Object-aware Video-language Pre-training for Retrieval.
Alex Jinpeng WangYixiao GeGuanyu CaiRui YanXudong LinYing ShanXiaohu QieMike Zheng ShouPublished in: CoRR (2021)
Keyphrases
- content based indexing
- video indexing
- video sequences
- multimedia
- multimedia information
- video data
- multimedia documents
- object motion
- video content
- image retrieval
- d objects
- object tracking
- video frames
- video streams
- information retrieval
- multimedia search
- cut detection
- object model
- video database
- multimedia databases
- video search
- video retrieval
- multimedia data
- multiple objects
- video objects
- training set
- relevance feedback
- combining information from multiple
- content based video
- news video
- pre trained
- video analysis
- natural language
- moving objects
- programming language
- retrieval systems
- complex objects
- object detectors
- language learning
- retrieval model
- video scene
- video dataset
- test collection
- training examples
- temporal continuity
- video surveillance
- video clips
- audio visual content