Related papers: Harnessing Perceptual Adversarial Patches for Crow…

In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map…

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…

Autonomous vehicles are typical complex intelligent systems with artificial intelligence at their core. However, perception methods based on deep learning are extremely vulnerable to adversarial samples, resulting in security accidents. How…

Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Recent works on adversarial examples for image classification focus on directly modifying pixels with minor perturbations. The small perturbation requirement is imposed to ensure the generated adversarial examples being natural and…

Recently, crowd counting using supervised learning achieves a remarkable improvement. Nevertheless, most counters rely on a large amount of manually labeled data. With the release of synthetic crowd data, a potential alternative is…

Adversarial patch is one of the important forms of performing adversarial attacks in the physical world. To improve the naturalness and aggressiveness of existing adversarial patches, location-aware patches are proposed, where the patch's…

This study enhances a crowd density estimation algorithm originally designed for image-based analysis by adapting it for video-based scenarios. The proposed method integrates a denoising probabilistic model that utilizes diffusion processes…

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…

Crowd scene analysis has received a lot of attention recently due to the wide variety of applications, for instance, forensic science, urban planning, surveillance and security. In this context, a challenging task is known as crowd…

Generalization performance of trained computer vision systems that use computer graphics (CG) generated data is not yet effective due to the concept of 'domain-shift' between virtual and real data. Although simulated data augmented with a…

Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis,…

Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information.…

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…

If a robot can predict crowds in parts of its environment that are inaccessible to its sensors, then it can plan to avoid them. This paper proposes a fast, online algorithm that learns average crowd densities in different areas. It also…

Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning. However, it is well-known that deep learning models lack the robustness to…