Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Lin Yan"'
Autor:
Lin, Yan, Liu, Yichen, Zhou, Zeyu, Wen, Haomin, Zheng, Erwen, Guo, Shengnan, Lin, Youfang, Wan, Huaiyu
Vehicle trajectories provide crucial movement information for various real-world applications. To better utilize vehicle trajectories, it is essential to develop a trajectory learning approach that can effectively and efficiently extract rich semanti
Externí odkaz:
http://arxiv.org/abs/2408.04916
Autor:
Gong, Letian, Wan, Huaiyu, Guo, Shengnan, Li, Xiucheng, Lin, Yan, Zheng, Erwen, Wang, Tianyi, Zhou, Zeyu, Lin, Youfang
The rapid growth of location-based services (LBS) has yielded massive amounts of data on human mobility. Effectively extracting meaningful representations for user-generated check-in sequences is pivotal for facilitating various downstream services.
Externí odkaz:
http://arxiv.org/abs/2407.15899
Autor:
Lin, Yan, Zhou, Zeyu, Liu, Yicheng, Lv, Haochen, Wen, Haomin, Li, Tianyi, Li, Yushuai, Jensen, Christian S., Guo, Shengnan, Lin, Youfang, Wan, Huaiyu
Spatio-temporal (ST) trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent anal
Externí odkaz:
http://arxiv.org/abs/2407.12550
In this article, we introduce a class of multilinear fractional integral operators with generalized kernels that are weaker than the Dini kernel condition. We establish the boundedness of multilinear fractional integral operators with generalized ker
Externí odkaz:
http://arxiv.org/abs/2406.08736
This paper considers utilizing the knowledge of age gains to reduce the network average age of information (AoI) in random access with event-driven periodic updating for the first time. Built on the form of slotted ALOHA, we require each device to de
Externí odkaz:
http://arxiv.org/abs/2406.00720
Autor:
Zhou, Zeyu, Lin, Yan, Wen, Haomin, Xu, Qisen, Guo, Shengnan, Hu, Jilin, Lin, Youfang, Wan, Huaiyu
Spatio-temporal trajectories are crucial in various data mining tasks. It is important to develop a versatile trajectory learning method that performs different tasks with high accuracy. This involves effectively extracting two core aspects of inform
Externí odkaz:
http://arxiv.org/abs/2405.12459
Recovering intermediate missing GPS points in a sparse trajectory, while adhering to the constraints of the road network, could offer deep insights into users' moving behaviors in intelligent transportation systems. Although recent studies have demon
Externí odkaz:
http://arxiv.org/abs/2404.19141
Autor:
Lin, Yan-Bo, Bertasius, Gedas
Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual pretraining. Our fr
Externí odkaz:
http://arxiv.org/abs/2403.19638
The rapid development of Large Language Models (LLMs) has facilitated a variety of applications from different domains. In this technical report, we explore the integration of LLMs and the popular academic writing tool, Overleaf, to enhance the effic
Externí odkaz:
http://arxiv.org/abs/2403.09733
We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually
Externí odkaz:
http://arxiv.org/abs/2403.08755