FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3180447501> ?p ?o ?g. }

• W3180447501 endingPage "2745" @default.
• W3180447501 startingPage "2732" @default.
• W3180447501 abstract "Previous video salient object detection (VSOD) approaches have mainly focused on the perspective of network design for achieving performance improvements. However, with the recent slowdown in the development of deep learning techniques, it might become increasingly difficult to anticipate another breakthrough solely via complex networks. Therefore, this paper proposes a universal learning scheme to obtain a further 3&#x0025; performance improvement for all state-of-the-art (SOTA) VSOD models. The major highlight of our method is that we propose the &#x2018;motion quality&#x2019;, a new concept for mining video frames from the &#x2018;buffered&#x2019; testing video stream for constructing a fine-tuning set. By using our approach, all frames in this set can all well-detect their salient object by the &#x2018;target SOTA model&#x2019; &#x2014; the one we want to improve. Thus, the VSOD results of the mined set, which were previously derived by the target SOTA model, can be directly applied as pseudolearning objectives to fine-tune a completely new spatial model that has been pretrained on the widely used DAVIS-TR set. Since some spatial scenes in the buffered testing video stream are shown, the fine-tuned spatial model can perform very well for the remaining unseen testing frames, outperforming the target SOTA model significantly. Although offline model fine tuning requires additional time costs, the performance gain can still benefit scenarios without speed requirements. Moreover, its semisupervised methodology might have considerable potential to inspire the VSOD community in the future." @default.
• W3180447501 created "2021-07-19" @default.
• W3180447501 creator A5019581026 @default.
• W3180447501 creator A5030724247 @default.
• W3180447501 creator A5054958308 @default.
• W3180447501 creator A5063013411 @default.
• W3180447501 creator A5081897709 @default.
• W3180447501 date "2022-05-01" @default.
• W3180447501 modified "2023-10-15" @default.
• W3180447501 title "A Novel Video Salient Object Detection Method via Semisupervised Motion Quality Perception" @default.
• W3180447501 cites W1522734439 @default.
• W3180447501 cites W1954128991 @default.
• W3180447501 cites W1969226866 @default.
• W3180447501 cites W1982075130 @default.
• W3180447501 cites W1990881985 @default.
• W3180447501 cites W2068723588 @default.
• W3180447501 cites W2100470808 @default.
• W3180447501 cites W2110019070 @default.
• W3180447501 cites W2138682569 @default.
• W3180447501 cites W2176137647 @default.
• W3180447501 cites W2470139095 @default.
• W3180447501 cites W2501148868 @default.
• W3180447501 cites W2547489168 @default.
• W3180447501 cites W2548527721 @default.
• W3180447501 cites W2550617893 @default.
• W3180447501 cites W2556053754 @default.
• W3180447501 cites W2569272946 @default.
• W3180447501 cites W2585592883 @default.
• W3180447501 cites W2588503511 @default.
• W3180447501 cites W2610147486 @default.
• W3180447501 cites W2615981376 @default.
• W3180447501 cites W2736833563 @default.
• W3180447501 cites W2757028014 @default.
• W3180447501 cites W2765102497 @default.
• W3180447501 cites W2765103010 @default.
• W3180447501 cites W2768270796 @default.
• W3180447501 cites W2783231089 @default.
• W3180447501 cites W2793029440 @default.
• W3180447501 cites W2793668851 @default.
• W3180447501 cites W2798807298 @default.
• W3180447501 cites W2799108379 @default.
• W3180447501 cites W2800632947 @default.
• W3180447501 cites W2803472033 @default.
• W3180447501 cites W2884414611 @default.
• W3180447501 cites W2890110575 @default.
• W3180447501 cites W2894404285 @default.
• W3180447501 cites W2894890793 @default.
• W3180447501 cites W2895340898 @default.
• W3180447501 cites W2921653116 @default.
• W3180447501 cites W2923266522 @default.
• W3180447501 cites W2939217524 @default.
• W3180447501 cites W2942939335 @default.
• W3180447501 cites W2943978556 @default.
• W3180447501 cites W2948500402 @default.
• W3180447501 cites W2948537313 @default.
• W3180447501 cites W2955060956 @default.
• W3180447501 cites W2955084925 @default.
• W3180447501 cites W2961348656 @default.
• W3180447501 cites W2962159375 @default.
• W3180447501 cites W2962965915 @default.
• W3180447501 cites W2963112696 @default.
• W3180447501 cites W2963253279 @default.
• W3180447501 cites W2963450895 @default.
• W3180447501 cites W2963732700 @default.
• W3180447501 cites W2963782415 @default.
• W3180447501 cites W2963868681 @default.
• W3180447501 cites W2964156315 @default.
• W3180447501 cites W2964738399 @default.
• W3180447501 cites W2965638232 @default.
• W3180447501 cites W2969626490 @default.
• W3180447501 cites W2973058802 @default.
• W3180447501 cites W2979028048 @default.
• W3180447501 cites W2986056979 @default.
• W3180447501 cites W2987391422 @default.
• W3180447501 cites W2990984982 @default.
• W3180447501 cites W2997217064 @default.
• W3180447501 cites W3000471755 @default.
• W3180447501 cites W3003376220 @default.
• W3180447501 cites W3006871679 @default.
• W3180447501 cites W3085887408 @default.
• W3180447501 cites W3087221416 @default.
• W3180447501 cites W3087299940 @default.
• W3180447501 cites W3091452821 @default.
• W3180447501 cites W3107310749 @default.
• W3180447501 cites W3117097536 @default.
• W3180447501 cites W3122238731 @default.
• W3180447501 cites W3149149291 @default.
• W3180447501 doi "https://doi.org/10.1109/tcsvt.2021.3095843" @default.
• W3180447501 hasPublicationYear "2022" @default.
• W3180447501 type Work @default.
• W3180447501 sameAs 3180447501 @default.
• W3180447501 citedByCount "17" @default.
• W3180447501 countsByYear W31804475012022 @default.
• W3180447501 countsByYear W31804475012023 @default.
• W3180447501 crossrefType "journal-article" @default.
• W3180447501 hasAuthorship W3180447501A5019581026 @default.
• W3180447501 hasAuthorship W3180447501A5030724247 @default.
• W3180447501 hasAuthorship W3180447501A5054958308 @default.

• next