Zobrazeno 1 - 10
of 29 507
pro vyhledávání: '"LIANG, Chen"'
We present CasualGaze, a novel eye-gaze-based target selection technique to support natural and casual eye-gaze input. Unlike existing solutions that require users to keep the eye-gaze center on the target actively, CasualGaze allows users to glance
Externí odkaz:
http://arxiv.org/abs/2408.12710
A long-standing challenge in end-user programming (EUP) is to trade off between natural user expression and the complexity of programming tasks. As large language models (LLMs) are empowered to handle semantic inference and natural language understan
Externí odkaz:
http://arxiv.org/abs/2408.12687
Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle to cope wit
Externí odkaz:
http://arxiv.org/abs/2408.10627
Message passing neural networks have demonstrated significant efficacy in predicting molecular interactions. Introducing equivariant vectorial representations augments expressivity by capturing geometric data symmetries, thereby improving model accur
Externí odkaz:
http://arxiv.org/abs/2406.13265
Autor:
Liu, Quangao, Li, Ruiqi, Jiang, Maowei, Yang, Wei, Liang, Chen, Pang, LongLong, Zou, Zhuozhang
Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making accurate fo
Externí odkaz:
http://arxiv.org/abs/2406.12921
Efficiently modeling sequences with infinite context length has been a long-standing problem. Past works suffer from either the quadratic computation complexity or the limited extrapolation ability on length generalization. In this work, we present S
Externí odkaz:
http://arxiv.org/abs/2406.07522
Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has changed th
Externí odkaz:
http://arxiv.org/abs/2406.06891
Autor:
Tang, Chunxu, Fan, Bin, Zhao, Jing, Liang, Chen, Wang, Yi, Wang, Beinan, Qiu, Ziyue, Qiu, Lu, Ding, Bowen, Sun, Shouzhuo, Che, Saiguang, Mai, Jiaming, Chen, Shouwei, Zhu, Yu, Xie, Jianjian, Yutian, Sun, Li, Yao, Zhang, Yangjun, Wang, Ke, Chen, Mingmin
With the exponential growth of data and evolving use cases, petabyte-scale OLAP data platforms are increasingly adopting a model that decouples compute from storage. This shift, evident in organizations like Uber and Meta, introduces operational chal
Externí odkaz:
http://arxiv.org/abs/2406.05962
Pixel-level Video Understanding requires effectively integrating three-dimensional data in both spatial and temporal dimensions to learn accurate and stable semantic information from continuous frames. However, existing advanced models on the VSPW da
Externí odkaz:
http://arxiv.org/abs/2406.04979
Autor:
Lin, Wang, Chen, Jingyuan, Shi, Jiaxin, Zhu, Yichen, Liang, Chen, Miao, Junzhong, Jin, Tao, Zhao, Zhou, Wu, Fei, Yan, Shuicheng, Zhang, Hanwang
We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity of user-pro
Externí odkaz:
http://arxiv.org/abs/2405.06914