Object Recognition by Sequential Figure-Ground Ranking

By João Carreira, Fuxin Li, Cristian Sminchisescu. 2011

123 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

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.”
Lifting Object Detection Datasets into 3D (2015, methodology): “We also bypass segmentation, another yet incompletely solved vision problem despite much recent progress [9], [10], and rely on ground truth silhouettes as input to our dense reconstruction engine which is based on a novel visual hull based algorithm.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, neutral): “Recently, this approach has dominated the Pascal segmentation challenge [6], [7], [8], improved object detection [9], ﬁne-grained categorization [10] and proven competitive in large-scale classiﬁcation [11].”
Laplacian Reconstruction and Refinement for Semantic Segmentation (2016, background): “, [1,2,3]) that relied on hand-designed features and recognizers trained from scratch.”
Semantic Segmentation with Second-Order Pooling (2012, methodology): “Prediction Learning Exp-χ(2) [18] (7 descript.”
Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation (2015, result): “We observe that approaches like [2,8,9], which focus on classifying bottomup region candidates using strong features on the region have obtained significantly better results than MRFbased methods [30].”
Reconstructing PASCAL VOC (2014, methodology): “We also bypass segmentation, another yet incompletely solved vision problem despite much recent progress [7, 6], and rely on ground truth silhouettes as input to our dense reconstruction”
Volumetric Semantic Segmentation Using Pyramid Context Features (2013, background): “[2, 8, 9] operate by classifying object candidates obtained by expensive bottom-up grouping.”
Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs (2016, methodology): “The SvrSegm method [57] which achieves 34.”
The Role of Context for Object Detection and Semantic Segmentation in the Wild (2014, background): “For both detection and segmentation, it has been shown that representing a region larger than an object itself leads to better performance [32, 6, 22, 8].”
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation (2016, background): “, [2,3,28]) that relied on hand-designed features and recognizers trained from scratch.”
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images (2013, background): “We observe that approaches like [4, 1], which focus on classifying bottom-up regions candidates using strong features on the region have obtained significantly better results than MRF-based methods [16].”
Amodal Instance Segmentation (2016, unknown): “A diverse range of approaches for this problem have been developed; earlier approaches extend CRF-based formulations [24,22,3], consider combining object detections with region proposals [15], scoring groupings of over-segmented regions [35], aggregating information from multiple foreground-backgrou”
Robust video segment proposals with painless occlusion handling (2015, background): “Holistic segment proposals can often cover entire objects in the image with excellent accuracy, hence shape and other global appearance features can be extracted from them, leading to better recognition accuracy.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2017, methodology): “Recently, this approach has dominated the PASCAL segmentation challenge [6], [7], [8], [9], improved object detection [10], fine-grained categorization [11] and proven competitive in large-scale classification [12].”
Video Segmentation by Tracking Many Figure-Ground Segments (2013, background): “These advances have made unsupervised segmentation applicable to difficult high-level tasks, such as semantic segmentation [23, 2, 10] and video saliency reasoning [19].”
Probabilistic Joint Image Segmentation and Labeling (2011, methodology): “Multiple chi-square kernels K(x, y) = exp(−γχ(2)(x, y)) are combined as in [28].”