Comprehending the Gossips: Meme Explanation in Time-Sync Video Comment via Multimodal Cues.
Zheyong XieWeidong HeTong XuShiwei WuChen ZhuPing YangEnhong ChenPublished in: ACM Trans. Asian Low Resour. Lang. Inf. Process. (2023)
Keyphrases
- multimodal fusion
- video data
- multimedia
- visual cues
- video sequences
- video streams
- video frames
- video content
- video analysis
- video clips
- spatial and temporal
- audio visual
- event detection
- online video
- multiple modalities
- multi modal
- multimodal information
- event recognition
- moving foreground
- video images
- story segmentation
- video processing
- video shots
- neural network
- video segmentation
- video database
- video retrieval
- key frames
- real time video
- multimedia data
- space time
- motion cues
- depth perception
- low level
- high level
- real time