Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Lai, Zeqiang"'
Autor:
Wu, Jiannan, Zhong, Muyan, Xing, Sen, Lai, Zeqiang, Liu, Zhaoyang, Wang, Wenhai, Chen, Zhe, Zhu, Xizhou, Lu, Lewei, Lu, Tong, Luo, Ping, Qiao, Yu, Dai, Jifeng
We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broad
Externí odkaz:
http://arxiv.org/abs/2406.08394
Autor:
Liu, Zhaoyang, Lai, Zeqiang, Gao, Zhangwei, Cui, Erfei, Li, Ziheng, Zhu, Xizhou, Lu, Lewei, Chen, Qifeng, Qiao, Yu, Dai, Jifeng, Wang, Wenhai
We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving complex real-world tasks. Despite the remarkable performance of LLMs, they still struggle with tool invocation due to ambiguou
Externí odkaz:
http://arxiv.org/abs/2310.17796
The revolution of artificial intelligence content generation has been rapidly accelerated with the booming text-to-image (T2I) diffusion models. Within just two years of development, it was unprecedentedly of high-quality, diversity, and creativity t
Externí odkaz:
http://arxiv.org/abs/2310.07653
Autor:
Lai, Zeqiang, Duan, Yuchen, Dai, Jifeng, Li, Ziheng, Fu, Ying, Li, Hongsheng, Qiao, Yu, Wang, Wenhai
The evolution of semantic segmentation has long been dominated by learning more discriminative image representations for classifying each pixel. Despite the prominent advancements, the priors of segmentation masks themselves, e.g., geometric and sema
Externí odkaz:
http://arxiv.org/abs/2306.01721
Autor:
Liu, Zhaoyang, He, Yinan, Wang, Wenhai, Wang, Weiyun, Wang, Yi, Chen, Shoufa, Zhang, Qinglong, Lai, Zeqiang, Yang, Yang, Li, Qingyun, Yu, Jiashuo, Li, Kunchang, Chen, Zhe, Yang, Xue, Zhu, Xizhou, Wang, Yali, Wang, Limin, Luo, Ping, Dai, Jifeng, Qiao, Yu
We present an interactive visual framework named InternGPT, or iGPT for short. The framework integrates chatbots that have planning and reasoning capabilities, such as ChatGPT, with non-verbal instructions like pointing movements that enable users to
Externí odkaz:
http://arxiv.org/abs/2305.05662
In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the gl
Externí odkaz:
http://arxiv.org/abs/2303.09040
Fusion-based hyperspectral image (HSI) super-resolution has become increasingly prevalent for its capability to integrate high-frequency spatial information from the paired high-resolution (HR) RGB reference image. However, most of the existing metho
Externí odkaz:
http://arxiv.org/abs/2302.06298
Autor:
Lai, Zeqiang, Fu, Ying
Hyperspectral image denoising is unique for the highly similar and correlated spectral information that should be properly considered. However, existing methods show limitations in exploring the spectral correlations across different bands and featur
Externí odkaz:
http://arxiv.org/abs/2301.11525
Autor:
Lai, Zeqiang, Fu, Ying
Hyperspectral image is unique and useful for its abundant spectral bands, but it subsequently requires extra elaborated treatments of the spatial-spectral correlation as well as the global correlation along the spectrum for building a robust and powe
Externí odkaz:
http://arxiv.org/abs/2211.14811
Publikováno v:
Neurocomputing 481 (2022) 281-293
Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes. In this paper, we propose to restore
Externí odkaz:
http://arxiv.org/abs/2209.08240