Abstract | ||
---|---|---|
In the last few years, substantially different approaches have been adopted for segmenting and detecting "things" (object categories that have a well defined shape such as people and cars) and "stuff" (object categories which have an amorphous spatial extent such as grass and sky). This paper proposes a framework for scene understanding that relates both things and stuff by using a novel way of modeling high order potentials. This representation allows us to enforce labelling consistency between hypotheses of detected objects (things) and image segments (stuff) in a single graphical model. We show that an efficient graph-cut algorithm can be used to perform maximum a posteriori (MAP) inference in this model. We evaluate our method on the Stanford dataset [1] by comparing it against state-of-the-art methods for object segmentation and detection. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33885-4_30 | ECCV Workshops (3) |
Keywords | Field | DocType |
object segmentation,efficient graph-cut algorithm,high order potential,image segment,single graphical model,amorphous spatial extent,different approach,object category,high-order potential modeling,relating thing,stanford dataset,labelling consistency | Conditional random field,Computer vision,Market segmentation,Pattern recognition,Inference,Computer science,Segmentation,Artificial intelligence,Spatial extent,Maximum a posteriori estimation,Graphical model | Conference |
Volume | ISSN | Citations |
7585 | 0302-9743 | 10 |
PageRank | References | Authors |
0.74 | 18 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Byung-soo Kim | 1 | 123 | 14.14 |
Min Sun | 2 | 1083 | 59.15 |
Pushmeet Kohli | 3 | 7398 | 332.84 |
Silvio Savarese | 4 | 3975 | 161.69 |