Related papers: Transformer-Based Dual-Optical Attention Fusion Cr…
The existing crowd counting methods usually adopted attention mechanism to tackle background noise, or applied multi-level features or multi-scales context fusion to tackle scale variation. However, these approaches deal with these two…
Crowd counting problem that counts the number of people in an image has been extensively studied in recent years. In this paper, we introduce a new variant of crowd counting problem, namely "Categorized Crowd Counting", that counts the…
Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based models, often…
3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer a question under that situation. However, existing methods…
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…
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the distribution of data points, plays an important role in…
Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning. Recent attempts to combine RGB frames and event streams have shown promise, yet they typically rely…
Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications. In this paper, we propose a novel method using an attention model to exploit head…
Recently, deep neural networks have made remarkable achievements in 3D point cloud classification. However, existing classification methods are mainly implemented on idealized point clouds and suffer heavy degradation of per-formance on…
Crowd counting and localization have become increasingly important in computer vision due to their wide-ranging applications. While point-based strategies have been widely used in crowd counting methods, they face a significant challenge,…
Event classification is inherently sequential and multimodal. Therefore, deep neural models need to dynamically focus on the most relevant time window and/or modality of a video. In this study, we propose the Multi-level Attention Fusion…
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with…
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…
Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution. However, further improvement tends to saturate mainly because of the confusing background…
Human attention mechanisms often work in a top-down manner, yet it is not well explored in vision research. Here, we propose the Top-Down Attention Framework (TDAF) to capture top-down attentions, which can be easily adopted in most…
Accurately segmenting blood vessels in retinal fundus images is crucial in the early screening, diagnosing, and evaluating some ocular diseases, yet it poses a nontrivial uncertainty for the segmentation task due to various factors such as…
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…
Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple…
Currently, for crowd counting, the fully supervised methods via density map estimation are the mainstream research directions. However, such methods need location-level annotation of persons in an image, which is time-consuming and…
Crowd counting in still images is a challenging problem in practice due to huge crowd-density variations, large perspective changes, severe occlusion, and variable lighting conditions. The state-of-the-art patch rescaling module (PRM) based…