Yutao Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yutao Hu has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Xianbin Cao
Beihang University
7 shared publications - Xiaoyan Luo
Beihang University
4 shared publications - Baochang Zhang
Beihang University
3 shared publications - Jun Zhang
Beijing Institute of Technology
3 shared publications - Jungong Han
The University of Sheffield
3 shared publications - Jian Yang
Beijing Institute of Technology
2 shared publications
Latest Publications
- 21 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP  (10518215) , 1
Towards Semantic-aware Aerial Video Anomaly Detection by Exploiting Multimodal Large Language Model
Drones have become increasingly widely applied in surveillance systems due to their mobility, making aerial video anomaly detection methods more crucial. Anomalies in aerial videos often present as semantic conflicts, such as the presence of unexpected objects or unusual behaviors that do not align with the context. Previous approaches often relied on manually crafted knowledge graphs to detect such conflicts, which suffer from poor scalability. Recently, owing to their sufficient alignment training, multimodal large language models (MLLMs) have emerged as a generalized solution for semantic understanding. However, the direct application of MLLMs does not yield satisfactory anomaly detection performance in aerial videos. First, aerial videos often manifest platform-induced pseudo-motion, which obscures the true motion of objects and exacerbates detection errors. Second, without sufficient labeled data for fine-tuning, generic MLLMs often lack scene-level semantic guidance to reliably distinguish abnormal events that include contextually inappropriate behaviors. To address these challenges, we propose SemAero, an MLLM-based framework to address these challenges by: 1) designing an ego-motion reduction module to enhance model perception on object movement, 2) generating scene-specific prompts adaptively with step-by-step guidance for reasonable output, and 3) refining scores with dual-stream consistent feature for better domain-specific anomaly detection. Evaluated across 8 diverse aerial scenes and 73 sub-datasets, SemAero achieves a 3.09% improvement in AUC-ROC over the second-best model, demonstrating its ability in aerial video anomaly detection.
- 21 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP  (10518215) , 1
Towards Semantic-aware Aerial Video Anomaly Detection by Exploiting Multimodal Large Language Model
Drones have become increasingly widely applied in surveillance systems due to their mobility, making aerial video anomaly detection methods more crucial. Anomalies in aerial videos often present as semantic conflicts, such as the presence of unexpected objects or unusual behaviors that do not align with the context. Previous approaches often relied on manually crafted knowledge graphs to detect such conflicts, which suffer from poor scalability. Recently, owing to their sufficient alignment training, multimodal large language models (MLLMs) have emerged as a generalized solution for semantic understanding. However, the direct application of MLLMs does not yield satisfactory anomaly detection performance in aerial videos. First, aerial videos often manifest platform-induced pseudo-motion, which obscures the true motion of objects and exacerbates detection errors. Second, without sufficient labeled data for fine-tuning, generic MLLMs often lack scene-level semantic guidance to reliably distinguish abnormal events that include contextually inappropriate behaviors. To address these challenges, we propose SemAero, an MLLM-based framework to address these challenges by: 1) designing an ego-motion reduction module to enhance model perception on object movement, 2) generating scene-specific prompts adaptively with step-by-step guidance for reasonable output, and 3) refining scores with dual-stream consistent feature for better domain-specific anomaly detection. Evaluated across 8 diverse aerial scenes and 73 sub-datasets, SemAero achieves a 3.09% improvement in AUC-ROC over the second-best model, demonstrating its ability in aerial video anomaly detection.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 4014316
Measurement-Consistent Low-Field MRI Enhancement via k-Space Noise Modeling
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 4014316
Measurement-Consistent Low-Field MRI Enhancement via k-Space Noise Modeling
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 4010915
FIDNet: Frequency-Informed Diffusion Network for Low-Field MRI Enhancement
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 4010915
FIDNet: Frequency-Informed Diffusion Network for Low-Field MRI Enhancement
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (5) , 6586-6600
AEGIS: Using Conditional Multi-View Diffusion Model to Achieve Angiographic Enhancement in Non-Contrast CT
