Show, Read and Reason: Table Structure Recognition with Flexible Context Aggregator.
Hao LiuXin LiBing LiuDeqiang JiangYinsong LiuBo RenRongrong JiPublished in: ACM Multimedia (2021)
Keyphrases
- recognition rate
- object recognition
- recognition accuracy
- real time
- structural analysis
- pattern recognition
- action recognition
- context sensitive
- visual recognition
- shape recognition
- unsupervised learning
- handwritten digits
- contextual information
- logical structure
- activity recognition
- active vibration control
- context aware
- human activities
- feature extraction
- three dimensional
- website
- image processing
- information systems
- neural network
- data sets