Shape Sharing for Object Segmentation

By Jaechul Kim, Kristen Grauman. 2012

80 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

What Makes for Effective Detection Proposals? (2015, neutral): “Grouping proposal methods attempt to generate multiple (possibly overlapping) segments that are likely to correspond to objects.”
Lifting Object Detection Datasets into 3D (2015, methodology): “The ﬁrst step of our algorithm is to estimate the camera viewpoint for each of the instances using the factorization based rigid structure-from-motion algorithm of Marques and Costeira [53].”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “Top: original image, instance-level ground truth from COCO and our multiscale hierarchical segmentation.”
SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning (2013, methodology): “Category-independent matching ignores the class label of training exemplars and attempts to match either regions [12], windows [13], or entire images [19], without regard to detected objects.”
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors (2019, methodology): “In addition to grouping, some object segmentation works have simultaneously used shape priors as unaries in probabilitic framework [1, 47, 20], augmented proposals [7], or as top-down prior to help grouping [46, 24, 3].”
RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions (2014, methodology): “Without supervision, systems such as [9, 6, 19, 34, 31] are able to generate a pool of overlapping segment proposals, where most foreground objects are captured by at least one segment from the pool.”
Salient object detection: A survey (2014, background): “by ﬁgure-ground segmenting the image are combined to form object proposals in a recent work [182]. Alternatively, object proposals can be generated by leveraging an auxiliary dataset. Kim and Grauman [179] introduce a global category-independent shape prior for object proposal generation. By perform”
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network (2016, methodology): “More related to our work is generating segmented object proposals [4, 10, 14, 24, 26, 29, 43].”
Boosting Object Proposals: From Pascal to COCO (2015, background): “It currently has become an active topic of research in computer vision [18, 4, 22, 15, 25, 17, 6, 10].”
Multiscale Combinatorial Grouping (2014, background): “[10] Shape sharing [15] Regions and parts [3] Selective search [26] Sel.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2017, background): “[11], [15], [16], [6], [11], [17].”
Scene Parsing with Object Instances and Occlusion Ordering (2014, background): “The form of our object potentials is inspired by [12].”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, methodology): “We take inspiration from recent work that segments objects from images using silhouettes learned from different object classes [34].”
Data-Driven Objectness (2015, unknown): “[14] also is based on a similar observation that regularity among objects can be helpful for separating generic objects from background.”
Multi-instance object segmentation with occlusion handling (2015, background): “Recent years have witnessed significant progress in bottom-up object segmentation algorithms [25, 7, 4, 35].”