Related papers: Optimising CSRNet with parameter-free attention me…
Crowd instance segmentation is a crucial task with a wide range of applications, including surveillance and transportation. Currently, point labels are common in crowd datasets, while region labels (e.g., boxes) are rare and inaccurate. The…
Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces)…
Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…
Pedestrian detection and tracking in crowded video sequences have many applications, including autonomous driving, robot navigation and pedestrian flow analysis. However, detecting and tracking pedestrians in high-density crowds face many…
In this paper we propose ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification. To train and evaluate the proposed multi-objective technique, a new 100…
Crowd scene analysis receives growing attention due to its wide applications. Grasping the accurate crowd location (rather than merely crowd count) is important for spatially identifying high-risk regions in congested scenes. In this paper,…
Video surveillance using drones is both convenient and efficient due to the ease of deployment and unobstructed movement of drones in many scenarios. An interesting application of drone-based video surveillance is to estimate crowd…
Video-based person re-identification (ReID) is challenging due to the presence of various interferences in video frames. Recent approaches handle this problem using temporal aggregation strategies. In this work, we propose a novel Context…
The existing crowd counting models require extensive training data, which is time-consuming to annotate. To tackle this issue, we propose a simple yet effective crowd counting method by utilizing the Segment-Everything-Everywhere Model…
Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task lies in the…
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…
Current crowd-counting models often rely on single-modal inputs, such as visual images or wireless signal data, which can result in significant information loss and suboptimal recognition performance. To address these shortcomings, we…
The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features. However, these attention mechanisms ignore an implicit sub-task of…
Vision-based automatic counting of people has widespread applications in intelligent transportation systems, security, and logistics. However, there is currently no large-scale public dataset for benchmarking approaches on this problem.…
Crowd estimation is a very challenging problem. The most recent study tries to exploit auditory information to aid the visual models, however, the performance is limited due to the lack of an effective approach for feature extraction and…
Forecasting the flow of crowds is of great importance to traffic management and public safety, yet a very challenging task affected by many complex factors, such as inter-region traffic, events and weather. In this paper, we propose a…
Crowd simulation is a central topic in several fields including graphics. To achieve high-fidelity simulations, data has been increasingly relied upon for analysis and simulation guidance. However, the information in real-world data is…
Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion. Many methods only focus on the local appearance features and they cannot handle the aforementioned…
A crowd density forecasting task aims to predict how the crowd density map will change in the future from observed past crowd density maps. However, the past crowd density maps are often incomplete due to the miss-detection of pedestrians,…
Understanding the movement patterns of objects (e.g., humans and vehicles) in a city is essential for many applications, including city planning and management. This paper proposes a method for predicting future city-wide crowd flows by…