Zobrazeno 1 - 10
of 1 633
pro vyhledávání: '"CHAN, S. H."'
Autor:
Yu, Zhongyi, Wu, Zhenghao, Zhong, Shuhan, Su, Weifeng, Chan, S. -H. Gary, Lee, Chul-Ho, Zhuo, Weipeng
Missing values are a common problem that poses significant challenges to data analysis and machine learning. This problem necessitates the development of an effective imputation method to fill in the missing values accurately, thereby enhancing the o
Externí odkaz:
http://arxiv.org/abs/2410.08794
Autor:
Chen, Jierun, Wei, Fangyun, Zhao, Jinjing, Song, Sizhe, Wu, Bohuai, Peng, Zhuoxuan, Chan, S. -H. Gary, Zhang, Hongyang
Referring expression comprehension (REC) involves localizing a target instance based on a textual description. Recent advancements in REC have been driven by large multimodal models (LMMs) like CogVLM, which achieved 92.44% accuracy on RefCOCO. Howev
Externí odkaz:
http://arxiv.org/abs/2406.16866
Knowing a pedestrian's conveyor state of "elevator," "escalator," or "neither" is fundamental in many applications such as indoor navigation and people flow management. We study, for the first time, classifying the conveyor state of a pedestrian, giv
Externí odkaz:
http://arxiv.org/abs/2405.03218
Autor:
Peng, Zhuoxuan, Chan, S. -H. Gary
Due to its promising results, density map regression has been widely employed for image-based crowd counting. The approach, however, often suffers from severe performance degradation when tested on data from unseen scenarios, the so-called "domain sh
Externí odkaz:
http://arxiv.org/abs/2403.09124
Knowledge distillation (KD) has been recognized as an effective tool to compress and accelerate models. However, current KD approaches generally suffer from an accuracy drop and/or an excruciatingly long distillation process. In this paper, we tackle
Externí odkaz:
http://arxiv.org/abs/2312.13223
Unsupervised domain adaptation (UDA) seeks to bridge the domain gap between the target and source using unlabeled target data. Source-free UDA removes the requirement for labeled source data at the target to preserve data privacy and storage. However
Externí odkaz:
http://arxiv.org/abs/2312.00540
Time series data, including univariate and multivariate ones, are characterized by unique composition and complex multi-scale temporal variations. They often require special consideration of decomposition and multi-scale modeling to analyze. Existing
Externí odkaz:
http://arxiv.org/abs/2310.11959
Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly when handling out-of-distribution (OoD) data, where the training and test
Externí odkaz:
http://arxiv.org/abs/2307.12219
Autor:
Zhuo, Weipeng, Chiu, Ka Ho, Chen, Jierun, Zhao, Ziqi, Chan, S. -H. Gary, Ha, Sangtae, Lee, Chul-Ho
Floor labels of crowdsourced RF signals are crucial for many smart-city applications, such as multi-floor indoor localization, geofencing, and robot surveillance. To build a prediction model to identify the floor number of a new RF signal upon its me
Externí odkaz:
http://arxiv.org/abs/2307.05914
Autor:
He, Tianlang, Lu, Keyan, Jiao, Xianfeng, Xu, Tianfan, Xu, Chang, Liu, Yang, Liu, Weiqing, Chan, S. -H. Gary, Bian, Jiang
Multi-agent market model is a stock trading simulation system, which generates order flow given the agent variable of the model. We study calibrating the agent variable to simulate the order flow of any given historical trading day. In contrast to th
Externí odkaz:
http://arxiv.org/abs/2307.12987