Egocentric Video-Language Pretraining.
Kevin Qinghong LinAlex Jinpeng WangMattia SoldanMichael WrayRui YanEric Zhongcong XuDifei GaoRong-Cheng TuWenzhe ZhaoWeijie KongChengfei CaiHongfa WangDima DamenBernard GhanemWei LiuMike Zheng ShouPublished in: CoRR (2022)
Keyphrases
- video content
- video summarization
- multimedia
- video frames
- programming language
- video streams
- video sequences
- real time
- video data
- video database
- visual saliency
- natural language
- event recognition
- language learning
- real time video
- video clips
- visual data
- video images
- online video
- video segments
- target language
- digital video
- video segmentation
- video retrieval
- key frames
- activity recognition
- information retrieval
- neural network
- data sets