Related papers: Crowd Density Estimation using Novel Feature Descr…
Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just counting numbers for the whole crowd scene, which brings…
With multiple crowd gatherings of millions of people every year in events ranging from pilgrimages to protests, concerts to marathons, and festivals to funerals; visual crowd analysis is emerging as a new frontier in computer vision. In…
In this work, we use the Belief Function Theory which extends the probabilistic framework in order to provide uncertainty bounds to different categories of crowd density estimators. Our method allows us to compare the multi-scale…
Research in neural networks in the field of computer vision has achieved remarkable accuracy for point estimation. However, the uncertainty in the estimation is rarely addressed. Uncertainty quantification accompanied by point estimation…
We present a novel procedural framework to generate an arbitrary number of labeled crowd videos (LCrowdV). The resulting crowd video datasets are used to design accurate algorithms or training models for crowded scene understanding. Our…
While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we…
Perspective distortions and crowd variations make crowd counting a challenging task in computer vision. To tackle it, many previous works have used multi-scale architecture in deep neural networks (DNNs). Multi-scale branches can be either…
We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale…
Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The…
In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference (BIGD). In an image patch, we randomly sample multi-scale block pairs and utilize the intensity and gradient differences…
Heavy occlusion and dense gathering in crowd scene make pedestrian detection become a challenging problem, because it's difficult to guess a precise full bounding box according to the invisible human part. To crack this nut, we propose a…
Modern, state-of-the-art deep learning approaches yield human like performance in numerous object detection and classification tasks. The foundation for their success is the availability of training datasets of substantially high quantity,…
Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main challenge of…
In recent years, vision-based crowd analysis has been studied extensively due to its practical applications in real world. In this paper, we formulate a novel crowd analysis problem, in which we aim to predict the crowd distribution in the…
Sentiment classification is a fundamental task in content analysis. Although deep learning has demonstrated promising performance in text classification compared with shallow models, it is still not able to train a satisfying classifier for…
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers. We address the inference and learning problems using such a crowdsourced dataset with noise. Due to the nature of…
Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited information of RGB images and cannot well discover…
Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representations, they require some labeled data to map these features to…
In this paper, a novel Unified Multi-Task Learning Framework of Real-Time Drone Supervision for Crowd Counting (MFCC) is proposed, which utilizes an image fusion network architecture to fuse images from the visible and thermal infrared…
Human identification is a much attention problem in computer vision. Gender classification plays an important role in human identification as preprocess step. So far, various methods have been proposed to solve this problem. Absolutely,…