Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes.
Jonathan J. Y. KimMartin UrschlerPatricia J. RiddleJörg S. WickerPublished in: CoRR (2022)
Keyphrases
- multi object
- visual features
- multiple objects
- semantic concepts
- low level features
- visual information
- image classification
- visual content
- visual appearance
- image retrieval
- human perception
- low level
- image annotation
- keywords
- low level visual features
- high level
- key frames
- human actions
- multi modal
- statistical shape model
- computer vision
- visual and textual features
- semantically meaningful
- image sequences