Probabilistic Joint Image Segmentation and Labeling

By Adrian Ion, João Carreira, Cristian Sminchisescu. 2011

44 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Is stuff easier than things? Several works found that stuff is easier to segment than things [50, 28, 36, 51, 53, 62, 60, 63].”
Feedforward semantic segmentation with zoom-out features (2014, background): “Such models incorporate local evidence in unary potentials, while interactions between label assignments are captured by pairwise and possibly higher-order potentials.”
Training Deep Networks with Structured Layers by Matrix Backpropagation (2015, methodology): “Second-Order Pooling is one of the competitive hand-designed feature descriptors for regions [9] used in the top-performing method of the PASCAL VOC semantic segmentation, comp. 5 track [56, 57].”
Matrix Backpropagation for Deep Networks with Structured Layers (2015, methodology): “Second-Order Pooling is one of the competitive handdesigned feature descriptors for regions [6] used in the top-performing method of the PASCAL VOC semantic segmentation, comp. 5 track [21] [27].”
Semantic segmentation using regions and parts (2012, methodology): “VOC(%) [18] [10] [21] [5] SRL UC3M TTI [23] [9] FULL FULL”
The Pascal Visual Object Classes Challenge: A Retrospective (2014, methodology): “Pa-rameter learning was achieved using the method of Ion et al (2011b).”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, background): “[1], [79] as well as for multiregion image segmentation [3], [4] and cosegmentation [80].”