Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Xiao, Yicheng"'
Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video in a zero-shot manner. Despite extensive efforts, maintaining the temporal consistency of edited video
Externí odkaz:
http://arxiv.org/abs/2406.08850
Autor:
Xiao, Yicheng, Song, Lin, Huang, Shaoli, Wang, Jiangshan, Song, Siyu, Ge, Yixiao, Li, Xiu, Shan, Ying
The state space models, employing recursively propagated features, demonstrate strong representation capabilities comparable to Transformer models and superior efficiency. However, constrained by the inherent geometric constraints of sequences, it st
Externí odkaz:
http://arxiv.org/abs/2406.02395
Autor:
Luo, Zhuoyan, Wu, Yinghao, Cheng, Tianheng, Liu, Yong, Xiao, Yicheng, Wang, Hongfa, Zhang, Xiao-Ping, Yang, Yujiu
The newly proposed Generalized Referring Expression Segmentation (GRES) amplifies the formulation of classic RES by involving complex multiple/non-target scenarios. Recent approaches address GRES by directly extending the well-adopted RES frameworks
Externí odkaz:
http://arxiv.org/abs/2405.15658
The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance. Most prior works adopt unified DETR framework to generate segmentation masks in query-to-instance manner. In this
Externí odkaz:
http://arxiv.org/abs/2401.00663
Autor:
Luo, Zhuoyan, Xiao, Yicheng, Liu, Yong, Li, Shuyan, Wang, Yitong, Tang, Yansong, Li, Xiu, Yang, Yujiu
This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for
Externí odkaz:
http://arxiv.org/abs/2305.17011
In this paper, we propose SemanticAC, a semantics-assisted framework for Audio Classification to better leverage the semantic information. Unlike conventional audio classification methods that treat class labels as discrete vectors, we employ a langu
Externí odkaz:
http://arxiv.org/abs/2302.05940
Autor:
Xiao, Yicheng, Zhang, Junpeng
Deep convolutional neural network with increased number of parameters has achieved improved precision in task of object detection on natural images, where objects of interests are annotated with horizontal boundary boxes. On aerial images captured fr
Externí odkaz:
http://arxiv.org/abs/2206.09796
Autor:
Wang, Run, Fang, Shaoli, Xiao, Yicheng, Gao, Enlai, Jiang, Nan, Li, Yaowang, Mou, Linlin, Shen, Yanan, Zhao, Wubin, Li, Sitong, Fonseca, Alexandre F., Galvão, Douglas S., Chen, Mengmeng, He, Wenqian, Yu, Kaiqing, Lu, Hongbing, Wang, Xuemin, Qian, Dong, Aliev, Ali E., Li, Na, Haines, Carter S., Liu, Zhongsheng, Mu, Jiuke, Wang, Zhong, Yin, Shougen, Lima, Márcio D., An, Baigang, Zhou, Xiang, Liu, Zunfeng, Baughman, Ray H.
Higher efficiency, lower cost refrigeration is needed for both large and small scale cooling. Refrigerators using entropy changes during cycles of stretching or hydrostatically compression of a solid are possible alternatives to the vapor-compression
Externí odkaz:
http://arxiv.org/abs/1910.11156
Publikováno v:
In Microelectronics Journal June 2023 136
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.