High-performance video content recognition with long-term recurrent convolutional network for FPGA.
Xiaofan ZhangXinheng LiuAnand RamachandranChuanhao ZhugeShibin TangPeng OuyangZuofu ChengKyle RupnowDeming ChenPublished in: FPL (2017)
Keyphrases
- video content
- convolutional network
- convolutional neural networks
- video streams
- video data
- content based video
- video sequences
- video quality
- object recognition
- video retrieval
- video frames
- video summarization
- feature extractor
- coarse to fine
- key frames
- activity recognition
- video shots
- multimedia
- feature extraction
- recognition scheme
- search engine
- action recognition
- visual features
- object detection
- low level