Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning.
Tao JinSiyu HuangYingming LiZhongfei ZhangPublished in: CoRR (2019)
Keyphrases
- high order
- low rank
- cross modal
- higher order
- pairwise
- multi modal
- multimedia
- tensor decomposition
- visual data
- high dimensional data
- matrix factorization
- markov random field
- video sequences
- convex optimization
- linear combination
- distance measure
- pattern recognition
- missing data
- video frames
- object recognition
- visual recognition