Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Doshi, Keval"'
Anomaly detection in videos is an important computer vision problem with various applications including automated video surveillance. Although adversarial attacks on image understanding models have been heavily investigated, there is not much work on
Externí odkaz:
http://arxiv.org/abs/2204.03141
While anomaly detection in time series has been an active area of research for several years, most recent approaches employ an inadequate evaluation criterion leading to an inflated F1 score. We show that a rudimentary Random Guess method can outperf
Externí odkaz:
http://arxiv.org/abs/2203.05167
Autor:
Doshi, Keval, Yilmaz, Yasin
While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is capable of c
Externí odkaz:
http://arxiv.org/abs/2203.05156
Autor:
Doshi, Keval, Yilmaz, Yasin
Due to its relevance in intelligent transportation systems, anomaly detection in traffic videos has recently received much interest. It remains a difficult problem due to a variety of factors influencing the video quality of a real-time traffic feed,
Externí odkaz:
http://arxiv.org/abs/2104.09758
Autor:
Doshi, Keval, Yilmaz, Yasin
Anomaly detection in videos has been attracting an increasing amount of attention. Despite the competitive performance of recent methods on benchmark datasets, they typically lack desirable features such as modularity, cross-domain adaptivity, interp
Externí odkaz:
http://arxiv.org/abs/2103.11299
Autor:
Doshi, Keval, Yilmaz, Yasin
Road damage detection is critical for the maintenance of a road, which traditionally has been performed using expensive high-performance sensors. With the recent advances in technology, especially in computer vision, it is now possible to detect and
Externí odkaz:
http://arxiv.org/abs/2011.00728
Autor:
Doshi, Keval, Yilmaz, Yasin
Anomaly detection in surveillance videos is attracting an increasing amount of attention. Despite the competitive performance of recent methods, they lack theoretical performance analysis, particularly due to the complex deep neural network architect
Externí odkaz:
http://arxiv.org/abs/2010.07110
Internet of Things (IoT) networks consist of sensors, actuators, mobile and wearable devices that can connect to the Internet. With billions of such devices already in the market which have significant vulnerabilities, there is a dangerous threat to
Externí odkaz:
http://arxiv.org/abs/2006.08064
Autor:
Doshi, Keval, Yilmaz, Yasin
Anomaly detection in surveillance videos has been recently gaining attention. A challenging aspect of high-dimensional applications such as video surveillance is continual learning. While current state-of-the-art deep learning approaches perform well
Externí odkaz:
http://arxiv.org/abs/2004.07941
Autor:
Doshi, Keval, Yilmaz, Yasin
Anomaly detection in surveillance videos has been recently gaining attention. Even though the performance of state-of-the-art methods on publicly available data sets has been competitive, they demand a massive amount of training data. Also, they lack
Externí odkaz:
http://arxiv.org/abs/2004.02072