Interactive Object Counting

By Carlos Arteta, Victor S. Lempitsky, J. Alison Noble, Andrew Zisserman. 2014

189 citations recorded by the source corpus.

Subfields: Biophysics, 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 Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

DeepSetNet: Predicting Sets with Deep Neural Networks (2016, methodology): “It is important to bear in mind that unlike many existing approaches that learn to count [1, 5, 12, 20, 24, 35, 50, 51], our main goal is not object counting.”
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (2017, unknown): “There are also a number of density regression-based methods [23, 16, 5] which can estimate object counts by the density of a countable object and then aggregate over that density.”
Efficient Point Process Inference for Large-Scale Object Detection (2016, methodology): “However, unlike [21, 16, 1] where only the quantity of objects is estimated, our method returns also object locations which can be used for analysing object spatial distributions, or object tracking.”
Neural Arithmetic Logic Units (2018, background): “A widely studied task is counting objects in images [2, 4 ?”
Improving Object Counting with Heatmap Regulation (2018, background): “The authors in [12] enhance the approach of [10] by providing options to interactively receive dot annotations from the users and iteratively correcting the annotations via further visualization.”
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning (2016, background): “Most contemporary counting methods can be broadly categorized as a density estimator [14,15,16] or, detection instance counter [11,13,17].”
Incorporating Side Information by Adaptive Convolution (2017, background): “Most of the recent state-of-the-art object counting algorithms adopt the density estimation approach (Arteta et al. 2014; Fiaschi et al. 2012; Zhang et al. 2015, 2016; Onoro-Rubio and López-Sastre 2016; Sam et al. 2017; Sindagi and Patel 2017).”
Context-Aware Crowd Counting (2018, background): “The same can be said about methods that count objects instead of people [1, 2, 8].”
Towards Perspective-Free Object Counting with Deep Learning (2016, background): “In [3], the authors propose an interactive counting system, which simplifies the costly learning-to-count approach [6], proposing the use of a simple ridge regressor.”
Learning Short-Cut Connections for Object Counting (2018, methodology): “The size of the filter is chosen to be [4,4] for those features maps that are greater or equal to [24,24], while for those that are smaller we use a slightly reduced size of [3,3].”
Microscopy cell counting and detection with fully convolutional regression networks (2018, methodology): “1 N/A 3 .”
Learning to Count Leaves in Rosette Plants (2015, methodology): “To compare our performance with methods that do use such topological information, we adapt also two density-based methods to our application [4, 23].”
Counting in the Wild (2016, methodology): “The most common task in which dot-annotations are used is that of counting [1, 4, 8, 25], where they are used in combination with direct information about the spatial extent of the object in order to define object density maps that can be regressed.”
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation (2015, unknown): “[5] 1.”