GrabCut in One Cut
Citations
3,653 citations
Cites methods from "GrabCut in One Cut"
...Although several new methods [53], [54] have been developed since the initial version of this work [1], to the best of our knowledge, our salient object segmentation results are still the best results reported on the most widely used benchmark [33]....
[...]
371 citations
145 citations
144 citations
86 citations
References
10,404 citations
"GrabCut in One Cut" refers methods in this paper
...Some well-known approaches to segmentation [25, 19, 6] consider model parameters as extra optimization variables in their segmentation energies....
[...]
5,670 citations
4,463 citations
3,723 citations
3,653 citations
"GrabCut in One Cut" refers background or methods or result in this paper
...Optimizing E3(S) results in precision = 91%, recall = 85% and F-measure = 86%, whereas incorporating the appearance term in E4(S) yields precision = 89%, recall = 89% and F-measure = 89%, which is comparable to the state-of-the-art results reported in literature [7](precision = 90%, recall = 90%, F-measure = 90%)....
[...]
...Salient objects usually have an appearance that is distinct from the background [1, 7, 17]....
[...]
...14 compares the performance of E3(S) and E4(S) with that of FT [1], CA [9], LC [24], HC [7] and RC [7] in terms of precision, recall and F-measure defined as...
[...]
...Note that our optimization requires one graph-cut only, rather than the iterated EM-style grab-cut refinement in [7]....
[...]
...Saliency segmentation results reported for dataset [1]: Precison-Recall and F-measure bars for E3(S), E4(S) are compared to FT[1], CA[9], LC[24], HC[7] and RC[7]....
[...]