Zobrazeno 1 - 10
of 140
pro vyhledávání: '"James T. Kwok"'
Publikováno v:
IET Image Processing, Vol 16, Iss 12, Pp 3247-3257 (2022)
Abstract Recently, residual and dense networks have effectively promoted the development of image super‐resolution (SR). However, most dense networks based SR methods do not make full use of dense feature information. To solve this problem, a pyram
Externí odkaz:
https://doaj.org/article/d23f1462e90e4e82bf8b1ddc60b0c81f
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5a8c79a65726e7dcb481e58eeb89914
https://doi.org/10.1109/icassp49357.2023.10095978
https://doi.org/10.1109/icassp49357.2023.10095978
Publikováno v:
IEEE transactions on neural networks and learning systems.
Training deep neural networks (DNNs) typically requires massive computational power. Existing DNNs exhibit low time and storage efficiency due to the high degree of redundancy. In contrast to most existing DNNs, biological and social networks with va
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2796c9fe5483b6532f20bd87e3888a3
https://pubmed.ncbi.nlm.nih.gov/36342998
https://pubmed.ncbi.nlm.nih.gov/36342998
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
Feature extractor plays a critical role in text recognition (TR), but customizing its architecture is relatively less explored due to expensive manual tweaking. In this work, inspired by the success of neural architecture search (NAS), we propose to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e95d52a7cc62be3a3058c8b16bf1529d
https://pubmed.ncbi.nlm.nih.gov/36094971
https://pubmed.ncbi.nlm.nih.gov/36094971
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:9567-9575
Recurrent autoencoder is a popular model for time series anomaly detection, in which outliers or abnormal segments are identified by their high reconstruction errors. However, existing recurrent autoencoders can easily suffer from overfitting and err
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::43b74bfed9a6d173884902d17df25e85
https://doi.org/10.1609/aaai.v35i11.17152
https://doi.org/10.1609/aaai.v35i11.17152
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 32:788-798
A least squares support vector machine (LS-SVM) offers performance comparable to that of SVMs for classification and regression. The main limitation of LS-SVM is that it lacks sparsity compared with SVMs, making LS-SVM unsuitable for handling large-s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c680a8d67c785f057a0845b017e94e27
https://doi.org/10.1109/tnnls.2020.2979466
https://doi.org/10.1109/tnnls.2020.2979466
Publikováno v:
IEEE Transactions on Multimedia. 23:3907-3918
The last few years have witnessed the rise of the big data era, in which approximate nearest neighbor search is a fundamental problem in many applications, such as large-scale image retrieval. Recently, many research results demonstrate that hashing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b338bb1f0b34aff4069728e1404c3d75
https://doi.org/10.1109/tmm.2020.3033118
https://doi.org/10.1109/tmm.2020.3033118
Publikováno v:
IJCNN
Few-shot classification aims at learning new concepts with only a few labeled examples. In this paper, we focus on metric-based methods that have achieved state-of-the-art performance. However, they classify query examples based on embeddings extract
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf7dea2922cb24a9d7dd7e82eb86bbaf
https://doi.org/10.1109/ijcnn52387.2021.9533845
https://doi.org/10.1109/ijcnn52387.2021.9533845
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(10)
In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated as low-rank
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bbcf2bdd0843aead70670bd4a6323a76
https://pubmed.ncbi.nlm.nih.gov/34061741
https://pubmed.ncbi.nlm.nih.gov/34061741
Publikováno v:
WWW
Matrix learning is at the core of many machine learning problems. A number of real-world applications such as collaborative filtering and text mining can be formulated as a low-rank matrix completion problems, which recovers incomplete matrix using l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd879d31905296db9b013aa3dc1be916
https://doi.org/10.1145/3442381.3450142
https://doi.org/10.1145/3442381.3450142