Zobrazeno 1 - 10
of 6 621
pro vyhledávání: '"HUANG, Hua"'
Autor:
Zhao, Zijia, Guo, Longteng, Yue, Tongtian, Hu, Erdong, Shao, Shuai, Yuan, Zehuan, Huang, Hua, Liu, Jing
In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset c
Externí odkaz:
http://arxiv.org/abs/2410.18715
Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) optimization methods offer a mem
Externí odkaz:
http://arxiv.org/abs/2410.08989
Effective activation functions introduce non-linear transformations, providing neural networks with stronger fitting capa-bilities, which help them better adapt to real data distributions. Huawei Noah's Lab believes that dynamic activation functions
Externí odkaz:
http://arxiv.org/abs/2409.08283
As an emerging vision sensor, the event camera has gained popularity in various vision tasks such as optical flow estimation, stereo matching, and depth estimation due to its high-speed, sparse, and asynchronous event streams. Unlike traditional appr
Externí odkaz:
http://arxiv.org/abs/2407.21735
Event-based video reconstruction has garnered increasing attention due to its advantages, such as high dynamic range and rapid motion capture capabilities. However, current methods often prioritize the extraction of temporal information from continuo
Externí odkaz:
http://arxiv.org/abs/2407.10636
Autor:
Huang, Yuanfei, Huang, Hua
Existing learning-based denoising methods typically train models to generalize the image prior from large-scale datasets, suffering from the variability in noise distributions encountered in real-world scenarios. In this work, we propose a new perspe
Externí odkaz:
http://arxiv.org/abs/2407.09094
Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. While most methods emphasize space-domain learning using image space priors like non-local similarity, frequency-domain learning using image frequency priors rema
Externí odkaz:
http://arxiv.org/abs/2406.00683
Second-order optimizers, maintaining a matrix termed a preconditioner, are superior to first-order optimizers in both theory and practice. The states forming the preconditioner and its inverse root restrict the maximum size of models trained by secon
Externí odkaz:
http://arxiv.org/abs/2405.18144
Accurately estimating scene lighting is critical for applications such as mixed reality. Existing works estimate illumination by generating illumination maps or regressing illumination parameters. However, the method of generating illumination maps h
Externí odkaz:
http://arxiv.org/abs/2404.12768
Sparse matrix-vector multiplication (SpMV) is a crucial computing kernel with widespread applications in iterative algorithms. Over the past decades, research on SpMV optimization has made remarkable strides, giving rise to various optimization contr
Externí odkaz:
http://arxiv.org/abs/2404.06047