Angiographic enhancement of non-contrast CT (NCCT) using AI techniques is essential for diagnosing patients unable to use contrast agents. However, AI angiography remains a challenging task because of the feature fragility, structural complexity, and spatial continuity. In this paper, we propose an angiographic framework based on a conditional multi-view diffusion model called AEGIS with three innovations: multi-view hybrid learning (MHL), conditional angiographic diffusion estimation (CADE), and multi-view map fusion (MMF). 1) MHL targets Contrast Map (CM), the difference between NCCT and CT angiography, from multiple views to perceive 3D features in 2D space, enhancing the stability of feature representation. 2) CADE is a conditional diffusion model using NCCT as spatial guidance, providing crucial information for CM generation. 3) MMF adopts a lightweight AutoEncoder for filtering and fusing multi-view CMs, maintaining coherence between adjacent slices while modifying slight bias in low-dimensional representations, thus optimizing data quality and accuracy. Experiments demonstrate our superior performance, which achieve state-of-the-art image quality (PSNR+6.69, SSIM+3.17, MSE-46.38), segmentation evaluation (CADIR×10.49, HSDIR×5.57) and feature distance (FID-64.27). Visualizations and positive evaluation scores from clinicians further reveals that AEGIS has significant potential in clinical applications.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (5) , 6586-6600
AEGIS: Using Conditional Multi-View Diffusion Model to Achieve Angiographic Enhancement in Non-Contrast CT
Angiographic enhancement of non-contrast CT (NCCT) using AI techniques is essential for diagnosing patients unable to use contrast agents. However, AI angiography remains a challenging task because of the feature fragility, structural complexity, and spatial continuity. In this paper, we propose an angiographic framework based on a conditional multi-view diffusion model called AEGIS with three innovations: multi-view hybrid learning (MHL), conditional angiographic diffusion estimation (CADE), and multi-view map fusion (MMF). 1) MHL targets Contrast Map (CM), the difference between NCCT and CT angiography, from multiple views to perceive 3D features in 2D space, enhancing the stability of feature representation. 2) CADE is a conditional diffusion model using NCCT as spatial guidance, providing crucial information for CM generation. 3) MMF adopts a lightweight AutoEncoder for filtering and fusing multi-view CMs, maintaining coherence between adjacent slices while modifying slight bias in low-dimensional representations, thus optimizing data quality and accuracy. Experiments demonstrate our superior performance, which achieve state-of-the-art image quality (PSNR+6.69, SSIM+3.17, MSE-46.38), segmentation evaluation (CADIR×10.49, HSDIR×5.57) and feature distance (FID-64.27). Visualizations and positive evaluation scores from clinicians further reveals that AEGIS has significant potential in clinical applications.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-15
Diffusion Self-Distillation for Remote Sensing Scene Classification
Remote sensing scene classification, a fundamental task in remote image analysis, has obtained rapid progress due to the powerful capabilities of Convolutional Neural Networks (CNNs). Achieving precise classification performance heavily relies on the feature extraction capacity of the network. However, due to the large variation and severe distortion within the images, extracting robust feature representations is necessary but challenging. Self-distillation could enhance the shallow layers by providing stronger gradients and more accurate supervision from deeper layers, thereby promoting the extraction of spatially detailed features. Nonetheless, due to the limited capacity of shallow layers to learn truly valuable knowledge, shallow layer features can be viewed as the noisy version of deep layer features and contain more disruptive factors, which significantly impedes the effectiveness of self-distillation. To address this issue, in this paper, we establish the Diffusion Self-Distillation Network (DSDNet), which incorporates the conditional diffusion denoising model into the self-distillation framework. Specifically, DSDNet filters noise from shallow features through the diffusion denoising process, enabling more precise and accurate distillation between the refined student features and the teacher features. Extensive experiments on four challenging remote sensing datasets emonstrate that the proposed DSDNet achieves significant performance improvements over various backbone networks with negligible increases in parameters, delivering state-of-the-art classification performance. Our code and dataset are available on https://github.com/toggle1995/DSDNet.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-15
Diffusion Self-Distillation for Remote Sensing Scene Classification
Remote sensing scene classification, a fundamental task in remote image analysis, has obtained rapid progress due to the powerful capabilities of Convolutional Neural Networks (CNNs). Achieving precise classification performance heavily relies on the feature extraction capacity of the network. However, due to the large variation and severe distortion within the images, extracting robust feature representations is necessary but challenging. Self-distillation could enhance the shallow layers by providing stronger gradients and more accurate supervision from deeper layers, thereby promoting the extraction of spatially detailed features. Nonetheless, due to the limited capacity of shallow layers to learn truly valuable knowledge, shallow layer features can be viewed as the noisy version of deep layer features and contain more disruptive factors, which significantly impedes the effectiveness of self-distillation. To address this issue, in this paper, we establish the Diffusion Self-Distillation Network (DSDNet), which incorporates the conditional diffusion denoising model into the self-distillation framework. Specifically, DSDNet filters noise from shallow features through the diffusion denoising process, enabling more precise and accurate distillation between the refined student features and the teacher features. Extensive experiments on four challenging remote sensing datasets emonstrate that the proposed DSDNet achieves significant performance improvements over various backbone networks with negligible increases in parameters, delivering state-of-the-art classification performance. Our code and dataset are available on https://github.com/toggle1995/DSDNet.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33  (6) , 2813-2825
Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection
Anomaly detection in surveillance videos aims to identify frames where abnormal events happen. Existing approaches assume that the training and testing videos are from the same scene, exhibiting poor generalization performance when encountering an unseen scene. In this paper, we propose a Variational Anomaly Detection Network (VADNet), which is characterized by its high scene-adaptation - it can identify abnormal events in a new scene only via referring to a few normal samples without fine-tuning. Our model embodies two major innovations. First, a novel Variational Normal Inference (VNI) module is proposed to formulate image reconstruction in a conditional variational auto-encoder (CVAE) framework, which learns a probabilistic decision model instead of a traditional deterministic one. Secondly, a Margin Learning Embedding (MLE) module is leveraged to boost the variational inference and aid in distinguishing normal events. We theoretically demonstrate that minimizing the triplet loss in MLE module facilitates maximizing the evidence lower bound (ELBO) of CVAE, which promotes the convergence of VNI. By incorporating variational inference with margin learning, VADNet becomes much more generative that is able to handle the uncertainty caused by the changed scene and limited reference data. Extensive experiments on several datasets demonstrate that the proposed VADNet can adapt to a new scene effectively without fine-tuning and achieve remarkable performance, which outperforms other methods significantly and establishes new state-of-the-art in the case of few-shot scene-adaptive anomaly detection. We believe our method is closer to real-world application due to its strong generalization ability. All codes are released in https://github.com/huangxx156/VADNet.
- 8 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33  (6) , 2813-2825
Boosting Variational Inference With Margin Learning for Few-Shot Scene-Adaptive Anomaly Detection
Anomaly detection in surveillance videos aims to identify frames where abnormal events happen. Existing approaches assume that the training and testing videos are from the same scene, exhibiting poor generalization performance when encountering an unseen scene. In this paper, we propose a Variational Anomaly Detection Network (VADNet), which is characterized by its high scene-adaptation - it can identify abnormal events in a new scene only via referring to a few normal samples without fine-tuning. Our model embodies two major innovations. First, a novel Variational Normal Inference (VNI) module is proposed to formulate image reconstruction in a conditional variational auto-encoder (CVAE) framework, which learns a probabilistic decision model instead of a traditional deterministic one. Secondly, a Margin Learning Embedding (MLE) module is leveraged to boost the variational inference and aid in distinguishing normal events. We theoretically demonstrate that minimizing the triplet loss in MLE module facilitates maximizing the evidence lower bound (ELBO) of CVAE, which promotes the convergence of VNI. By incorporating variational inference with margin learning, VADNet becomes much more generative that is able to handle the uncertainty caused by the changed scene and limited reference data. Extensive experiments on several datasets demonstrate that the proposed VADNet can adapt to a new scene effectively without fine-tuning and achieve remarkable performance, which outperforms other methods significantly and establishes new state-of-the-art in the case of few-shot scene-adaptive anomaly detection. We believe our method is closer to real-world application due to its strong generalization ability. All codes are released in https://github.com/huangxx156/VADNet.
- 28 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60  (01962892) , 1-13
Variational Self-Distillation for Remote Sensing Scene Classification
Supported by deep learning techniques, remote sensing scene classification, a fundamental task in remote image analysis, has recently obtained remarkable progress. However, due to the severe uncertainty and perturbation within an image, it is still a challenging task and remains many unsolved problems. In this article, we note that regular one-hot labels cannot precisely describe remote sensing images, and they fail to provide enough information for supervision and limiting the discriminative feature learning of the network. To solve this problem, we propose a variational self-distillation network (VSDNet), in which the class entanglement information from the prediction vector acts as the supplement to the category information. Then, the exploited information is hierarchically distilled from the deep layers into the shallow parts via a variational knowledge transfer (VKT) module. Notably, the VKT module performs knowledge distillation in a probabilistic way through variational estimation, which enables end-to-end optimization for mutual information and promotes robustness to uncertainty within the image. Extensive experiments on four challenging remote sensing datasets demonstrate that, with a negligible parameter increase, the proposed VSDNet brings a significant performance improvement over different backbone networks and delivers state-of-the-art results.
