Simultaneous detection and segmentation for generic objects

Torrent, Albert; Lladó, Xavier; Freixenet, Jordi; Torralba, Antonio

doi:10.1109/icip.2011.6116636

Cited by 4 publications

(2 citation statements)

References 106 publications

(187 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Table II shows the comparison of performance for the Weizmann horse dataset. At detection EER, we achieve better detection results and improved the segmentation quality by 10.1% compared to the recent related method of Torrent et al [16]. We also get higher segmentation quality than the early bottom-up segmentation method of Ren et al [17].…”

Section: Resultsmentioning

confidence: 64%

See 1 more Smart Citation

Combined Object Detection and Segmentation

Vansteenberge¹,

Minoh²

2013

IJMLC

View full text Add to dashboard Cite

We develop a method for combined object detection and segmentation in natural scene. In our approach segmentation and detection are considered as two faces of the same coin that should be combined into a single framework. There are two main steps in our strategy. First we focus on the learning of a visual vocabulary that efficiently encompasses objects’ appearance, spatial configuration and underlying segmentation. This vocabulary is used within a Hough voting framework to produces object’s configuration. The second step consists in searching for valid objects’ configurations by interpreting and scoring them in terms of both detection and segmentation. This allows us to prune false detections and hallucinated object-like segmentation. Experiments show the advantage of the combined approach and the improvements over recent related methods

show abstract

Section: Resultsmentioning

confidence: 64%

“…Fscore Det. EER Image Zhu [18] 89.2% 99.1% 228 Ren et al [17] 80.2% -172 Torrent et al [16] 69.1% 97.0% 262 RF Det. + Seg.…”

Section: Methodsmentioning

confidence: 99%