Litcius/Paper detail

SCESS-Net: Semantic consistency enhancement and segment selection network for audio–visual event localization

Jichen Gao, Suiping Zhou, Hang Yu, Chenyang Li, Xiaoxi Hu

2025Computer Vision and Image Understanding7 citationsDOI

Topics & Concepts

Computer scienceSemantics (computer science)Event (particle physics)PoolingConsistency (knowledge bases)Artificial intelligenceFeature (linguistics)Semantic similaritySimilarity (geometry)Machine learningFeature learningSemantic matchingDiscriminative modelVisualizationModalitiesDeep learningNatural language processingTask (project management)Spatial analysisSelection (genetic algorithm)Mutual informationChannel (broadcasting)Feature selectionAttention networkForcing (mathematics)SubnetworkPattern recognition (psychology)Feature extractionSemantic computingMusic and Audio ProcessingVideo Analysis and SummarizationSpeech and Audio Processing
SCESS-Net: Semantic consistency enhancement and segment selection network for audio–visual event localization | Litcius