Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-Wise Pseudo Labeling
Jinxing Zhou, Dan Guo, Yiran Zhong, Meng Wang
Topics & Concepts
ParsingArtificial intelligenceComputer sciencePattern recognition (psychology)Audio visualSpeech recognitionNatural language processingComputer visionMultimediaMusic and Audio ProcessingSpeech and Audio ProcessingVideo Analysis and Summarization