Zobrazeno 1 - 10
of 831
pro vyhledávání: '"Fang Pengfei"'
Publikováno v:
Redai dili, Vol 44, Iss 2, Pp 339-349 (2024)
The urban-rural fringe is located between the central urban built-up area and the rural hinterland, which is a transition zone for land use, economic development, and population structure. It is the most dynamic area between urban and rural areas and
Externí odkaz:
https://doaj.org/article/6c354444694d4a48a253b4cc77973d86
Cross-Domain Few-Shot Learning (CD-FSL) aims to transfer knowledge from seen source domains to unseen target domains, which is crucial for evaluating the generalization and robustness of models. Recent studies focus on utilizing visual styles to brid
Externí odkaz:
http://arxiv.org/abs/2412.09073
Autor:
Xue, Hui, An, Yuexuan, Qin, Yongchun, Li, Wenqian, Wu, Yixin, Che, Yongjuan, Fang, Pengfei, Zhang, Minling
Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to mimic this
Externí odkaz:
http://arxiv.org/abs/2408.09722
Publikováno v:
Dianzi Jishu Yingyong, Vol 45, Iss 7, Pp 102-106 (2019)
Aiming at the problems of inaccurate judgment of linear range and the inability to measure dynamically of traditional compliance measuring instrument of loudspeaker spider，a spider compliance measurement system based on STM32 was designed. In the h
Externí odkaz:
https://doaj.org/article/396f7055ba4442a98dbe33ec5e4b1f1b
Real-world text can be damaged by corrosion issues caused by environmental or human factors, which hinder the preservation of the complete styles of texts, e.g., texture and structure. These corrosion issues, such as graffiti signs and incomplete sig
Externí odkaz:
http://arxiv.org/abs/2401.14832
In the era of Artificial Intelligence Generated Content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image, text-to-video, text-to-audio, etc) are gradually reshaping the natural content in the real world. The key to multimoda
Externí odkaz:
http://arxiv.org/abs/2401.00430
Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text images, visual
Externí odkaz:
http://arxiv.org/abs/2311.17955
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analysis of the audio-visual data reveals a large degree of hyperbolicity,
Externí odkaz:
http://arxiv.org/abs/2308.12558
Hyperbolic geometry, a Riemannian manifold endowed with constant sectional negative curvature, has been considered an alternative embedding space in many learning scenarios, \eg, natural language processing, graph learning, \etc, as a result of its i
Externí odkaz:
http://arxiv.org/abs/2304.10764
Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks. Although numerous progress has been ma
Externí odkaz:
http://arxiv.org/abs/2302.10414