Related papers: TransCrowd: weakly-supervised crowd counting with …
In real-world crowd counting applications, the crowd densities vary greatly in spatial and temporal domains. A detection based counting method will estimate crowds accurately in low density scenes, while its reliability in congested areas…
Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of…
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value.…
We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to…
Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal…
Crowd counting and localization are important in applications such as public security and traffic management. Existing methods have achieved impressive results thanks to extensive laborious annotations. This paper propose a novel…
Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the…
In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…
This paper proposes an adaptive auxiliary task learning based approach for object counting problems. Unlike existing auxiliary task learning based methods, we develop an attention-enhanced adaptively shared backbone network to enable both…
Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images. We introduce a new approach for solving weakly supervised semantic segmentation with deep Convolutional Neural…
In NLP, convolutional neural networks (CNNs) have benefited less than recurrent neural networks (RNNs) from attention mechanisms. We hypothesize that this is because the attention in CNNs has been mainly implemented as attentive pooling…
Graph convolution network (GCN) attracts intensive research interest with broad applications. While existing work mainly focused on designing novel GCN architectures for better performance, few of them studied a practical yet challenging…
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…
Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd…
In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses VGG16 as the backbone network and employs density map generated by the final…
Crowd counting plays a vital role in public safety, traffic regulation, and smart city management. However, despite the impressive progress achieved by CNN- and Transformer-based models, their performance often deteriorates when applied…
The initial seed based on the convolutional neural network (CNN) for weakly supervised semantic segmentation always highlights the most discriminative regions but fails to identify the global target information. Methods based on…
Background noise and scale variation are common problems that have been long recognized in crowd counting. Humans glance at a crowd image and instantly know the approximate number of human and where they are through attention the crowd…
Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power…