Author name cluster

Fei Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

EAAI Journal 2025 Journal Article

A comb concatenation diffusion model for hyperspectral image super-resolution

Yinghao Xu
Hao Wang
Xin Sun
Qianlong Xie
Wenwen Zhang
Peng Ren
Fei Zhou
Susanto Rahardja

One primary challenge of hyperspectral image super-resolution is addressing the high dimensionality and complexity of both the spectral and spatial domains. The diffusion model incorporates conditional knowledge and utilizes a step-by-step denoising method, thereby skillfully coping with the high dimensionality and complexity of hyperspectral images. However, a major difficulty encountered by diffusion-based hyperspectral image super-resolution techniques is the accurate use of conditional knowledge to guide and limit the denoising process. Additionally, the lack of sufficient conditional knowledge results in inadequate information for generating detailed high-resolution images. To address these issues, we develop a comb concatenation strategy specifically designed for diffusion models. This strategy strengthens the accuracy of conditional knowledge in guiding and constraining the noisy image through the comb concatenation of conditional knowledge and noisy images. Additionally, we propose a comb concatenation diffusion model for hyperspectral image super-resolution, consisting of three components. The first component is the comb concatenation block, which accurately utilizes conditional knowledge to guide the denoising process. The second component is the conditional encoding block, responsible for generating rich conditional knowledge. Finally, we develop a noise prediction block tailored for the hyperspectral image super-resolution diffusion framework. This block effectively manages accurate and comprehensive conditional knowledge representations. The three complementary components work together to maintain both spatial resolution and spectral fidelity. Extensive experimental results on the Houston, Chikusei, and Qingdao university of science and technology-1 datasets demonstrate that our framework outperforms state-of-the-art methods in both quantitative evaluations and visual quality across various scenarios. We release our source code at https: //gitee. com/YinghaoXU/ISEDM for public evaluations.

Details DOI

EAAI Journal 2025 Journal Article

ElecBench: A large language model benchmark in electric power domain

Sai Zhang
Qiaochu Huang
Qiang Zhang
Xiao Liang
Weiwei Liu
Kunlun Gao
Fei Zhou
Congcong Shi

Large language models (LLMs) have made substantial advancements in the field of natural language processing, necessitating the development of new benchmarks to accurately track their progress. In this paper, we introduce ElecBench, the first benchmark specifically designed for the electric power domain. ElecBench comprises 24 datasets spanning different scenarios, covering general electric power knowledge and four specific business applications, with a total of 34, 030 data entries. Furthermore, we evaluate the performance of a series of open-source Chinese LLMs on ElecBench. Our experiments demonstrate that ElecBench serves as an effective benchmark for electric power scenarios and highlight that existing LLMs require further optimization to gain domain-specific knowledge and achieve better performance.

Details DOI

IS Journal 2024 Journal Article

Artificial Intelligence-Based Video Saliency Prediction: Challenges and Trends

Jiongzhi Lin
Baitao Huang
Fei Zhou

Video saliency prediction (VSP) aims to identify regions in videos that attract human attention and gaze. In the past, researchers have conducted extensive studies on VSP, establishing various video saliency datasets and prediction models. Leveraging the powerful end-to-end learning capabilities of deep learning techniques and the availability of large-scale video saliency datasets, the performance of saliency prediction models has significantly improved. Today, with the development of multimedia technologies, the task of VSP has generated numbers of promising directions, such as high dynamic range VSP and audio VSP, among others. This article focuses on the challenges of VSP in the context of multimedia technologies; reviews the research on video saliency, including video saliency datasets and prediction models; and then introduces potential research directions in conjunction with contemporary multimedia technologies.

Details DOI

NeurIPS Conference 2024 Conference Paper

Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning

Fei Zhou
Peng Wang
Lei Zhang
Zhenghua Chen
Wei Wei
Chen Ding
Guosheng Lin
Yanning Zhang

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the target task diverges from that in the source domain, meta-learning based method is susceptible to over-fitting. To overcome this, we introduce a novel framework, Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning, which is crafted to comprehensively exploit the cross-domain transferable image prior that each image can be decomposed into complementary low-frequency content details and high-frequency robust structural characteristics. Motivated by this insight, we propose to decompose each query image into its high-frequency and low-frequency components, and parallel incorporate them into the feature embedding network to enhance the final category prediction. More importantly, we introduce a feature reconstruction prior and a prediction consistency prior to separately encourage the consistency of the intermediate feature as well as the final category prediction between the original query image and its decomposed frequency components. This allows for collectively guiding the network's meta-learning process with the aim of learning generalizable image feature embeddings, while not introducing any extra computational cost in the inference phase. Our framework establishes new state-of-the-art results on multiple cross-domain few-shot learning benchmarks.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Aesthetically Relevant Image Captioning

Zhipeng Zhong
Fei Zhou
Guoping Qiu

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS’s can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC, are available at https://github.com/PengZai/ARIC

PDF Details DOI

IJCAI Conference 2022 Conference Paper

KPN-MFI: A Kernel Prediction Network with Multi-frame Interaction for Video Inverse Tone Mapping

Gaofeng Cao
Fei Zhou
Han Yan
Anjie Wang
Leidong Fan

Up to now, the image-based inverse tone mapping (iTM) models have been widely investigated, while there is little research on video-based iTM methods. It would be interesting to make use of these existing image-based models in the video iTM task. However, directly transferring the imagebased iTM models to video data without modeling spatial-temporal information remains nontrivial and challenging. Considering both the intra-frame quality and the inter-frame consistency of a video, this article presents a new video iTM method based on a kernel prediction network (KPN), which takes advantage of multi-frame interaction (MFI) module to capture temporal-spatial information for video data. Specifically, a basic encoder-decoder KPN, essentially designed for image iTM, is trained to guarantee the mapping quality within each frame. More importantly, the MFI module is incorporated to capture temporal-spatial context information and preserve the inter-frame consistency by exploiting the correction between adjacent frames. Notably, we can readily extend any existing image iTM models to video iTM ones by involving the proposed MFI module. Furthermore, we propose an inter-frame brightness consistency loss function based on the Gaussian pyramid to reduce the video temporal inconsistency. Extensive experiments demonstrate that our model outperforms state-ofthe-art image and video-based methods. The code is available at https: //github. com/caogaofeng/KPNMFI.

PDF Details DOI