Zobrazeno 1 - 10
of 995
pro vyhledávání: '"Savvides, P."'
Knowledge Graph (KG) is playing an increasingly important role in various AI systems. For e-commerce, an efficient and low-cost automated knowledge graph construction method is the foundation of enabling various successful downstream applications. In
Externí odkaz:
http://arxiv.org/abs/2410.21237
Autor:
Qiu, Kai, Li, Xiang, Chen, Hao, Sun, Jie, Wang, Jinglu, Lin, Zhe, Savvides, Marios, Raj, Bhiksha
Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency o
Externí odkaz:
http://arxiv.org/abs/2408.09027
Autor:
Huang, Yu-Kai, Zheng, Yutong, Su, Yen-Shuo, Bolimera, Anudeepsekhar, Zhang, Han, Chen, Fangyi, Savvides, Marios
Facial attribute editing plays a crucial role in synthesizing realistic faces with specific characteristics while maintaining realistic appearances. Despite advancements, challenges persist in achieving precise, 3D-aware attribute modifications, whic
Externí odkaz:
http://arxiv.org/abs/2407.18392
Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we
Externí odkaz:
http://arxiv.org/abs/2405.19854
Autor:
Nguyen, Xuan-Bac, Duong, Chi Nhan, Savvides, Marios, Roy, Kaushik, Churchill, Hugh, Luu, Khoa
Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal. This is because of the limitation of large-scale balanced data with well-annotated labels for sensitive or protected a
Externí odkaz:
http://arxiv.org/abs/2304.07408
Autor:
Ambrosios-Antonios Savvides
Publikováno v:
Geotechnics, Vol 4, Iss 3, Pp 693-717 (2024)
In precedent years mostly, though rarely nowadays, shear deformable structures were constructed across the globe. Also, the soil is deformed as a shear cantilever, which means that the shear forces and stresses are more prominent than the respective
Externí odkaz:
https://doaj.org/article/dcaf5150380c47b8b9693be27b6d3800
Publikováno v:
International Journal of Geo-Engineering, Vol 15, Iss 1, Pp 1-48 (2024)
Abstract A collection of feed forward neural networks (FNN) for estimating the limit pressure load and the according displacements at limit state of a footing settlement is presented. The training procedure is through supervised learning with error l
Externí odkaz:
https://doaj.org/article/63a9e4a5eb294edea66965c2972f9077
Autor:
Chen, Hao, Tao, Ran, Fan, Yue, Wang, Yidong, Wang, Jindong, Schiele, Bernt, Xie, Xing, Raj, Bhiksha, Savvides, Marios
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling
Externí odkaz:
http://arxiv.org/abs/2301.10921
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitatio
Externí odkaz:
http://arxiv.org/abs/2212.07593
Publikováno v:
Fuel Communications, Vol 20, Iss , Pp 100125- (2024)
Cities continue to expand along with the growth of population, while our mobility systems often fail to meet the demands for social, environmental and economic sustainability. The second industrial revolution enabled the extensive use of private vehi
Externí odkaz:
https://doaj.org/article/9b516a5aee084c24b6d251bc52405188