Zobrazeno 1 - 10
of 2 452
pro vyhledávání: '"Chen, Xiaodong P."'
Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-inten
Externí odkaz:
http://arxiv.org/abs/2410.12813
Human motion capture is the foundation for many computer vision and graphics tasks. While industrial motion capture systems with complex camera arrays or expensive wearable sensors have been widely adopted in movie and game production, consumer-affor
Externí odkaz:
http://arxiv.org/abs/2407.16341
Autor:
Egli, Jana, Forrai, Benedek, Buchner, Thomas, Su, Jiangtao, Chen, Xiaodong, Katzschmann, Robert K.
Conventional industrial robots often use two-fingered grippers or suction cups to manipulate objects or interact with the world. Because of their simplified design, they are unable to reproduce the dexterity of human hands when manipulating a wide ra
Externí odkaz:
http://arxiv.org/abs/2404.19448
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less important layers t
Externí odkaz:
http://arxiv.org/abs/2403.19135
Autor:
Yang, Shiyuan, Hou, Liang, Huang, Haibin, Ma, Chongyang, Wan, Pengfei, Zhang, Di, Chen, Xiaodong, Liao, Jing
Recent text-to-video diffusion models have achieved impressive progress. In practice, users often desire the ability to control object motion and camera movement independently for customized video creation. However, current methods lack the focus on
Externí odkaz:
http://arxiv.org/abs/2402.03162
Recently, text-to-image denoising diffusion probabilistic models (DDPMs) have demonstrated impressive image generation capabilities and have also been successfully applied to image inpainting. However, in practice, users often require more control ov
Externí odkaz:
http://arxiv.org/abs/2310.07222
Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and effici
Externí odkaz:
http://arxiv.org/abs/2308.16475
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 8, Pp 331-334 (2024)
Objective Connecting Passage 1 in the interval of Jiujiang North Station and Longqiao Road Station of Chengdu Metro Line 19 Phase II is located in water-rich sandy cobble stratum. Limited by the location of the surrounding buildings (structures), it
Externí odkaz:
https://doaj.org/article/e434216e5b2442aa91c9e30d85d53c63
Autor:
Wen, Zhoufutu, Zhao, Xinyu, Jin, Zhipeng, Yang, Yi, Jia, Wei, Chen, Xiaodong, Li, Shuanglong, Liu, Lin
In the multimedia era, image is an effective medium in search advertising. Dynamic Image Advertising (DIA), a system that matches queries with ad images and generates multimodal ads, is introduced to improve user experience and ad revenue. The core o
Externí odkaz:
http://arxiv.org/abs/2306.14112
Autor:
Lin, Qifeng, Li, Rui, Zhang, Feilong, Kazuki, Kai, Chen, Ong Zong, Chen, Xiaodong, Sato, Hirotaka
By leveraging their high mobility and small size, insects have been combined with microcontrollers to build up cyborg insects for various practical applications. Unfortunately, all current cyborg insects rely on implanted electrodes to control their
Externí odkaz:
http://arxiv.org/abs/2303.10990