Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Gao Mingqi"'
The correlation between NLG automatic evaluation metrics and human evaluation is often regarded as a critical criterion for assessing the capability of an evaluation metric. However, different grouping methods and correlation coefficients result in v
Externí odkaz:
http://arxiv.org/abs/2410.16834
The evaluation of natural language generation (NLG) tasks is a significant and longstanding research area. With the recent emergence of powerful large language models (LLMs), some studies have turned to LLM-based automatic evaluation methods, which d
Externí odkaz:
http://arxiv.org/abs/2406.18365
Autor:
Ding, Henghui, Liu, Chang, Wei, Yunchao, Ravi, Nikhila, He, Shuting, Bai, Song, Torr, Philip, Miao, Deshui, Li, Xin, He, Zhenyu, Wang, Yaowei, Yang, Ming-Hsuan, Xu, Zhensong, Yao, Jiangtao, Wu, Chengjing, Liu, Ting, Liu, Luoqi, Liu, Xinyu, Zhang, Jing, Zhang, Kexin, Yang, Yuting, Jiao, Licheng, Yang, Shuyuan, Gao, Mingqi, Luo, Jingnan, Yang, Jinyu, Han, Jungong, Zheng, Feng, Cao, Bin, Zhang, Yisi, Lin, Xuanxu, He, Xingjian, Zhao, Bo, Liu, Jing, Pan, Feiyu, Fang, Hao, Lu, Xiankai
Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided Video Seg
Externí odkaz:
http://arxiv.org/abs/2406.17005
Human evaluation is viewed as a reliable evaluation method for NLG which is expensive and time-consuming. To save labor and costs, researchers usually perform human evaluation on a small subset of data sampled from the whole dataset in practice. Howe
Externí odkaz:
http://arxiv.org/abs/2406.07967
Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical report, we investigated and validated the effectiveness of static-domina
Externí odkaz:
http://arxiv.org/abs/2406.07043
Controllable video editing has demonstrated remarkable potential across diverse applications, particularly in scenarios where capturing or re-capturing real-world videos is either impractical or costly. This paper introduces a novel and efficient sys
Externí odkaz:
http://arxiv.org/abs/2402.14316
Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces their reliability. For further verification, we first consider avoidin
Externí odkaz:
http://arxiv.org/abs/2402.12055
Evaluating natural language generation (NLG) is a vital but challenging problem in artificial intelligence. Traditional evaluation metrics mainly capturing content (e.g. n-gram) overlap between system outputs and references are far from satisfactory,
Externí odkaz:
http://arxiv.org/abs/2402.01383
How well can large language models (LLMs) generate summaries? We develop new datasets and conduct human evaluation experiments to evaluate the zero-shot generation capability of LLMs across five distinct summarization tasks. Our findings indicate a c
Externí odkaz:
http://arxiv.org/abs/2309.09558
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant ch
Externí odkaz:
http://arxiv.org/abs/2309.02041