Zobrazeno 1 - 10
of 2 053
pro vyhledávání: '"Pietikäinen, A"'
Publikováno v:
in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 11532-11539, Dec. 2024
Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-i
Externí odkaz:
http://arxiv.org/abs/2411.15895
Autor:
Pietikäinen, Iivari, Černotík, Ondřej, Eickbusch, Alec, Maiti, Aniket, Garmon, John W. O., Filip, Radim, Girvin, Steven M.
Three-dimensional microwave cavity resonators have been shown to reach lifetimes of the order of a second by maximizing the cavity volume relative to its surface, using better materials, and improving surface treatments. Such cavities represent an id
Externí odkaz:
http://arxiv.org/abs/2403.02278
Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient
Externí odkaz:
http://arxiv.org/abs/2402.00422
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this
Externí odkaz:
http://arxiv.org/abs/2308.06764
Autor:
Su, Zhuo, Zhang, Jiehua, Liu, Tianpeng, Liu, Zhen, Zhang, Shuanghui, Pietikäinen, Matti, Liu, Li
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution. It explores the broad "middle spectrum" area between channel prun
Externí odkaz:
http://arxiv.org/abs/2304.06305
From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning
LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are more discri
Externí odkaz:
http://arxiv.org/abs/2303.08414
Autor:
Zhang, Jiehua, Zhang, Xueyang, Su, Zhuo, Yu, Zitong, Feng, Yanghe, Lu, Xin, Pietikäinen, Matti, Liu, Li
Developing lightweight Deep Convolutional Neural Networks (DCNNs) and Vision Transformers (ViTs) has become one of the focuses in vision research since the low computational cost is essential for deploying vision models on edge devices. Recently, res
Externí odkaz:
http://arxiv.org/abs/2211.02292
Efficiency and robustness are increasingly needed for applications on 3D point clouds, with the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which often demand real-time and reliable responses. The paper tackles t
Externí odkaz:
http://arxiv.org/abs/2209.05924
Autor:
Sheng, Changchong, Kuang, Gangyao, Bai, Liang, Hou, Chenping, Guo, Yulan, Xu, Xin, Pietikäinen, Matti, Liu, Li
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning t
Externí odkaz:
http://arxiv.org/abs/2205.10839
Autor:
Pietikäinen, Matti, Silven, Olli
Artificial intelligence (AI) has become a part of everyday conversation and our lives. It is considered as the new electricity that is revolutionizing the world. AI is heavily invested in both industry and academy. However, there is also a lot of hyp
Externí odkaz:
http://arxiv.org/abs/2201.01466