Zobrazeno 1 - 10
of 837
pro vyhledávání: '"Zhang, Kunpeng"'
Autor:
Sun, Mingwei, Zhang, Kunpeng
Video-based apparent affect detection plays a crucial role in video understanding, as it encompasses various elements such as vision, audio, audio-visual interactions, and spatiotemporal information, which are essential for accurate video predictions
Externí odkaz:
http://arxiv.org/abs/2408.15209
Autor:
Zhang, Kunpeng, Yi, Xinlei, Wen, Guanghui, Cao, Ming, Johansson, Karl H., Chai, Tianyou, Yang, Tao
This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online a
Externí odkaz:
http://arxiv.org/abs/2406.14060
Autor:
Xiao, Changrong, Ma, Wenxing, Song, Qingping, Xu, Sean Xin, Zhang, Kunpeng, Wang, Yufang, Fu, Qi
Receiving timely and personalized feedback is essential for second-language learners, especially when human instructors are unavailable. This study explores the effectiveness of Large Language Models (LLMs), including both proprietary and open-source
Externí odkaz:
http://arxiv.org/abs/2401.06431
This paper focuses on the distributed online convex optimization problem with time-varying inequality constraints over a network of agents, where each agent collaborates with its neighboring agents to minimize the cumulative network-wide loss over ti
Externí odkaz:
http://arxiv.org/abs/2311.01957
Publikováno v:
Network and Distributed System Security (NDSS) Symposium 2024, 26 February - 1 March 2024, San Diego, CA, USA
Mutation-based fuzzing is popular and effective in discovering unseen code and exposing bugs. However, only a few studies have concentrated on quantifying the importance of input bytes, which refers to the degree to which a byte contributes to the di
Externí odkaz:
http://arxiv.org/abs/2308.09239
Image captioning, an important vision-language task, often requires a tremendous number of finely labeled image-caption pairs for learning the underlying alignment between images and texts. In this paper, we proposed a multimodal data augmentation me
Externí odkaz:
http://arxiv.org/abs/2305.01855
This paper proposes an audience selection framework for online brand advertising based on user activities on social media platforms. It is one of the first studies to our knowledge that develops and analyzes implicit brand-brand networks for online b
Externí odkaz:
http://hdl.handle.net/10150/623353
http://arizona.openrepository.com/arizona/handle/10150/623353
http://arizona.openrepository.com/arizona/handle/10150/623353
Large-scale data missing is a challenging problem in Intelligent Transportation Systems (ITS). Many studies have been carried out to impute large-scale traffic data by considering their spatiotemporal correlations at a network level. In existing traf
Externí odkaz:
http://arxiv.org/abs/2301.11691
Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data or synthe
Externí odkaz:
http://arxiv.org/abs/2212.10888
Autor:
Zhang, Kunpeng1 (AUTHOR) 18272948458@163.com, Wu, Weijun1 (AUTHOR) 18538361628@163.com, Fan, Jiahui2 (AUTHOR) 17537183680@163.com, Yuan, Chengfang2 (AUTHOR) chengfang1102@zzu.edu.cn
Publikováno v:
Materials (1996-1944). Sep2024, Vol. 17 Issue 17, p4307. 27p.