X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval.
Satya Krishna GortiNoël VouitsisJunwei MaKeyvan GolestanMaksims VolkovsAnimesh GargGuangwei YuPublished in: CVPR (2022)
Keyphrases
- video retrieval
- cross modal
- video search
- video segments
- video collections
- multi modal
- video database
- video data
- concept based video retrieval
- video content
- visual content
- content based retrieval
- content based video retrieval
- multimedia retrieval
- visual data
- key frames
- video shots
- retrieval systems
- semantic gap
- video clips
- text retrieval
- visual similarity
- semantic concepts
- information retrieval
- multimedia databases
- video sequences
- multimedia documents
- news video
- text mining
- video streams
- video frames
- image retrieval
- semantic content
- text documents
- high dimensional
- image understanding