BING: Binarized normed gradients for objectness estimation at 300fps

By Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, Philip H. S. Torr. Computational Visual Media, 2014

783 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/636cea485f77373ae18e32ac8e1c4e37555db5bd

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

In Industrial and Manufacturing Engineering

Citations in the corpus

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, methodology): “In terms of bounding box proposals, we compare also against SharpMask [39], DeepMask [40], EB [49], RPN [48] MCG and SCG [16], LPO [42], BING [50], SeSe [45], GLS [46], RIGOR [47], Obj [51], and RP [52].”
Richer Convolutional Features for Edge Detection (2016, background): “It is usually considered as a low-level technique, and varieties of high-level tasks have greatly benefited from the development of edge detection, such as object detection [17, 55], object proposal [9, 54, 60–62] and image segmentation [1, 3, 8, 56].”
Object Detection in 20 Years: A Survey (2019, positive): “After 2014, with the popularity of deep CNN in visual recognition, the top-down, learningbased approaches began to show more advantages in this problem [19], [75], [76].”
Visual Grounding Via Accumulated Attention (2020, background): “There are also many faster but less accurate object detectors, such as MultiBox [55], BING [56], and Selective Search [57], where they have to increase the number of proposals to improve the recall rate.”
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes (2018, methodology): “detection performance is shown in [48] for a lot of different proposal methods like selective search [49], MCG [50] and BING [51].”
Multi-level Fusion Based 3D Object Detection from Monocular Images (2018, methodology): “The widely-used ones include BING [5], Selective Search [35], EdgeBoxes [39], Deep-Mask [27, 28] and RPN [31].”
Attend and Imagine: Multi-Label Image Classification With Visual Attention and Recurrent Neural Networks (2019, methodology): “To extract regions from images, previous studies always use the existing region proposal extraction algorithms and their pre-extracted regions, for example BING [47], Objectness Measure [49], Multiscale Combinatorial Grouping (MCG) [50], etc.”
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, methodology): “, [35] and [67] for OD, [88] and [89] for SOD, and [54] and [90] for COD).”
MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning (2020, methodology): “In detail, we ﬁrst initialize an objectness map by setting locations corresponding to the top three object proposals returned by BING [6] to 1 and the rest to 0.5; then, we initialize a motion map as the normalized optical ﬂow magnitude.”
Multi-label Image Recognition by Recurrently Discovering Attentional Regions (2017, background): “A batch of hypothesis regions are first produced by either exploiting bottom-up image cues [25] or casting extra detectors [4], and these regions are assumed to contain all possible foreground objects in the image.”
Attentive Systems: A Survey (2017, methodology): “On the one hand, object hypotheses generation approaches consider saliency as a useful cue for measuring objectness of a region (Alexe et al. 2012; Cheng et al. 2014; Krähenbühl and Koltun 2014; Zitnick and Dollár 2014).”
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (2015, methodology): “, superpixels (-sppxl), BING [45] boxes (-bb) and MCG [46] segmentations (-seg), are utilized for post-processing to further boost the segmentation results.”
Pixel Difference Networks for Efficient Edge Detection (2021, background): “boundaries play an important role in various higher-level computer vision tasks such as object recognition and detection [29, 11], object proposal generation [6, 54], image editing [10], and image segmentation [41, 4].”
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (2017, result): “A number of recent works prove that deep networks-based region proposal methods have surpassed the previous works [29, 4, 33, 9], which are based on the low-level cues, by a large margin.”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, methodology): “6 C ar # candidates 10 1 10 2 10 3 10 4 re c a ll a t Io U t h re s h o ld 0 .7 0 0.2 0.4 0.6 0.8 1 BING SS EB MCG MCG-D Ours-G Ours # candidates 10 1 10 2 10 3 10 4 re c a ll a t Io U t h re s h o ld 0 .7 0 0.2 0.4 0.6 0.8 1 BING SS EB MCG MCG-D Ours-G Ours # candidates 10 1 10 2 10 3 10 4 re c a l”
TORNADO: A Spatio-Temporal Convolutional Regression Network for Video Action Proposal (2017, background): “In contrast to static object proposal [4, 44, 29] which considers appearance cue only, action proposal in videos is much more complex and requires to integrate several components including (1) a fast and accurate candidate action box generator that can simultaneously consider appearance, motion and ”
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection (2017, result): “Our algorithm is superior than or on par with previous state-of-the-arts, including: BING (Cheng et al., 2014), EdgeBox (Zitnick and Dollar, 2014), GOP (Kra-henbuhl and Koltun, 2014), Selective Search (Uijlings et al., 2013), MCG (Arbel´aez et al., 2014), Endres (Endres and Hoiem, 2014), Prims (Man ”
Res2Net: A New Multi-Scale Backbone Architecture (2019, methodology): “age classiﬁcation [28], object detection [43], attention prediction [45], target tracking [63], action recognition [46], semantic segmentation [6], salient object detection [2], [24], object proposal [12], [43], skeleton extraction [67], stereo matching [42], and edge detection [37], [57]. Unsurpris”