Actor-agnostic Multi-label Action Recognition with Multi-modal Query.
Anindya MondalSauradip NagJoaquin M. PradaXiatian ZhuAnjan DuttaPublished in: ICCV (Workshops) (2023)
Keyphrases
- multi modal
- action recognition
- multi label
- image annotation
- multi label classification
- text categorization
- image classification
- bag of words
- human actions
- video search
- max margin
- graph cuts
- text classification
- binary classification
- automatic image annotation
- computer vision
- web images
- relevance feedback
- high dimensional
- semantic concepts
- class labels
- image search
- keywords
- visual features
- image collections
- visual words
- data mining
- markov random field
- information retrieval