HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue.
Sunjae YoonDahyun KimEunseop YoonHee Suk YoonJunyeong KimChnag D. YooPublished in: CoRR (2023)
Keyphrases
- multimedia
- audio video
- scene change detection
- digital video
- multimedia processing
- visual data
- video content analysis
- video data
- video files
- video material
- video sequences
- video clips
- digital audio
- multimedia information
- audio files
- video content
- video analysis
- lecture videos
- video streams
- audio signals
- video signals
- content based video retrieval
- human machine
- signal processing
- video copy detection
- story segmentation
- long video
- audio features
- audio stream
- closed captions
- video retrieval
- mixed initiative
- audio content
- audio visual
- video database
- multimedia data
- key frames
- online video
- video shots
- dialogue system
- multimedia databases
- natural language
- audio visual content
- image sequences
- video frames
- conversational agent
- video recordings
- sign language
- audio signal
- video scene
- video indexing
- news video