Counting in the Wild

By Carlos Arteta, Victor S. Lempitsky, Andrew Zisserman. 2016

317 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications, 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 Artificial Intelligence

In Computer Science Applications

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Features by Watching Objects Move (2016, methodology): “Similar techniques have been successfully explored earlier in segmentation [3, 22].”
Representation Learning by Learning to Count (2017, methodology): “There are methods to count humans in crowds [4, 42, 8], cars [28], and penguins [2].”
Counting Vehicles with Deep Learning in Onboard UAV Imagery (2019, background): “In [6] authors count Antarctic penguins from images captured by smart cameras with the intention of monitoring the population of the continent.”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, background): “…and counting, they however cover only traditional methods that use hand-crafted features and do not take into account the recent advancements driven primarily by CNN-based approaches [87, 39, 113, 11, 85, 97, 4, 98, 111, 107, 70, 88] and creation of new challenging crowd datasets [106, 107, 111].”
FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation (2019, background): “From top to bottom: android robot; the river from UC Merced Land Use Dataset [37]; a large cell image cropped into patches; herds of sheep; penguin from Oxford penguin counting dataset [1]; flock of wild goose; different images of fields of sunflower depict various scales in the presence of occlusio”
Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (2019, methodology): “Our application results on the penguin dataset [64].”
Understanding Traffic Density from Large-Scale Web Camera Data (2017, methodology): “[2] does not specifically solve the large perspective and object scale variation problems.”
Computational bioacoustics with deep learning: a review and roadmap (2021, methodology): “Counting and density estimation using DL has been explored for image data (e.g. Arteta et al. (2016)), a kind of highly nonlinear regression task.”
Context-Aware Crowd Counting (2018, background): “The same can be said about methods that count objects instead of people [1, 2, 8].”
Improving Object Counting with Heatmap Regulation (2018, background): “Extensions to this basic idea are provided in [11,12,13,14,15].”
Bayesian Loss for Crowd Count Estimation With Point Supervision (2019, background): “…potentials to handle similar tasks in other domains, includ-∗ ing estimating the number of vehicles in trafﬁc congestion [29, 30, 56, 14, 28], counting the cells and bacteria from microscopic images [20, 42, 44, 45, 8], and animal crowd estimations for ecological survey [27, 1, 18], to name a few.”
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild (2020, background): “Counting objects and people in images [3, 7, 24, 28, 49] is an active area in computer vision.”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “Recent advances in CNNs have been exploited for the task of crowd counting and these methods [4, 5, 6, 7, 7, 22, 23, 52, 53, 54, 55, 56] have demonstrated significant improvements over the traditional methods.”
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (2018, methodology): “CNN based approaches for crowd counting include [16], [29], [30], [19], [2].”
MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond (2021, background): “…for specialized objects has a number of practical applications (Marsden et al., 2018), including but are not limited to cell counting (Xie et al., 2018), crowd counting (Sindagi & Patel, 2017), vehicle counting (Onoro-Rubio & L´opez-Sastre, 2016), wild-life counting (Arteta et al., 2016), etc .”
Where are the Blobs: Counting by Localization with Point Supervision (2018, methodology): “Our benchmark uses datasets representing different settings for object counting: Mall [15], UCSD [16], and ShanghaiTech B [17] as crowd datasets; MIT Traffic [18], and Park lot [5] as surveillance datasets; Trancos [6] as a traffic monitoring dataset; and Penguins [1] as a population monitoring data”