Prime Object Proposals with Randomized Prim's Algorithm

By Santiago Manen, Matthieu Guillaumin, Luc Van Gool. 2013

310 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

ImageNet Large Scale Visual Recognition Challenge (2014, background): “7 The Third Research Institute of the Ministry of Public Security Jie Shao, Xiaoteng Zhang, JianYing Zhou, Jian Wang, Jian Chen, Yanfeng Shang, Wenfei Wang, Lin Mei, Chuanping Hu (Girshick et al. 2014; Manen et al. 2013; Howard 2014)”
What Makes for Effective Detection Proposals? (2015, methodology): “, by using multiple low level segmentations [19], [26], [29] or starting with an over-segmentation and randomising the merge process [26].”
Learning Open-World Object Proposals without Learning to Classify (2021, background): “In early works, the emphasis was on category-independent object proposals [2, 4, 18, 39, 74], where the goal is to identify instances of all objects in the image irrespective of their category.”
Scalable, High-Quality Object Detection (2014, background): “Given the recent success of novel sophisticated proposal generation methods [1, 22, 24, 14, 3, 10, 2, 11], the possibility of directly learned methods overtaking engineered meth-ods might seem far fetched at ﬁrst glance.”
Learning visual groups from co-occurrences in space and time (2015, methodology): “…straightforward approach to this problem would be to train a supervised clas-siﬁer to predict indicator variable Q ∈ { 0 , 1 , where Q = 1 iff A and B lie on the same object Manen et al. (2013). this paper to } Throughout , we use Q indicate the property that A and B share the same semantic label.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “We add the state of the art in boxes proposals [26], [27], [25], and [16] to the comparison.”
Self-taught object localization with deep networks (2014, methodology): “Objectness methods [2, 6, 30, 4, 3, 16, 36, 25, 21, 26, 32, 14] aim at generating bounding boxes that yield high recall for a high number of candidates, i.”
Unsupervised Object Discovery and Tracking in Video Collections (2015, background): “We consider a set of videos v , each consisting of T frames (images) v t ( t = 1 , . . . , T ), and denote by R ( v t ) a set of candidate regions identiﬁed in v t by some separate bottom-up region proposal process [21].”
How good are detection proposals, really? (2014, methodology): “RandomizedPrim’s [22] is similar to SelectiveSearch in terms of features to merge low-level superpixels.”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “(a-b) Given two images and their multi-scale region proposals [34], the proposed matching algorithm efficiently evaluates candidate matches between two sets of regions (2205×1044 regions in this example) and produce match confidences for them.”
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection (2017, background): “In recent years, the emergence of object proposal algorithms (Uijlings et al., 2013; Manén et al., 2013; Arbeláez et al., 2014; Hayder et al., 2016; Kong et al., 2016; Ghodrati et al., 2016; Chavali et al., 2016; Sun et al., 2016; Li et al., 2017a) have significantly boosted the development of…”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “Manen et al. [104] proposed a similar method which exploits merging randomized trees with learned similarity metrics.”
Object localization in ImageNet by looking out of the window (2015, methodology): “This uses the same candidate windows [23] and features we use.”
Recent Advances in Deep Learning for Object Detection (2019, background): “Manen et al. [83] proposed a similar idea to merge superpixels.”
Unsupervised Image Matching and Object Discovery as Optimization (2019, methodology): “[12] is totally unsupervised once given the region proposals, the randomized Prim’s algorithm itself is supervised [33].”
Object detection by labeling superpixels (2015, methodology): “Recently, many methods are further proposed to get more compact and efficient object proposals, including the unsupervised approach [23, 50, 2] and the supervised approach [1, 62, 6, 36].”
Geodesic Object Proposals (2014, methodology): “[16] vary the proposal budget N from 0 to 10, 000.”