Related papers: Getting the Numbers Right$\unicode{x2014}$Modellin…

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of…

The field of object detection and understanding is rapidly evolving, driven by advances in both traditional CNN-based models and emerging multi-modal large language models (LLMs). While CNNs like ResNet and YOLO remain highly effective for…

Counting is a fundamental operation for various real-world visual tasks, requiring both object recognition and robust counting capabilities. Despite their advanced visual perception, large vision-language models (LVLMs) are known to…

The task of crowd counting in varying density scenes is an extremely difficult challenge due to large scale variations. In this paper, we propose a novel dual path multi-scale fusion network architecture with attention mechanism named…

Compared with single image based crowd counting, video provides the spatial-temporal information of the crowd that would help improve the robustness of crowd counting. But translation, rotation and scaling of people lead to the change of…

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…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…

Small Object Detection (SOD) poses significant challenges due to limited information and the model's low class prediction score. While Transformer-based detectors have shown promising performance, their potential for SOD remains largely…

While deep learning-based general object detection has made significant strides in recent years, the effectiveness and efficiency of small object detection remain unsatisfactory. This is primarily attributed not only to the limited…

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements…

Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…

Despite the growing success of Convolution neural networks (CNN) in the recent past in the task of scene segmentation, the standard models lack some of the important features that might result in sub-optimal segmentation outputs. The widely…

Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep representations. However, these methods cannot well cope with scene text due…

This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight…

In this paper we advance the state-of-the-art for crowd counting in high density scenes by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016). Producing an accurate and robust crowd…

Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method…

Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a…

This study proposes a semi-supervised co-training framework for object detection in densely packed retail environments, where limited labeled data and complex conditions pose major challenges. The framework combines Faster R-CNN (utilizing…