From Semi-supervised to Transfer Counting of Crowds

Loy, Chen Change; Gong, Shaogang; Xiang, Tao

doi:10.1109/iccv.2013.270

Cited by 118 publications

(67 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is believed that given a fixed number of labelling budget, the most representative frames (in the sense of covering different crowd densities/counts) are the most useful ones to label. This brings in a chicken-and-egg problem [37], without labelling all frames, how does one know which ones are representative? Intuitively, the diversity between the selected frames should be as large as possible.…”

Section: Semi-supervised Elastic Netmentioning

confidence: 99%

“…We evaluate the inductive inference performance [37] of SSEN which is the error rate on the "unlabelled data in the test partition". We examine the effect of labelled and unlabelled data by measuring the MSE performance across labelled set f10; 50; 100; 200; 400; 600g given unlabelled set f0; 200; 400; 800; 1000g on Peds1 and Peds2 datasets.…”

Section: Undersampled Srcmentioning

confidence: 99%

See 1 more Smart Citation

Robust people counting using sparse representation and random projection

Foroughi

Ray

Zhang

2015

Pattern Recognition

View full text Add to dashboard Cite

Section: Semi-supervised Elastic Netmentioning

confidence: 99%

Section: Undersampled Srcmentioning

confidence: 99%

Robust people counting using sparse representation and random projection

Foroughi

Ray

Zhang

2015

Pattern Recognition

View full text Add to dashboard Cite

“…Consequently, the learned regression model can be used to estimate the density map of any given image, and the corresponding object count is calculated as the integral of the density map. Different from other VOC methods [8], [5], [9], [10], [23], [11], [12], [2], [24], [13], [25], the DE-VOC methods yield object density maps that are useful for the analysis of object distributions across the whole image.…”

Section: A Related Workmentioning

confidence: 99%

Manifold-Based Visual Object Counting

Wang

Zou

Wang

2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Visual object counting (VOC) is an emerging area in computer vision which aims to estimate the number of objects of interest in a given image or video. Recently, object density based estimation method is shown to be promising for object counting as well as rough instance localization. However, the performance of this method tends to degrade when dealing with new objects and scenes. To address this limitation, we propose a manifold-based method for visual object counting (M-VOC), based on the manifold assumption that similar image patches share similar object densities. Firstly, the local geometry of a given image patch is represented linearly by its neighbors using a predefined patch training set, and the object density of this given image patch is reconstructed by preserving the local geometry using locally linear embedding. To improve the characterization of local geometry, additional constraints such as sparsity and non-negativity are also considered via regularization, nonlinear mapping, as well as kernel trick. Compared with the state-of-the-art VOC methods, our proposed M-VOC methods achieve competitive performance on seven benchmark datasets. Experiments verify that the proposed M-VOC methods have several favorable properties, such as robustness to the variation in the size of training dataset and image resolution, as often encountered in real-world VOC applications.

show abstract

“…For example, [13] proposed a system that elegantly combines SSL and MTL with active learning and manifold learning to share information across camera views. The boundaries between different types of transfer learning are also loose.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Model Adaptation for Crowd Counts

Liu

Vasconcelos

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

The problem of transfer learning is considered in the domain of crowd counting. A solution based on Bayesian model adaptation of Gaussian processes is proposed. This is shown to produce intuitive model updates, which are tractable, and lead to an adapted model (predictive distribution) that accounts for all information in both training and adaptation data. The new adaptation procedure achieves significant gains over previous approaches, based on multi-task learning, while requiring much less computation to deploy. This makes it particularly suited for the problem of expanding the capacity of crowd counting camera networks. A large video dataset for the evaluation of adaptation approaches to crowd counting is also introduced. This contains a number of adaptation tasks, involving information transfer across video collected by 1) a single camera under different scene conditions (different times of the day) and 2) video collected from different cameras. Evaluation of the proposed model adaptation procedure in this dataset shows good performance in realistic operating conditions.

show abstract

From Semi-supervised to Transfer Counting of Crowds

Cited by 118 publications

References 25 publications

Robust people counting using sparse representation and random projection

Robust people counting using sparse representation and random projection

Manifold-Based Visual Object Counting

Bayesian Model Adaptation for Crowd Counts

Contact Info

Product

Resources

About