Zobrazeno 1 - 10
of 580
pro vyhledávání: '"Zhao, Haoyu"'
Autor:
Zhang, Xing, Gu, Jiaxi, Zhao, Haoyu, Wang, Shicong, Xu, Hang, Pei, Renjing, Xu, Songcen, Wu, Zuxuan, Jiang, Yu-Gang
Temporal Video Grounding (TVG) aims to localize a moment from an untrimmed video given the language description. Since the annotation of TVG is labor-intensive, TVG under limited supervision has accepted attention in recent years. The great success o
Externí odkaz:
http://arxiv.org/abs/2406.07091
Robot-assisted minimally invasive surgery benefits from enhancing dynamic scene reconstruction, as it improves surgical outcomes. While Neural Radiance Fields (NeRF) have been effective in scene reconstruction, their slow inference speeds and lengthy
Externí odkaz:
http://arxiv.org/abs/2405.17872
Visual grounding is an essential tool that links user-provided text queries with query-specific regions within an image. Despite advancements in visual grounding models, their ability to comprehend complex queries remains limited. To overcome this li
Externí odkaz:
http://arxiv.org/abs/2405.17104
The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets. To address the challenge of poor generalization across different domains, we introduce a Plug-and
Externí odkaz:
http://arxiv.org/abs/2403.11689
In clinical examinations and diagnoses, low-dose computed tomography (LDCT) is crucial for minimizing health risks compared with normal-dose computed tomography (NDCT). However, reducing the radiation dose compromises the signal-to-noise ratio, leadi
Externí odkaz:
http://arxiv.org/abs/2403.11672
Public LLMs such as the Llama 2-Chat have driven huge activity in LLM research. These models underwent alignment training and were considered safe. Recently Qi et al. (2023) reported that even benign fine-tuning (e.g., on seemingly safe datasets) can
Externí odkaz:
http://arxiv.org/abs/2402.18540
Autor:
Ritvo, Paul, Knyahnytska, Yuliya, Pirbaglou, Meysam, Wang, Wei, Tomlinson, George, Zhao, Haoyu, Linklater, Renee, Bai, Shari, Kirk, Megan, Katz, Joel, Harber, Lillian, Daskalakis, Zafiris
Publikováno v:
Journal of Medical Internet Research, Vol 23, Iss 3, p e24380 (2021)
BackgroundApproximately 70% of mental health disorders appear prior to 25 years of age and can become chronic when ineffectively treated. Individuals between 18 and 25 years old are significantly more likely to experience mental health disorders, sub
Externí odkaz:
https://doaj.org/article/ea2caf10ae4742faa8334eeb697a5368
Identity-consistent video generation seeks to synthesize videos that are guided by both textual prompts and reference images of entities. Current approaches typically utilize cross-attention layers to integrate the appearance of the entity, which pre
Externí odkaz:
http://arxiv.org/abs/2311.17338
Autor:
Balasubramanian, Rishab, Li, Jiawei, Tadepalli, Prasad, Wang, Huazheng, Wu, Qingyun, Zhao, Haoyu
We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capture the vulnerability and robustness of CMAB. The attackability condit
Externí odkaz:
http://arxiv.org/abs/2310.05308
Autor:
Gu, Jiaxi, Wang, Shicong, Zhao, Haoyu, Lu, Tianyi, Zhang, Xing, Wu, Zuxuan, Xu, Songcen, Zhang, Wei, Jiang, Yu-Gang, Xu, Hang
Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and infere
Externí odkaz:
http://arxiv.org/abs/2309.03549