Zobrazeno 1 - 10
of 2 176
pro vyhledávání: '"Wang Yongqing"'
Autor:
Liu, Jizhong, Li, Gang, Zhang, Junbo, Dinkel, Heinrich, Wang, Yongqing, Yan, Zhiyong, Wang, Yujun, Wang, Bin
Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibil
Externí odkaz:
http://arxiv.org/abs/2406.13275
Autor:
Yan, Zhiyong, Dinkel, Heinrich, Wang, Yongqing, Liu, Jizhong, Zhang, Junbo, Wang, Yujun, Wang, Bin
Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given t
Externí odkaz:
http://arxiv.org/abs/2406.07012
Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks,
Externí odkaz:
http://arxiv.org/abs/2406.06992
As graph representation learning often suffers from label scarcity problems in real-world applications, researchers have proposed graph domain adaptation (GDA) as an effective knowledge-transfer paradigm across graphs. In particular, to enhance model
Externí odkaz:
http://arxiv.org/abs/2402.00904
Autor:
Guo, Fangda, Luo, Xuanpu, Liu, Yanghao, Chen, Guoxin, Wang, Yongqing, Shen, Huawei, Cheng, Xueqi
Due to the ability of modeling relationships between two different types of entities, bipartite graphs are naturally employed in many real-world applications. Community Search in bipartite graphs is a fundamental problem and has gained much attention
Externí odkaz:
http://arxiv.org/abs/2401.12895
Autor:
Chen, Guoxin, Guo, Fangda, Wang, Yongqing, Liu, Yanghao, Yu, Peiying, Shen, Huawei, Cheng, Xueqi
Community search is a personalized community discovery problem designed to identify densely connected subgraphs containing the query node. Recently, community search in heterogeneous information networks (HINs) has received considerable attention. Ex
Externí odkaz:
http://arxiv.org/abs/2311.08919
Autor:
Chen, Guoxin, Wang, Yongqing, Guo, Fangda, Guo, Qinglang, Shao, Jiangli, Shen, Huawei, Cheng, Xueqi
Most existing methods that address out-of-distribution (OOD) generalization for node classification on graphs primarily focus on a specific type of data biases, such as label selection bias or structural bias. However, anticipating the type of bias i
Externí odkaz:
http://arxiv.org/abs/2310.09586
Augmentation and knowledge distillation (KD) are well-established techniques employed in audio classification tasks, aimed at enhancing performance and reducing model sizes on the widely recognized Audioset (AS) benchmark. Although both techniques ar
Externí odkaz:
http://arxiv.org/abs/2308.11957
Graph domain adaptation models are widely adopted in cross-network learning tasks, with the aim of transferring labeling or structural knowledge. Currently, there mainly exist two limitations in evaluating graph domain adaptation models. On one side,
Externí odkaz:
http://arxiv.org/abs/2307.11341
Autor:
Lin, Jiuxin, Wang, Peng, Dinkel, Heinrich, Chen, Jun, Wu, Zhiyong, Yan, Zhiyong, Wang, Yongqing, Zhang, Junbo, Wang, Yujun
Previously, Target Speaker Extraction (TSE) has yielded outstanding performance in certain application scenarios for speech enhancement and source separation. However, obtaining auxiliary speaker-related information is still challenging in noisy envi
Externí odkaz:
http://arxiv.org/abs/2306.16241