Results 1 to 10 of about 109,484 (148)
Adaptive Weighted Face Alignment by Multi-Scale Feature and Offset Prediction
IET Biometrics, 2023 Traditional heatmap regression methods have some problems such as the lower limit of theoretical error and the lack of global constraints, which may lead to the collapse of the results in practical application. In this paper, we develop a facial landmark
Jingwen Li +3 more
doaj +1 more source
DM-DQN: Dueling Munchausen deep Q network for robot path planning
Complex & Intelligent Systems, 2022 In order to achieve collision-free path planning in complex environment, Munchausen deep Q-learning network (M-DQN) is applied to mobile robot to learn the best decision. On the basis of Soft-DQN, M-DQN adds the scaled log-policy to the immediate reward.
Yuwan Gu +5 more
doaj +1 more source
Artificial intelligence in computational materials science
MRS Bulletin, 2022 Abstract In this themed collection we aim to broadly review some of the critical, recent progress in the application of AI/ML to various aspects of computational materials science and materials science more broadly. In this collection spread across two issues, we have assembled a collection of articles from leaders in the broad domain of applying AI/ML,
Kulik, Heather J., Tiwary, Pratyush
openaire +2 more sources
Role of Artificial Intelligence in Computer Science
International Journal of Scientific Research in Science, Engineering and Technology, 2022 This is done by exhibiting both the prehistoric remains and the castle itself through many forms of technological support, including multimedia interactive applications and artificial intelligence functions alongside computerized simulations. a growing body of researchers from the social and computer sciences are using computational experimentation in ...
null Kunal, null Muskan Rana
openaire +1 more source
Deep Feature Interactive Aggregation Network for Single Image Deraining
IEEE Access, 2022 Single image deraining aims to remove rain streaks from a degraded input and reconstruct a high-quality image. In recent years, image processing tasks mostly applied a U-shaped architecture to capture rich contextual information. However, it is difficult
Shaoli Cao +5 more
doaj +1 more source
Nature Communications, 2020 Haplotype reconstruction of distant genetic variants is problematic in short-read sequencing. Here, the authors describe HapTree-X, a probabilistic framework that uses differential allele-specific expression to better reconstruct paternal haplotypes from
Emily Berger +7 more
doaj +1 more source
CCPIN: Classification and Combine Parallel Interaction Network for CTR Prediction
Journal of Electrical and Computer Engineering, 2022 The study of feature interactions in deep neural network-based recommender systems has been a popular research area in industry and academic circles.
Guosheng Tan +2 more
doaj +1 more source
CNN-based two-branch multi-scale feature extraction network for retrosynthesis prediction
BMC Bioinformatics, 2022 Background Retrosynthesis prediction is the task of deducing reactants from reaction products, which is of great importance for designing the synthesis routes of the target products.
Feng Yang +4 more
doaj +1 more source
Robust facial landmark detection by probability‐guided hourglass network
IET Image Processing, 2023 The absence of local features and global shape constraints severely limits the performance of the hourglass network for facial landmark detection in unconstrained environments. Moreover, diverse feature types and scales may result in low accuracy.
Jingyan Fan +5 more
doaj +1 more source
Long and Short-Term Interest Contrastive Learning Under Filter-Enhanced Sequential Recommendation
IEEE Access, 2023 Existing self-supervised sequential recommendations face the problem of noisy interactions and sparse sequence data, and train models based only on item prediction losses, so they usually fail to learn an appropriate sequential representation.
Yi Li +4 more
doaj +1 more source