Video Moment Retrieval from Text Queries via Single Frame Annotation.
Ran CuiTianwen QianPai PengElena DaskalakiJingjing ChenXiaowei GuoHuyang SunYu-Gang JiangPublished in: SIGIR (2022)
Keyphrases
- text queries
- single frame
- video frames
- text retrieval
- visual features
- video sequences
- super resolution
- image collections
- image retrieval
- text search
- video shots
- retrieval systems
- image sequences
- retrieval framework
- handwritten documents
- visually similar
- multi frame
- surveillance videos
- search engine
- optical flow
- web images
- low resolution
- video data
- video search
- document collections
- low level
- video content
- image search
- video clips
- video retrieval
- image classification
- image annotation
- information retrieval
- high resolution
- multimedia
- search tasks
- visual content
- document retrieval
- information retrieval systems
- video database
- retrieval model
- video streams
- visual similarity
- image content
- moving objects
- high quality
- computer vision
- test collection