Zobrazeno 1 - 10
of 2 143
pro vyhledávání: '"Liu, Yifei"'
This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging results enable, for the first
Externí odkaz:
http://arxiv.org/abs/2405.19516
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech co
Externí odkaz:
http://arxiv.org/abs/2404.00368
Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions. While Pretrained Language Models (PLMs) have showca
Externí odkaz:
http://arxiv.org/abs/2403.04366
Synthetic data generation, a cornerstone of Generative Artificial Intelligence, promotes a paradigm shift in data science by addressing data scarcity and privacy while enabling unprecedented performance. As synthetic data becomes more prevalent, conc
Externí odkaz:
http://arxiv.org/abs/2310.17848
Autor:
Wu, Yiquan, Zhou, Siying, Liu, Yifei, Lu, Weiming, Liu, Xiaozhong, Zhang, Yating, Sun, Changlong, Wu, Fei, Kuang, Kun
Legal Judgment Prediction (LJP) has become an increasingly crucial task in Legal AI, i.e., predicting the judgment of the case in terms of case fact description. Precedents are the previous legal cases with similar facts, which are the basis for the
Externí odkaz:
http://arxiv.org/abs/2310.09241
Autor:
Hu, Yue, Ye, Xinan, Liu, Yifei, Kundu, Souvik, Datta, Gourav, Mutnuri, Srikar, Asavisanu, Namo, Ayanian, Nora, Psounis, Konstantinos, Beerel, Peter
This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resources. To create the dataset, we present a tool that allows the automated
Externí odkaz:
http://arxiv.org/abs/2308.03164
Publikováno v:
IEEE Winter Conference on Applications of Computer Vision (WACV 2024)
Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number of tokens
Externí odkaz:
http://arxiv.org/abs/2306.07050
This paper introduces a novel Perturbation-Assisted Inference (PAI) framework utilizing synthetic data generated by the Perturbation-Assisted Sample Synthesis (PASS) method. The framework focuses on uncertainty quantification in complex data scenario
Externí odkaz:
http://arxiv.org/abs/2305.18671
Autor:
Zang, Yunze, Liu, Yifei, Chen, Xuehong, Li, Anqi, Zhai, Yichen, Li, Shijie, Liu, Luling, Zhu, Chuanhai, Chen, Ruilin, Li, Shupeng, Jie, Na
Mapping crops using remote sensing technology is important for food security and land management. Machine learning-based methods has become a popular approach for crop mapping in recent years. However, the key to machine learning, acquiring ample and
Externí odkaz:
http://arxiv.org/abs/2302.10270
Autor:
Yi, Hongwei, Liang, Hualin, Liu, Yifei, Cao, Qiong, Wen, Yandong, Bolkart, Timo, Tao, Dacheng, Black, Michael J.
This work addresses the problem of generating 3D holistic body motions from human speech. Given a speech recording, we synthesize sequences of 3D body poses, hand gestures, and facial expressions that are realistic and diverse. To achieve this, we fi
Externí odkaz:
http://arxiv.org/abs/2212.04420