M-VAD Names: a Dataset for Video Captioning with Naming.
Stefano PiniMarcella CorniaFederico BolelliLorenzo BaraldiRita CucchiaraPublished in: CoRR (2019)
Keyphrases
- video sequences
- human actions
- multimedia
- video data
- video streams
- real time
- video content
- video frames
- weakly labeled
- benchmark datasets
- video clips
- online video
- digital video
- trecvid multimedia event detection
- event recognition
- video retrieval
- action recognition
- signal to noise ratio
- key frames
- multimedia data
- video analysis
- video segmentation
- synthetic datasets
- named entities
- video images
- real time video
- keywords
- neural network
- data sets