Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment.
Yongrae JoSeongyun LeeAiden SJ LeeHyunji LeeHanseok OhMinjoon SeoPublished in: CoRR (2023)
Keyphrases
- natural language descriptions
- video sequences
- text detection
- video segments
- video search
- video clips
- video data
- video content
- news video
- information retrieval
- multimedia documents
- multimedia
- video streams
- database
- video images
- closed captions
- event recognition
- real time
- video database
- free text
- video frames
- space time
- text mining
- video event detection
- video retrieval
- video surveillance
- text retrieval
- multimedia search
- search engine
- multi camera
- audio content
- video collections
- semantic labels
- web documents
- text documents
- textual descriptions
- digital video
- video shots