Zobrazeno 1 - 10
of 1 747
pro vyhledávání: '"Li Guorong"'
Publikováno v:
Shuitu baochi tongbao, Vol 43, Iss 5, Pp 212-219 (2023)
[Objective] Plateau pika (Ochotona curzoniae) is a key species in the alpine meadow ecosystem of the Qinghai-Xizang Plateau. The coupling relationship between pika activity and meadow degradation was analyzed in order to further improve the observati
Externí odkaz:
https://doaj.org/article/d3476881e6484b3da9ed490ed372ee43
Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose to take advantage of existing pre-trained large-scale vision and language models to directly generate captio
Externí odkaz:
http://arxiv.org/abs/2405.07046
Publikováno v:
Ceramics-Silikáty, Vol 62, Iss 1, Pp 8-14 (2017)
ZnO-Bi₂O₃-based varistor ceramics are typically sintered at temperatures above 1100 °C to ensure the proper microstructure development and the required current-voltage (I-U) characteristics. In this investigation the influence of the sintering r
Externí odkaz:
https://doaj.org/article/87c36a766ede487595f7d569d24d1053
Autor:
Yu, Xuehui, Chen, Pengfei, Wang, Kuiran, Han, Xumeng, Li, Guorong, Han, Zhenjun, Ye, Qixiang, Jiao, Jianbin
Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance due to the inconsistenc
Externí odkaz:
http://arxiv.org/abs/2401.17203
Single-point annotation in visual tasks, with the goal of minimizing labelling costs, is becoming increasingly prominent in research. Recently, visual foundation models, such as Segment Anything (SAM), have gained widespread usage due to their robust
Externí odkaz:
http://arxiv.org/abs/2312.15895
Describing video content according to users' needs is a long-held goal. Although existing video captioning methods have made significant progress, the generated captions may not focus on the entity that users are particularly interested in. To addres
Externí odkaz:
http://arxiv.org/abs/2312.13330
Autor:
Liu, Xinyan, Li, Guorong, Qi, Yuankai, Yan, Ziheng, Han, Zhenjun, Hengel, Anton van den, Yang, Ming-Hsuan, Huang, Qingming
Video Individual Counting (VIC) aims to predict the number of unique individuals in a single video. % Existing methods learn representations based on trajectory labels for individuals, which are annotation-expensive. % To provide a more realistic ref
Externí odkaz:
http://arxiv.org/abs/2312.05923
Autor:
Zhang, Chen, Li, Guorong, Qi, Yuankai, Ye, Hanhua, Qing, Laiyun, Yang, Ming-Hsuan, Huang, Qingming
The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or duration of anoma
Externí odkaz:
http://arxiv.org/abs/2312.01764
Autor:
Cao, Guangming, Yu, Xuehui, Yu, Wenwen, Han, Xumeng, Yang, Xue, Li, Guorong, Jiao, Jianbin, Han, Zhenjun
Single-point annotation in oriented object detection of remote sensing scenarios is gaining increasing attention due to its cost-effectiveness. However, due to the granularity ambiguity of points, there is a significant performance gap between previo
Externí odkaz:
http://arxiv.org/abs/2311.13128
In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticat
Externí odkaz:
http://arxiv.org/abs/2308.14103