Zobrazeno 1 - 10
of 139
pro vyhledávání: '"WANG Runqi"'
Autor:
Sun, Huixin, Wang, Runqi, Li, Yanjing, Cao, Xianbin, Jiang, Xiaolong, Hu, Yao, Zhang, Baochang
Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of training
Externí odkaz:
http://arxiv.org/abs/2409.17634
Text to Motion aims to generate human motions from texts. Existing settings assume that texts include action labels, which limits flexibility in practical scenarios. This paper extends this task with a more realistic assumption that the texts are arb
Externí odkaz:
http://arxiv.org/abs/2404.14745
Autor:
Huijben, Evi M. C., Terpstra, Maarten L., Galapon, Arthur Jr., Pai, Suraj, Thummerer, Adrian, Koopmans, Peter, Afonso, Manya, van Eijnatten, Maureen, Gurney-Champion, Oliver, Chen, Zeli, Zhang, Yiwen, Zheng, Kaiyi, Li, Chuanpu, Pang, Haowen, Ye, Chuyang, Wang, Runqi, Song, Tao, Fan, Fuxin, Qiu, Jingna, Huang, Yixing, Ha, Juhyung, Park, Jong Sung, Alain-Beaudoin, Alexandra, Bériault, Silvain, Yu, Pengxin, Guo, Hongbin, Huang, Zhanyao, Li, Gengwan, Zhang, Xueru, Fan, Yubo, Liu, Han, Xin, Bowen, Nicolson, Aaron, Zhong, Lujia, Deng, Zhiwei, Müller-Franzes, Gustav, Khader, Firas, Li, Xia, Zhang, Ye, Hémon, Cédric, Boussot, Valentin, Zhang, Zhihao, Wang, Long, Bai, Lu, Wang, Shaobin, Mus, Derk, Kooiman, Bram, Sargeant, Chelsea A. H., Henderson, Edward G. A., Kondo, Satoshi, Kasai, Satoshi, Karimzadeh, Reza, Ibragimov, Bulat, Helfer, Thomas, Dafflon, Jessica, Chen, Zijie, Wang, Enpei, Perko, Zoltan, Maspero, Matteo
Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density
Externí odkaz:
http://arxiv.org/abs/2403.08447
The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target datasets
Externí odkaz:
http://arxiv.org/abs/2311.02392
Autor:
Yang, Yuguang, Wang, Yiming, Geng, Shupeng, Wang, Runqi, Wang, Yimi, Wu, Sheng, Zhang, Baochang
The emergence of cross-modal foundation models has introduced numerous approaches grounded in text-image retrieval. However, on some domain-specific retrieval tasks, these models fail to focus on the key attributes required. To address this issue, we
Externí odkaz:
http://arxiv.org/abs/2306.06691
Autor:
Wang, Runqi, Duan, Xiaoyue, Kang, Guoliang, Liu, Jianzhuang, Lin, Shaohui, Xu, Songcen, Lv, Jinhu, Zhang, Baochang
Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which consists of a feature extractor and a classifier. The feature extracto
Externí odkaz:
http://arxiv.org/abs/2305.11488
Autor:
Wang, Runqi, Zheng, Hao, Duan, Xiaoyue, Liu, Jianzhuang, Lu, Yuning, Wang, Tian, Xu, Songcen, Zhang, Baochang
Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant informatio
Externí odkaz:
http://arxiv.org/abs/2305.11439
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 9, Pp 91-96 (2024)
Objective Accurate short term passenger flow prediction is of great significance to improve the operation and management efficiency of the ultra-large scale of urban rail transit network. However, the current research on deep exploration of the spati
Externí odkaz:
https://doaj.org/article/236a2b0de040444cbd3c121c42055c5d
Autor:
Duan, Xiaoyue, Kang, Guoliang, Wang, Runqi, Han, Shumin, Xue, Song, Wang, Tian, Zhang, Baochang
Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to adversarial attacks. The conventional solution for robust MAML is to in
Externí odkaz:
http://arxiv.org/abs/2211.15180
Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is an importa
Externí odkaz:
http://arxiv.org/abs/2208.12967