Stacked Pooling for Boosting Scale Invariance of Crowd Counting

Huang, Siyu; Li, Xi; Cheng, Zhi-Qi; Zhang, Zhongfei; Hauptmann, Alexander G.

doi:10.1109/icassp40776.2020.9053070

Cited by 19 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to show that the multiscale fusion module can effectively combine the information extracted from each branch in different densities we partition the images in the dataset into 5 different crowd density groups based on the number of people in each image, as in [18]. Consequently, Group 1 comprises the first 20 th percentile of density, Group 2 the second 20 th percentile, etc.…”

Section: Resultsmentioning

confidence: 99%

“…Datasets. We use two popular datasets, ShanghaiTech A and ShanghaiTech B [9], which are the most commonly used datasets in the area of crowd counting [8,10,2,11,20,18]. ShanghaiTech A contains 482 images with 241,677 total annotated heads.…”

Section: Methodsmentioning

confidence: 99%

“…After training the CNN, fine-tuning for each test image was carried out using the patches of training images with the same density rate. A stacked pooling approach was later proposed in [18] to solve the problem of counting variable head sizes in crowd images.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Multiscale Crowd Counting and Localization By Multitask Point Supervision

Zand¹,

Haleh²,

Farley³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them. In contrast to the relatively more popular density-based methods, our model uses point supervision to allow for crowd locations to be accurately identified. We test our model on two popular crowd counting datasets, ShanghaiTech A and B, and demonstrate that our method achieves strong results on both counting and localization tasks, with MSE measures of 110.7 and 15.0 for crowd counting and AP measures of 0.71 and 0.75 for localization, on ShanghaiTech A and B respectively. Our detailed ablation experiments show the impact of our multiscale approach as well as the effectiveness of the fusion

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale Crowd Counting and Localization By Multitask Point Supervision

Zand¹,

Haleh²,

Farley³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite the high coverage of surveillance cameras, human activity detections still rampage in places with a less sufficient police force, even directly under high-resolution cameras. Now, as the field of Artificial Intelligence and Computer Vision develops, new solutions such as Biometric Identification [3,4,5], Object Detection/Tracking [6,7,8], Crowd Density Analysis [9,10,11,12,13], and Action Recognition [14,15,16,17,18,19] have come to light, which in theory could automatically detect objects or actions. However, this seemingly useful technology remains confined to the laboratories as a consequence of deficiencies: 1) The narrow scope of the detection process (e.g., action-only or object-only) cripples the model accuracy, for it requires a comprehensive consideration of multiple factors to determine the nature of a situation.…”

Section: Introductionmentioning

confidence: 99%

HiFormer: Hierarchical transformer for grounded situation recognition

Pan

2024

ACE

View full text Add to dashboard Cite

The prevalence of monitoring video is critical to public safety, but existing Object Detection and Action Recognition models are overwhelmed by camera operators, unable to identify relevant events. In light of this, Grounding Situation Recognition (GSR) provides a practical solution to recognize the events in a surveillance video. That is, GSR can identify the noun entities (e.g., humans) and their actions (e.g., driving), and provide grounding frames for involved entities. Compared with Action Recognition and Object Detection, GSR is more in line with human cognitive habits, better allowing law enforcement agencies to understand the predictions. However, the crucial issue with most existing frameworks is the neglect of verb ambiguity, that is, superficially similar verbs but have distinct meanings (e.g. buying v.s. giving). Many existing works propose a two-stage model, which first blindly predicts the verb, and then uses this verb information to predict semantic roles. These frameworks ignore the importance of noun information during verb prediction, making them susceptible to misidentifications. To address this problem and better discern between ambiguous verbs, we propose HiFormer, a novel hierarchical transformer framework with direct and comprehensive consideration of similar verbs for each image, to more accurately identify the salient verb, semantic roles, and the grounding frames. Compared with the state-of-the-art models in Grounded Situation Recognition (SituFormer and CoFormer), HiFormer shows an advantage of over 35% and 20% on the Top-1 and Top-5 verb accuracy respectively, as well as 13% on the Top-1 Noun accuracy.

show abstract

“…While multiple pooling strategies have been proposed ( Graham, 2014 ; Gulcehre et al , 2014 ; He et al , 2014 ; Huang et al , 2018 ; Lee et al , 2016 ; Lu et al , 2015 ; Xie et al , 2015 ; Zeiler and Fergus, 2013 ; Zhai et al , 2017 ), max pooling and average pooling are popularly utilized in practical models ( Boureau et al , 2008 ; Jarrett et al , 2009 ; LeCun et al , 1990 , 1998 ). Max pooling is done by applying a max filter to subregions of the initial representation and global pooling utilizes an average filter.…”

Section: Introductionmentioning

confidence: 99%

Expectation pooling: an effective and interpretable pooling method for predicting DNA–protein binding

Luo¹,

Ding

et al. 2019

Bioinformatics

View full text Add to dashboard Cite

Motivation Convolutional neural networks (CNNs) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. While previous studies have built a connection between CNNs and probabilistic models, simple models of CNNs cannot achieve sufficient accuracy on this problem. Recently, some methods of neural networks have increased performance using complex neural networks whose results cannot be directly interpreted. However, it is difficult to combine probabilistic models and CNNs effectively to improve DNA–protein binding predictions. Results In this article, we present a novel global pooling method: expectation pooling for predicting DNA–protein binding. Our pooling method stems naturally from the expectation maximization algorithm, and its benefits can be interpreted both statistically and via deep learning theory. Through experiments, we demonstrate that our pooling method improves the prediction performance DNA–protein binding. Our interpretable pooling method combines probabilistic ideas with global pooling by taking the expectations of inputs without increasing the number of parameters. We also analyze the hyperparameters in our method and propose optional structures to help fit different datasets. We explore how to effectively utilize these novel pooling methods and show that combining statistical methods with deep learning is highly beneficial, which is promising and meaningful for future studies in this field. Availability and implementation All code is public in https://github.com/gao-lab/ePooling. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Stacked Pooling for Boosting Scale Invariance of Crowd Counting

Cited by 19 publications

References 20 publications

Multiscale Crowd Counting and Localization By Multitask Point Supervision

Multiscale Crowd Counting and Localization By Multitask Point Supervision

HiFormer: Hierarchical transformer for grounded situation recognition

Expectation pooling: an effective and interpretable pooling method for predicting DNA–protein binding

Contact Info

Product

Resources

About