Matches in SemOpenAlex for { <https://semopenalex.org/work/W3060719325> ?p ?o ?g. }
- W3060719325 abstract "With the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models trained by both spatial and temporal information. However, due to the lesser consideration of temporal information, the image saliency deep models may become fragile in the video sequences dominated by temporal information. Thus, the most recent video saliency detection approaches have adopted the network architecture starting with a spatial deep model that is followed by an elaborately designed temporal deep model. However, such methods easily encounter the performance bottleneck arising from the single stream learning methodology, so the overall detection performance is largely determined by the spatial deep model. In sharp contrast to the current mainstream methods, this paper proposes a novel plug-and-play scheme to weakly retrain a pretrained image saliency deep model for video data by using the newly sensed and coded temporal information. Thus, the retrained image saliency deep model will be able to maintain temporal saliency awareness, achieving much improved detection performance. Moreover, our method is simple yet effective for adapting any off-the-shelf pre-trained image saliency deep model to obtain high-quality video saliency detection. Additionally, both the data and source code of our method are publicly available." @default.
- W3060719325 created "2020-08-24" @default.
- W3060719325 creator A5030724247 @default.
- W3060719325 creator A5035153076 @default.
- W3060719325 creator A5049185198 @default.
- W3060719325 creator A5065912071 @default.
- W3060719325 creator A5091408797 @default.
- W3060719325 date "2020-08-02" @default.
- W3060719325 modified "2023-09-24" @default.
- W3060719325 title "A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data" @default.
- W3060719325 cites W1954128991 @default.
- W3060719325 cites W1969226866 @default.
- W3060719325 cites W1980120082 @default.
- W3060719325 cites W1983039297 @default.
- W3060719325 cites W2002781701 @default.
- W3060719325 cites W2037954058 @default.
- W3060719325 cites W2043331342 @default.
- W3060719325 cites W2068723588 @default.
- W3060719325 cites W2076756823 @default.
- W3060719325 cites W2100470808 @default.
- W3060719325 cites W2110019070 @default.
- W3060719325 cites W2118985252 @default.
- W3060719325 cites W2138682569 @default.
- W3060719325 cites W2147253850 @default.
- W3060719325 cites W2176137647 @default.
- W3060719325 cites W2470139095 @default.
- W3060719325 cites W2501148868 @default.
- W3060719325 cites W2518599539 @default.
- W3060719325 cites W2519528544 @default.
- W3060719325 cites W2548527721 @default.
- W3060719325 cites W2556053754 @default.
- W3060719325 cites W2569272946 @default.
- W3060719325 cites W2588503511 @default.
- W3060719325 cites W2729969528 @default.
- W3060719325 cites W2745150820 @default.
- W3060719325 cites W2757028014 @default.
- W3060719325 cites W2765103010 @default.
- W3060719325 cites W2768270796 @default.
- W3060719325 cites W2788154928 @default.
- W3060719325 cites W2790027547 @default.
- W3060719325 cites W2793029440 @default.
- W3060719325 cites W2799108379 @default.
- W3060719325 cites W2800632947 @default.
- W3060719325 cites W2803472033 @default.
- W3060719325 cites W2803610340 @default.
- W3060719325 cites W2884530474 @default.
- W3060719325 cites W2884555738 @default.
- W3060719325 cites W2895340898 @default.
- W3060719325 cites W2898976943 @default.
- W3060719325 cites W2904232353 @default.
- W3060719325 cites W2939217524 @default.
- W3060719325 cites W2948500402 @default.
- W3060719325 cites W2949503654 @default.
- W3060719325 cites W2960426010 @default.
- W3060719325 cites W2963112696 @default.
- W3060719325 cites W2963782415 @default.
- W3060719325 cites W2963823251 @default.
- W3060719325 cites W2963868681 @default.
- W3060719325 cites W2963951674 @default.
- W3060719325 cites W2964156315 @default.
- W3060719325 cites W2965638232 @default.
- W3060719325 cites W2969626490 @default.
- W3060719325 cites W2971631405 @default.
- W3060719325 cites W2979551929 @default.
- W3060719325 cites W2986056979 @default.
- W3060719325 cites W3003376220 @default.
- W3060719325 cites W846669277 @default.
- W3060719325 doi "https://doi.org/10.48550/arxiv.2008.09103" @default.
- W3060719325 hasPublicationYear "2020" @default.
- W3060719325 type Work @default.
- W3060719325 sameAs 3060719325 @default.
- W3060719325 citedByCount "0" @default.
- W3060719325 crossrefType "posted-content" @default.
- W3060719325 hasAuthorship W3060719325A5030724247 @default.
- W3060719325 hasAuthorship W3060719325A5035153076 @default.
- W3060719325 hasAuthorship W3060719325A5049185198 @default.
- W3060719325 hasAuthorship W3060719325A5065912071 @default.
- W3060719325 hasAuthorship W3060719325A5091408797 @default.
- W3060719325 hasBestOaLocation W30607193251 @default.
- W3060719325 hasConcept C108583219 @default.
- W3060719325 hasConcept C115961682 @default.
- W3060719325 hasConcept C127313418 @default.
- W3060719325 hasConcept C149635348 @default.
- W3060719325 hasConcept C153180895 @default.
- W3060719325 hasConcept C154945302 @default.
- W3060719325 hasConcept C159620131 @default.
- W3060719325 hasConcept C2780513914 @default.
- W3060719325 hasConcept C31972630 @default.
- W3060719325 hasConcept C41008148 @default.
- W3060719325 hasConcept C62649853 @default.
- W3060719325 hasConceptScore W3060719325C108583219 @default.
- W3060719325 hasConceptScore W3060719325C115961682 @default.
- W3060719325 hasConceptScore W3060719325C127313418 @default.
- W3060719325 hasConceptScore W3060719325C149635348 @default.
- W3060719325 hasConceptScore W3060719325C153180895 @default.
- W3060719325 hasConceptScore W3060719325C154945302 @default.
- W3060719325 hasConceptScore W3060719325C159620131 @default.
- W3060719325 hasConceptScore W3060719325C2780513914 @default.
- W3060719325 hasConceptScore W3060719325C31972630 @default.
- W3060719325 hasConceptScore W3060719325C41008148 @default.