MSVD-Turkish: A Large-Scale Dataset for Video Captioning in Turkish.
Begüm ÇitamakMenekse KuyuAykut ErdemErkut ErdemPublished in: SIU (2019)
Keyphrases
- trecvid multimedia event detection
- event recognition
- video event detection
- video data
- human actions
- video content
- small scale
- event detection
- video frames
- real time
- real life
- action recognition
- real world
- multimedia
- video sequences
- multi lingual
- database
- spatial and temporal
- video surveillance
- video retrieval
- video clips
- video analysis
- video images
- weakly labeled
- video dataset
- web videos
- space time
- image quality
- benchmark datasets
- online video
- real time video
- video streams
- key frames