W3205084906 cites W2463071499 @default.
• W3205084906 cites W2519803806 @default.
• W3205084906 cites W2520433280 @default.
• W3205084906 cites W2549139847 @default.
• W3205084906 cites W2550553598 @default.
• W3205084906 cites W2584637367 @default.
• W3205084906 cites W2585635281 @default.
• W3205084906 cites W2604211872 @default.
• W3205084906 cites W2622829582 @default.
• W3205084906 cites W2678677036 @default.
• W3205084906 cites W2752782242 @default.
• W3205084906 cites W2761121566 @default.
• W3205084906 cites W2798329462 @default.
• W3205084906 cites W2799185441 @default.
• W3205084906 cites W2883348239 @default.
• W3205084906 cites W2883780447 @default.
• W3205084906 cites W2886209409 @default.
• W3205084906 cites W2891175865 @default.
• W3205084906 cites W2892880750 @default.
• W3205084906 cites W2896888563 @default.
• W3205084906 cites W2926107957 @default.
• W3205084906 cites W2948383821 @default.
• W3205084906 cites W2953003997 @default.
• W3205084906 cites W2959022568 @default.
• W3205084906 cites W2962858109 @default.
• W3205084906 cites W2963047834 @default.
• W3205084906 cites W2963049565 @default.
• W3205084906 cites W2963078173 @default.
• W3205084906 cites W2963091558 @default.
• W3205084906 cites W2963180826 @default.
• W3205084906 cites W2963216120 @default.
• W3205084906 cites W2963319519 @default.
• W3205084906 cites W2963446712 @default.
• W3205084906 cites W2963637710 @default.
• W3205084906 cites W2963736028 @default.
• W3205084906 cites W2964140013 @default.
• W3205084906 cites W2964261250 @default.
• W3205084906 cites W2964304299 @default.
• W3205084906 cites W2979931389 @default.
• W3205084906 cites W2980073905 @default.
• W3205084906 cites W2981393440 @default.
• W3205084906 cites W2981420411 @default.
• W3205084906 cites W2981689412 @default.
• W3205084906 cites W2982119297 @default.
• W3205084906 cites W2984145721 @default.
• W3205084906 cites W2986451890 @default.
• W3205084906 cites W2987151592 @default.
• W3205084906 cites W2993235622 @default.
• W3205084906 cites W3000133216 @default.
• W3205084906 cites W3034417718 @default.
• W3205084906 cites W3034580371 @default.
• W3205084906 cites W3035186652 @default.
• W3205084906 cites W3035252826 @default.
• W3205084906 cites W3035486808 @default.
• W3205084906 cites W3036967712 @default.
• W3205084906 cites W3099899804 @default.
• W3205084906 cites W3100506510 @default.
• W3205084906 cites W3113160875 @default.
• W3205084906 cites W3133783521 @default.
• W3205084906 cites W3172865031 @default.
• W3205084906 doi "https://doi.org/10.1109/tcsvt.2021.3119983" @default.
• W3205084906 hasPublicationYear "2022" @default.
• W3205084906 type Work @default.
• W3205084906 sameAs 3205084906 @default.
• W3205084906 citedByCount "6" @default.
• W3205084906 countsByYear W32050849062022 @default.
• W3205084906 countsByYear W32050849062023 @default.
• W3205084906 crossrefType "journal-article" @default.
• W3205084906 hasAuthorship W3205084906A5029499523 @default.
• W3205084906 hasAuthorship W3205084906A5037306106 @default.
• W3205084906 hasAuthorship W3205084906A5037786771 @default.
• W3205084906 hasAuthorship W3205084906A5041045297 @default.
• W3205084906 hasAuthorship W3205084906A5050297728 @default.
• W3205084906 hasAuthorship W3205084906A5079473059 @default.
• W3205084906 hasConcept C105795698 @default.
• W3205084906 hasConcept C111919701 @default.
• W3205084906 hasConcept C116834253 @default.
• W3205084906 hasConcept C119857082 @default.
• W3205084906 hasConcept C124101348 @default.

• next