Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction.
Luowei ZhouNathan LouisJason J. CorsoPublished in: BMVC (2018)
Keyphrases
- video objects
- weakly supervised
- video sequences
- superpixels
- object class
- object segmentation
- object tracking
- relation extraction
- object detectors
- topic models
- video content
- text mining
- object classes
- video frames
- object categories
- named entities
- object recognition
- d objects
- bounding box
- object motion
- partial occlusion
- image segmentation
- target object
- image retrieval
- semi supervised
- probabilistic model
- viewpoint