Zobrazeno 1 - 10
of 6 064
pro vyhledávání: '"DAI, Li"'
Multi-view clustering can partition data samples into their categories by learning a consensus representation in an unsupervised way and has received more and more attention in recent years. However, there is an untrusted fusion problem. The reasons
Externí odkaz:
http://arxiv.org/abs/2412.16487
The multi-view hash method converts heterogeneous data from multiple views into binary hash codes, which is one of the critical technologies in multimedia retrieval. However, the current methods mainly explore the complementarity among multiple views
Externí odkaz:
http://arxiv.org/abs/2312.07327
Publikováno v:
Neural Regeneration Research, Vol 20, Iss 4, Pp 990-1008 (2025)
With the rapidly aging human population, age-related cognitive decline and dementia are becoming increasingly prevalent worldwide. Aging is considered the main risk factor for cognitive decline and acts through alterations in the composition of the g
Externí odkaz:
https://doaj.org/article/da30a3fa6fb14095bdc110176f00c231
Autor:
Conglin Wang, Fangyuan Cheng, Zhaoli Han, Bo Yan, Pan Liao, Zhenyu Yin, Xintong Ge, Dai Li, Rongrong Zhong, Qiang Liu, Fanglian Chen, Ping Lei
Publikováno v:
Neural Regeneration Research, Vol 20, Iss 2, Pp 518-532 (2025)
Cerebral edema caused by blood–brain barrier injury after intracerebral hemorrhage is an important factor leading to poor prognosis. Human-induced pluripotent stem cell–derived neural stem cell exosomes (hiPSC–NSC–Exos) have shown potential f
Externí odkaz:
https://doaj.org/article/7f5b8dcf3a774d90ab1d785e21426e40
Autor:
Shi, Mohan, Du, Zhihao, Chen, Qian, Yu, Fan, Li, Yangze, Zhang, Shiliang, Zhang, Jie, Dai, Li-Rong
Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recogn
Externí odkaz:
http://arxiv.org/abs/2305.12459
For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in a large l
Externí odkaz:
http://arxiv.org/abs/2305.12450
Autor:
Zeng, Xiao-Min, Song, Yan, Zhuo, Zhu, Zhou, Yu, Li, Yu-Hong, Xue, Hui, Dai, Li-Rong, McLoughlin, Ian
In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to perform frame-l
Externí odkaz:
http://arxiv.org/abs/2305.12111
Publikováno v:
International Journal of Ophthalmology, Vol 17, Iss 8, Pp 1411-1417 (2024)
AIM: To prevent neovascularization in diabetic retinopathy (DR) patients and partially control disease progression. METHODS: Hypoxia-related differentially expressed genes (DEGs) were identified from the GSE60436 and GSE102485 datasets, followed by g
Externí odkaz:
https://doaj.org/article/4426b31011c644eca2cc0ed0b6aa9df3
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED. Pretrained AST models have recently
Externí odkaz:
http://arxiv.org/abs/2303.03689
Autor:
Dai Li, Jing-Wen Mai, Jie Deng, Li Chen, Hai-Ting Fan, Wei-Lin Zhang, Wen-Jun Xin, Xia Feng, Ting Xu, De-Xing Luo
Publikováno v:
Neurobiology of Disease, Vol 202, Iss , Pp 106699- (2024)
Top-down projections transmit a series of signals encoding pain sensation to the ventrolateral periaqueductal gray (vlPAG), where they converge with various incoming projections to regulate pain. Clarifying the upstream regulatory hierarchy of vlPAG
Externí odkaz:
https://doaj.org/article/e21a68742a47412a853355aa3595d9a4