Zobrazeno 1 - 10
of 2 395
pro vyhledávání: '"liu, Haiyang"'
Autor:
Shao, Yihua, Liang, Siyu, Lin, Xiaolin, Ling, Zijian, Zhu, Zixian, Yan, Minxi, Liu, Haiyang, Chen, Siyu, Yan, Ziyang, Meng, Yilan, Zhang, Chenyu, Qin, Haotong, Magno, Michele, Yang, Yang, Lei, Zhen, Wang, Yan, Guo, Jingcai, Shao, Ling, Tang, Hao
Large language models (LLMs) show impressive performance in solving complex languagetasks. However, its large number of parameterspresent significant challenges for the deployment and application of the model on edge devices. Compressing large langua
Externí odkaz:
http://arxiv.org/abs/2411.00850
Autor:
Liu, Haiyang, Yang, Xingchao, Akiyama, Tomoya, Huang, Yuantian, Li, Qiaoge, Kuriyama, Shigeru, Taketomi, Takafumi
We present TANGO, a framework for generating co-speech body-gesture videos. Given a few-minute, single-speaker reference video and target speech audio, TANGO produces high-fidelity videos with synchronized body gestures. TANGO builds on Gesture Video
Externí odkaz:
http://arxiv.org/abs/2410.04221
Code smells indicate the potential problems of software quality so that developers can identify refactoring opportunities by detecting code smells. State-of-the-art approaches leverage heuristics, machine learning, and deep learning to detect code sm
Externí odkaz:
http://arxiv.org/abs/2402.10398
Traffic flow prediction plays a crucial role in alleviating traffic congestion and enhancing transport efficiency. While combining graph convolution networks with recurrent neural networks for spatial-temporal modeling is a common strategy in this re
Externí odkaz:
http://arxiv.org/abs/2401.04135
Autor:
Liu, Haiyang, Zhu, Zihao, Becherini, Giorgio, Peng, Yichen, Su, Mingyang, Zhou, You, Zhe, Xuefei, Iwamoto, Naoya, Zheng, Bo, Black, Michael J.
We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic c
Externí odkaz:
http://arxiv.org/abs/2401.00374
We propose a new type of high temperature superconducting (HTS) conductor concept: modularized conductors (MC) connected by Chinese traditional tenon mortise (TM) connection structure, reffered as TMMC. The conductor consists of multiple concentric r
Externí odkaz:
http://arxiv.org/abs/2312.10597
Systematic optimization over a wide power range is often achieved through the combination of modules of different power levels. This paper addresses the issue of enhancing the efficiency of a multiple module system connected in parallel during operat
Externí odkaz:
http://arxiv.org/abs/2311.06705
Traffic flow prediction is one of the most fundamental tasks of intelligent transportation systems. The complex and dynamic spatial-temporal dependencies make the traffic flow prediction quite challenging. Although existing spatial-temporal graph neu
Externí odkaz:
http://arxiv.org/abs/2310.08138
The immutable and trustable characteristics of blockchain enable smart contracts to be applied in various fields. Unfortunately, smart contracts are subject to various vulnerabilities, which are frequently exploited by attackers, causing financial da
Externí odkaz:
http://arxiv.org/abs/2306.04479
Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation
Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based features while
Externí odkaz:
http://arxiv.org/abs/2304.12685