Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313476633> ?p ?o ?g. }
- W4313476633 endingPage "22" @default.
- W4313476633 startingPage "1" @default.
- W4313476633 abstract "Audio information has not been considered an important factor in visual attention models regardless of many psychological studies that have shown the importance of audio information in the human visual perception system. Since existing visual attention models only utilize visual information, their performance is limited but also requires high-computational complexity due to the limited information available. To overcome these problems, we propose a lightweight audio-visual saliency (LAVS) model for video sequences. To the best of our knowledge, this article is the first trial to utilize audio cues for an efficient deep-learning model for the video saliency estimation. First, spatial-temporal visual features are extracted by the lightweight receptive field block (RFB) with the bidirectional ConvLSTM units. Then, audio features are extracted by using an improved lightweight environment sound classification model. Subsequently, deep canonical correlation analysis (DCCA) aims at capturing the correspondence between audio and spatial-temporal visual features, thus obtaining a spatial-temporal auditory saliency. Lastly, the spatial-temporal visual and auditory saliency are fused to obtain the audio-visual saliency map. Extensive comparative experiments and ablation studies validate the performance of the LAVS model in terms of effectiveness and complexity." @default.
- W4313476633 created "2023-01-06" @default.
- W4313476633 creator A5002554183 @default.
- W4313476633 creator A5019708391 @default.
- W4313476633 creator A5039990525 @default.
- W4313476633 creator A5043405654 @default.
- W4313476633 creator A5064168853 @default.
- W4313476633 creator A5085080585 @default.
- W4313476633 date "2023-02-27" @default.
- W4313476633 modified "2023-10-16" @default.
- W4313476633 title "A Novel Lightweight Audio-visual Saliency Model for Videos" @default.
- W4313476633 cites W1152443276 @default.
- W4313476633 cites W1903029394 @default.
- W4313476633 cites W1947031653 @default.
- W4313476633 cites W1978479866 @default.
- W4313476633 cites W2002781701 @default.
- W4313476633 cites W2004294009 @default.
- W4313476633 cites W2015394094 @default.
- W4313476633 cites W2032007016 @default.
- W4313476633 cites W2039313011 @default.
- W4313476633 cites W2047670868 @default.
- W4313476633 cites W2094432440 @default.
- W4313476633 cites W2119577735 @default.
- W4313476633 cites W2135835174 @default.
- W4313476633 cites W2148154194 @default.
- W4313476633 cites W2155479901 @default.
- W4313476633 cites W2161025448 @default.
- W4313476633 cites W2164084182 @default.
- W4313476633 cites W2184568381 @default.
- W4313476633 cites W2212216676 @default.
- W4313476633 cites W2288514685 @default.
- W4313476633 cites W2334831412 @default.
- W4313476633 cites W2338972621 @default.
- W4313476633 cites W2471855951 @default.
- W4313476633 cites W2498738402 @default.
- W4313476633 cites W2529272619 @default.
- W4313476633 cites W2533370895 @default.
- W4313476633 cites W2561270043 @default.
- W4313476633 cites W2588443678 @default.
- W4313476633 cites W2741835523 @default.
- W4313476633 cites W2757028014 @default.
- W4313476633 cites W2780708736 @default.
- W4313476633 cites W2807746031 @default.
- W4313476633 cites W2889942734 @default.
- W4313476633 cites W2904099109 @default.
- W4313476633 cites W2912100719 @default.
- W4313476633 cites W2922086303 @default.
- W4313476633 cites W2939124210 @default.
- W4313476633 cites W2946259291 @default.
- W4313476633 cites W2962965915 @default.
- W4313476633 cites W2963503775 @default.
- W4313476633 cites W2963581854 @default.
- W4313476633 cites W2963685207 @default.
- W4313476633 cites W2964114039 @default.
- W4313476633 cites W2969741484 @default.
- W4313476633 cites W2986131415 @default.
- W4313476633 cites W3022565501 @default.
- W4313476633 cites W3034287518 @default.
- W4313476633 cites W3041053424 @default.
- W4313476633 cites W3095348033 @default.
- W4313476633 cites W3101840568 @default.
- W4313476633 cites W3104979525 @default.
- W4313476633 cites W3122238731 @default.
- W4313476633 cites W4239147634 @default.
- W4313476633 doi "https://doi.org/10.1145/3576857" @default.
- W4313476633 hasPublicationYear "2023" @default.
- W4313476633 type Work @default.
- W4313476633 citedByCount "1" @default.
- W4313476633 countsByYear W43134766332023 @default.
- W4313476633 crossrefType "journal-article" @default.
- W4313476633 hasAuthorship W4313476633A5002554183 @default.
- W4313476633 hasAuthorship W4313476633A5019708391 @default.
- W4313476633 hasAuthorship W4313476633A5039990525 @default.
- W4313476633 hasAuthorship W4313476633A5043405654 @default.
- W4313476633 hasAuthorship W4313476633A5064168853 @default.
- W4313476633 hasAuthorship W4313476633A5085080585 @default.
- W4313476633 hasConcept C115961682 @default.
- W4313476633 hasConcept C127313418 @default.
- W4313476633 hasConcept C153180895 @default.
- W4313476633 hasConcept C154945302 @default.
- W4313476633 hasConcept C159620131 @default.
- W4313476633 hasConcept C160086991 @default.
- W4313476633 hasConcept C169760540 @default.
- W4313476633 hasConcept C2524010 @default.
- W4313476633 hasConcept C26760741 @default.
- W4313476633 hasConcept C2777210771 @default.
- W4313476633 hasConcept C28490314 @default.
- W4313476633 hasConcept C3017588708 @default.
- W4313476633 hasConcept C31972630 @default.
- W4313476633 hasConcept C33923547 @default.
- W4313476633 hasConcept C36464697 @default.
- W4313476633 hasConcept C41008148 @default.
- W4313476633 hasConcept C49774154 @default.
- W4313476633 hasConcept C62649853 @default.
- W4313476633 hasConcept C86803240 @default.
- W4313476633 hasConceptScore W4313476633C115961682 @default.
- W4313476633 hasConceptScore W4313476633C127313418 @default.
- W4313476633 hasConceptScore W4313476633C153180895 @default.