Related papers: Multi-level Memory-augmented Appearance-Motion Cor…
Wear and tear detection in fleet and shared vehicle systems is a critical challenge, particularly in rental and car-sharing services, where minor damage, such as dents, scratches, and underbody impacts, often goes unnoticed or is detected…
While the BD-rate performance of recent learned video codec models in both low-delay and random-access modes exceed that of respective modes of traditional codecs on average over common benchmarks, the performance improvements for…
This review article surveys the current progresses made toward video-based anomaly detection. We address the most fundamental aspect for video anomaly detection, that is, video feature representation. Much research works have been done in…
While generic object detection has achieved large improvements with rich feature hierarchies from deep nets, detecting small objects with poor visual cues remains challenging. Motion cues from multiple frames may be more informative for…
Object slip perception is essential for mobile manipulation robots to perform manipulation tasks reliably in the dynamic real-world. Traditional approaches to robot arms' slip perception use tactile or vision sensors. However, mobile robots…
Recent advances in unsupervised anomaly detection (UAD) have shifted from single-class to multi-class scenarios. In such complex contexts, the increasing pattern diversity has brought two challenges to reconstruction-based approaches: (1)…
Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skeleton sequences. We propose a holistic representation of…
Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it has been a common practice to learn normality under the…
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model…
The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven classification-based anomaly detection based on the sensor data collected in manufacturing processes.…
Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study…
Automatic fall detection is a vital technology for ensuring the health and safety of people. Home-based camera systems for fall detection often put people's privacy at risk. Thermal cameras can partially or fully obfuscate facial features,…
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…
Event cameras rely on motion to obtain information about scene appearance. This means that appearance and motion are inherently linked: either both are present and recorded in the event data, or neither is captured. Previous works treat the…
Video Anomaly Detection (VAD) is essential for computer vision research. Existing VAD methods utilize either reconstruction-based or prediction-based frameworks. The former excels at detecting irregular patterns or structures, whereas the…
Anomaly detection consists in identifying, within a dataset, those samples that significantly differ from the majority of the data, representing the normal class. It has many practical applications, e.g. ranging from defective product…
Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the conventional pixel reconstruction objective, which biases models…
Video anomaly detection is a challenging task due to the lack in approaches for representing samples. The visual representations of most existing approaches are limited by short-term sequences of observations which cannot provide enough…
Due to the problem of performance constraints of unsupervised video object detection, its large-scale application is limited. In response to this pain point, we propose another excellent method to solve this problematic point. By…
Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn "mapping…