Multimodal Fusion with Cross-Modal Attention for Action Recognition in Still Images.
Jia-Hua TsaiWei-Ta ChuPublished in: MMAsia (2022)
Keyphrases
- action recognition
- cross modal
- image database
- bag of features
- human actions
- image retrieval
- multi modal
- activity recognition
- image data
- visual similarity
- computer vision
- three dimensional
- image collections
- image features
- bag of words
- image classification
- object recognition
- keypoints
- visual features
- image regions
- similarity search
- image annotation
- visual data