Bottleneck Identification to Semantic Segmentation of Industrial 3D Point Cloud Scene via Deep Learning.
Romain CazorlaLine PoinelPanagiotis PapadakisCédric BuchePublished in: IJCAI (2021)
Keyphrases
- deep learning
- semantic segmentation
- weakly supervised
- scene classification
- superpixels
- multiple images
- object detectors
- object recognition
- object class
- input image
- unsupervised learning
- video sequences
- machine learning
- visual words
- topic models
- image classification
- conditional random fields
- multiscale
- image set
- single image
- relation extraction
- image patches
- object segmentation
- semi supervised
- multiple objects
- image representation
- object detection