Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Bakhtiarnia, Arian"'
Countless terms of service (ToS) are being signed everyday by users all over the world while interacting with all kinds of apps and websites. More often than not, these online contracts spanning double-digit pages are signed blindly by users who simp
Externí odkaz:
http://arxiv.org/abs/2409.00077
Autor:
Leporowski, Błażej, Bakhtiarnia, Arian, Bonnici, Nicole, Muscat, Adrian, Zanella, Luca, Wang, Yiming, Iosifidis, Alexandros
We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions. In addition, we propose a novel method named AVACA that combines visual
Externí odkaz:
http://arxiv.org/abs/2305.15084
The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting. Such resolutions are far beyond the memory and computation limits of current GPUs, and available deep neural network architectures and training proced
Externí odkaz:
http://arxiv.org/abs/2305.09271
Many deep learning tasks require annotations that are too time consuming for human operators, resulting in small dataset sizes. This is especially true for dense regression problems such as crowd counting which requires the location of every person i
Externí odkaz:
http://arxiv.org/abs/2301.12914
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to significant accuracy degradati
Externí odkaz:
http://arxiv.org/abs/2208.07075
Cameras in modern devices such as smartphones, satellites and medical equipment are capable of capturing very high resolution images and videos. Such high-resolution data often need to be processed by deep learning models for cancer detection, automa
Externí odkaz:
http://arxiv.org/abs/2207.13050
Images and video frames captured by cameras placed throughout smart cities are often transmitted over the network to a server to be processed by deep neural networks for various tasks. Transmission of raw images, i.e., without any form of compression
Externí odkaz:
http://arxiv.org/abs/2207.10155
Deploying deep neural networks (DNNs) on IoT and mobile devices is a challenging task due to their limited computational resources. Thus, demanding tasks are often entirely offloaded to edge servers which can accelerate inference, however, it also ca
Externí odkaz:
http://arxiv.org/abs/2205.11269
Publikováno v:
International Conference on Learning Representations, 2023
Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the overlap in
Externí odkaz:
http://arxiv.org/abs/2201.06268
Deep neural networks can be converted to multi-exit architectures by inserting early exit branches after some of their intermediate layers. This allows their inference process to become dynamic, which is useful for time critical IoT applications with
Externí odkaz:
http://arxiv.org/abs/2106.15183