Selective Search for Object Recognition

By Jasper R. R. Uijlings, K. V. D. Sande, Theo Gevers, Arnold M. W. Smeulders, Arnold W. M. Smeulders. 2013

5,664 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Fast R-CNN (2015, background): “There are two types of object detectors (roughly speaking): those that use a sparse set of “object proposals” ( e.g ., selective search [20]) and those that use a dense set , i.e . sliding window.”
Object Detection Networks on Convolutional Feature Maps (2015, methodology): “The result of “SVM on pool 5 ” is based on [13], for which the SVM is trained on the pool 5 features.”
ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “The winner of object detection task was UvA team, which utilized a new way of eﬃcient encoding (van de Sande et al., 2014) of densely sampled color descriptors (van de Sande et al., 2010) pooled using a multi-level spatial pyramid in a selective search framework (Uijlings et al., 2013).”
Caffe: Convolutional Architecture for Fast Feature Embedding (2014, methodology): “Girshick et al. [3] have combined Caﬀe together with techniques such as Selective Search [10] to eﬀectively perform simultaneous localization and recognition in natural images.”
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks (2013, methodology): “ng. This segmentation pre-processing or object proposal step has recently gained popularity in traditional computer vision to reduce the search space of position, scale and aspect ratio for detection [19, 2, 6, 29]. Hence an expensive classiﬁcation method can be applied at the optimal location in th”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “We followed the same protocol of submitting test results to the ILSVRC2013 evaluation server only twice, once with and once without bounding-box regression.”
Mask R-CNN (2017, methodology): “Related Work R-CNN: The Region-based CNN (R-CNN) approach [13] to bounding-box object detection is to attend to a manageable number of candidate object regions [38, 20] and evaluate convolutional networks [25, 24] independently on each RoI.”
Relation Networks for Object Detection (2017, background): “From the convolutional features and a sparse set of region proposals [48, 52, 38], a RoI pooling layer [24, 18, 23] extracts fixed resolution regional features (e.”
Fine-Grained Image Classification via Combining Vision and Language (2017, methodology): “First, we apply the selective search [43] to generate patches for each image.”
Unsupervised Visual Representation Learning by Context Prediction (2015, neutral): “ttle bus car cat chair cow table dog horse mbike person plant sheep sofa train tv mAP DPM-v5[16] 33.2 60.3 10.2 16.1 27.3 54.3 58.2 23 20 24.1 26.7 12.7 58.1 48.2 43.2 12 21.1 36.1 46 43.5 33.7 SS SPM[45] 43.5 46.5 10.4 12 9.3 49.4 53.7 39.4 12.5 36.9 42.2 26.4 47 52.4 23.5 12.11 29.9 36.3 42.2 48.8”
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression (2019, methodology): “[5] in RCNN parameterize the bounding box representation by predicting location and size offsets from a prior bounding box calculated using a selective search algorithm [23].”
UPSNet: A Unified Panoptic Segmentation Network (2019, background): “Beginning with the introduction of region-based CNN (R-CNN) [12], many early deep learning approaches to instance segmentation attacked the problem by casting the solution to instance segmentation as a two stage approach where a number of segment proposals are made, which is then followed by a votin”
SSD: Single Shot MultiBox Detector (2015, methodology): “In the most recent works like MultiBox [7,8], the Selective Search region proposals, which are based on low-level image features, are replaced by proposals generated directly from a separate deep neural network.”
End-to-End People Detection in Crowded Scenes (2015, methodology): “Currently, the best performing object detectors operate either by densely scanning the image in a sliding window fashion [17, 6, 27, 16], or by using a proposal mechanism such as [24, 21], and leveraging CNNs to classify a sparsified set of proposals [6].”
You Only Look Once: Unified, Real-Time Object Detection (2015, background): “Search [34] generates potential bounding boxes, a convolutional network extracts features, an SVM scores the boxes, a linear model adjusts the bounding boxes, and non-max suppression eliminates duplicate detections.”
Scalable Object Detection Using Deep Neural Networks (2013, methodology): “Another method is that of [8], using selective search [16] to propose 2000 candidate locations per image, extract toplayer features from a ConvNet and using a hard-negativetrained SVM to classify the locations into VOC classes.”
R-FCN: Object Detection via Region-based Fully Convolutional Networks (2016, methodology): “3 Related Work R-CNN [8] has demonstrated the effectiveness of using region proposals [28, 29] with deep networks.”