Zobrazeno 1 - 10
of 2 114
pro vyhledávání: '"WAN, Bo"'
Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during fine-tuning. To ad
Externí odkaz:
http://arxiv.org/abs/2407.07523
Autor:
Wan, Bo, Tschannen, Michael, Xian, Yongqin, Pavetic, Filip, Alabdulmohsin, Ibrahim, Wang, Xiao, Pinto, André Susano, Steiner, Andreas, Beyer, Lucas, Zhai, Xiaohua
Image captioning has been shown as an effective pretraining method similar to contrastive pretraining. However, the incorporation of location-aware information into visual pretraining remains an area with limited research. In this paper, we propose a
Externí odkaz:
http://arxiv.org/abs/2403.19596
In recent years, diffusion models have made remarkable strides in text-to-video generation, sparking a quest for enhanced control over video outputs to more accurately reflect user intentions. Traditional efforts predominantly focus on employing eith
Externí odkaz:
http://arxiv.org/abs/2403.10179
Autor:
Wan, Bo, Tuytelaars, Tinne
In this paper, we investigate the task of zero-shot human-object interaction (HOI) detection, a novel paradigm for identifying HOIs without the need for task-specific annotations. To address this challenging task, we employ CLIP, a large-scale pre-tr
Externí odkaz:
http://arxiv.org/abs/2309.05069
Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more va
Externí odkaz:
http://arxiv.org/abs/2308.14316
Autor:
Beyer, Lucas, Wan, Bo, Madan, Gagan, Pavetic, Filip, Steiner, Andreas, Kolesnikov, Alexander, Pinto, André Susano, Bugliarello, Emanuele, Wang, Xiao, Yu, Qihang, Chen, Liang-Chieh, Zhai, Xiaohua
There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one system and
Externí odkaz:
http://arxiv.org/abs/2303.17376
Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizable and scalable strategy for HOI detection is to use weak supervision,
Externí odkaz:
http://arxiv.org/abs/2303.01313
Autor:
Jing-E Zhu, Chun-Jun Sheng, Hui-Li Zhang, Jia-Xin Li, Xiao-Wan Bo, Jia-Jing Yin, Peng Yang, Song-Yuan Yu, Li-Ping Sun
Publikováno v:
International Journal of Hyperthermia, Vol 41, Iss 1 (2024)
Objectives This study aimed to analyze the safety, efficacy, and application prospects of ultrasound-guided microwave ablation (MWA) in the treatment of primary hyperthyroidism.Methods Eight patients with primary hyperthyroidism who underwent ultraso
Externí odkaz:
https://doaj.org/article/9500d4237ea143b0886c7a08ca561086
Publikováno v:
ACS Omega, Vol 9, Iss 17, Pp 19031-19042 (2024)
Externí odkaz:
https://doaj.org/article/3b32fc96c2c84db9aef7dfb71c9b40d9
Publikováno v:
In Science of the Total Environment 20 December 2024 957