Related papers: DVD: A Comprehensive Dataset for Advancing Violenc…
Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene…
Ensuring traffic safety and mitigating accidents in modern driving is of paramount importance, and computer vision technologies have the potential to significantly contribute to this goal. This paper presents a multi-modal Vision…
Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain…
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…
Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus…
Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Preparation and training of deploy-able deep learning…
Event cameras, or Dynamic Vision Sensor (DVS), are very promising sensors which have shown several advantages over frame based cameras. However, most recent work on real applications of these cameras is focused on 3D reconstruction and…
Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting…
We describe the Gun Violence Database (GVDB), a large and growing database of gun violence incidents in the United States. The GVDB is built from the detailed information found in local news reports about gun violence, and is constructed…
Crime in the 21st century is split into a virtual and real world. However, the former has become a global menace to people's well-being and security in the latter. The challenges it presents must be faced with unified global cooperation,…
In many real-world problems, there is typically a large discrepancy between the characteristics of data used in training versus deployment. A prime example is the analysis of aggression videos: in a criminal incidence, typically suspects…
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action…
Reliable 4D object detection, which refers to 3D object detection in streaming video, is crucial for perceiving and understanding the real world. Existing open-set 4D object detection methods typically make predictions on a frame-by-frame…
Objects, in the real world, rarely occur in isolation and exhibit typical arrangements governed by their independent utility, and their expected interaction with humans and other objects in the context. For example, a chair is expected near…
RGB-D data is essential for solving many problems in computer vision. Hundreds of public RGB-D datasets containing various scenes, such as indoor, outdoor, aerial, driving, and medical, have been proposed. These datasets are useful for…
Real-time video surveillance, through CCTV camera systems has become essential for ensuring public safety which is a priority today. Although CCTV cameras help a lot in increasing security, these systems require constant human interaction…
Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world. However, existing systems for video analysis still lack the ability to handle the problems of scalability, expansibility and…
Fight detection in videos is an emerging deep learning application with today's prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper,…
Live video denoising under realistic, multi-component sensor noise remains challenging for applications such as autofocus, autonomous driving, and surveillance. We propose PocketDVDNet, a lightweight video denoiser developed using our model…
Semi-supervised video anomaly detection (VAD) is a critical task in the intelligent surveillance system. However, an essential type of anomaly in VAD named scene-dependent anomaly has not received the attention of researchers. Moreover,…