Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Nasrollahi, Kamal"'
In this study, we formulate the task of Video Anomaly Detection as a probabilistic analysis of object bounding boxes. We hypothesize that the representation of objects via their bounding boxes only, can be sufficient to successfully identify anomalou
Externí odkaz:
http://arxiv.org/abs/2407.06000
As the global population ages, the number of fall-related incidents is on the rise. Effective fall detection systems, specifically in healthcare sector, are crucial to mitigate the risks associated with such events. This study evaluates the role of v
Externí odkaz:
http://arxiv.org/abs/2404.08088
Autor:
Madan, Neelu, Ristea, Nicolae-Catalin, Nasrollahi, Kamal, Moeslund, Thomas B., Ionescu, Radu Tudor
Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches (tokens) in
Externí odkaz:
http://arxiv.org/abs/2308.16572
Autor:
Madan, Neelu, Ristea, Nicolae-Catalin, Ionescu, Radu Tudor, Nasrollahi, Kamal, Khan, Fahad Shahbaz, Moeslund, Thomas B., Shah, Mubarak
Anomaly detection has recently gained increasing attention in the field of computer vision, likely due to its broad set of applications ranging from product fault detection on industrial production lines and impending event detection in video surveil
Externí odkaz:
http://arxiv.org/abs/2209.12148
Autor:
Barbalau, Antonio, Ionescu, Radu Tudor, Georgescu, Mariana-Iuliana, Dueholm, Jacob, Ramachandra, Bharathkumar, Nasrollahi, Kamal, Khan, Fahad Shahbaz, Moeslund, Thomas B., Shah, Mubarak
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted the attention of many researchers. In this work, we revisit the self-s
Externí odkaz:
http://arxiv.org/abs/2207.08003
Autor:
Selva, Javier, Johansen, Anders S., Escalera, Sergio, Nasrollahi, Kamal, Moeslund, Thomas B., Clapés, Albert
Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated wh
Externí odkaz:
http://arxiv.org/abs/2201.05991
Autor:
Ristea, Nicolae-Catalin, Madan, Neelu, Ionescu, Radu Tudor, Nasrollahi, Kamal, Khan, Fahad Shahbaz, Moeslund, Thomas B., Shah, Mubarak
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detecti
Externí odkaz:
http://arxiv.org/abs/2111.09099
Most existing face image Super-Resolution (SR) methods assume that the Low-Resolution (LR) images were artificially downsampled from High-Resolution (HR) images with bicubic interpolation. This operation changes the natural image characteristics and
Externí odkaz:
http://arxiv.org/abs/2102.03113
Autor:
Deliège, Adrien, Cioppa, Anthony, Giancola, Silvio, Seikavandi, Meisam J., Dueholm, Jacob V., Nasrollahi, Kamal, Ghanem, Bernard, Moeslund, Thomas B., Van Droogenbroeck, Marc
Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual
Externí odkaz:
http://arxiv.org/abs/2011.13367