Video ReCap: Recursive Captioning of Hour-Long Videos.
Md Mohaiminul IslamNgan HoXitong YangTushar NagarajanLorenzo TorresaniGedas BertasiusPublished in: CoRR (2024)
Keyphrases
- video content
- video frames
- video data
- video sequences
- video database
- video analysis
- video clips
- key frames
- video editing
- video streams
- online video
- event recognition
- youtube videos
- input video
- video indexing
- content based copy detection
- temporal coherence
- video surveillance
- spatiotemporal features
- video representation
- video event
- video browsing
- motion features
- video dataset
- video images
- video segments
- video search
- video shots
- video retrieval
- video material
- video classification
- moving camera
- human activities
- human actions
- successive frames
- video summarization
- video annotation
- visual analysis
- action recognition
- space time
- natural language descriptions
- stereoscopic video
- spatial and temporal
- action classification
- sports video
- high definition
- dynamic textures
- semantic concept detection
- long video
- video sharing
- low frame rate
- multimedia
- web videos
- video objects
- video processing
- motion estimation
- temporal segmentation
- lecture videos
- dynamic scenes
- temporal relationships
- news video
- video collections
- user generated
- textual descriptions
- video signals
- instructional videos
- camera motion