- 28 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60  (01962892) , 1-13
Variational Self-Distillation for Remote Sensing Scene Classification
Supported by deep learning techniques, remote sensing scene classification, a fundamental task in remote image analysis, has recently obtained remarkable progress. However, due to the severe uncertainty and perturbation within an image, it is still a challenging task and remains many unsolved problems. In this article, we note that regular one-hot labels cannot precisely describe remote sensing images, and they fail to provide enough information for supervision and limiting the discriminative feature learning of the network. To solve this problem, we propose a variational self-distillation network (VSDNet), in which the class entanglement information from the prediction vector acts as the supplement to the category information. Then, the exploited information is hierarchically distilled from the deep layers into the shallow parts via a variational knowledge transfer (VKT) module. Notably, the VKT module performs knowledge distillation in a probabilistic way through variational estimation, which enables end-to-end optimization for mutual information and promotes robustness to uncertainty within the image. Extensive experiments on four challenging remote sensing datasets demonstrate that, with a negligible parameter increase, the proposed VSDNet brings a significant performance improvement over different backbone networks and delivers state-of-the-art results.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (3) , 4005-4018
Hierarchical Self-Distilled Feature Learning for Fine-Grained Visual Categorization
Fine-grained visual categorization (FGVC) relies on hierarchical features extracted by deep convolutional neural networks (CNNs) to recognize closely alike objects. Particularly, shallow layer features containing rich spatial details are vital for specifying subtle differences between objects but are usually inadequately optimized due to gradient vanishing during backpropagation. In this article, hierarchical self-distillation (HSD) is introduced to generate well-optimized CNNs features for accurate fine-grained categorization. HSD inherits from the widely applied deep supervision and implements multiple intermediate losses for reinforced gradients. Besides that, we observe that the hard (one-hot) labels adopted for intermediate supervision hurt the performance of FGVC by enforcing overstrict supervision. As a solution, HSD seeks self-distillation where soft predictions generated by deeper layers of the network are hierarchically exploited to supervise shallow parts. Moreover, self-information entropy loss (SIELoss) is designed in HSD to adaptively soften intermediate predictions and facilitate better convergence. In addition, the gradient detached fusion (GDF) module is incorporated to produce an ensemble result with multiscale features via effective feature fusion. Extensive experiments on four challenging fine-grained datasets show that, with neglectable parameter increase, the proposed HSD framework and the GDF module both bring significant performance gains over different backbones, which also achieves state-of-the-art classification performance.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (3) , 4005-4018
Hierarchical Self-Distilled Feature Learning for Fine-Grained Visual Categorization
Fine-grained visual categorization (FGVC) relies on hierarchical features extracted by deep convolutional neural networks (CNNs) to recognize closely alike objects. Particularly, shallow layer features containing rich spatial details are vital for specifying subtle differences between objects but are usually inadequately optimized due to gradient vanishing during backpropagation. In this article, hierarchical self-distillation (HSD) is introduced to generate well-optimized CNNs features for accurate fine-grained categorization. HSD inherits from the widely applied deep supervision and implements multiple intermediate losses for reinforced gradients. Besides that, we observe that the hard (one-hot) labels adopted for intermediate supervision hurt the performance of FGVC by enforcing overstrict supervision. As a solution, HSD seeks self-distillation where soft predictions generated by deeper layers of the network are hierarchically exploited to supervise shallow parts. Moreover, self-information entropy loss (SIELoss) is designed in HSD to adaptively soften intermediate predictions and facilitate better convergence. In addition, the gradient detached fusion (GDF) module is incorporated to produce an ensemble result with multiscale features via effective feature fusion. Extensive experiments on four challenging fine-grained datasets show that, with neglectable parameter increase, the proposed HSD framework and the GDF module both bring significant performance gains over different backbones, which also achieves state-of-the-art classification performance.
- Open Access
- 31 January 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 17  (1s) , 1-20
Alignment Enhancement Network for Fine-grained Visual Categorization
Fine-grained visual categorization (FGVC) aims to automatically recognize objects from different sub-ordinate categories. Despite attracting considerable attention from both academia and industry, it remains a challenging task due to subtle visual differences among different classes. Cross-layer feature aggregation and cross-image pairwise learning become prevailing in improving the performance of FGVC by extracting discriminative class-specific features. However, they are still inefficient to fully use the cross-layer information based on the simple aggregation strategy, while existing pairwise learning methods also fail to explore long-range interactions between different images. To address these problems, we propose a novel Alignment Enhancement Network (AENet), including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Alignment (CIA). The CLA module exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross-layer feature aggregation to improve the capacity of feature representation for input images. The new CIA module is further introduced to produce the aligned feature map, which can enhance the relevant information as well as suppress the irrelevant information across the whole spatial region. Our method is based on an underlying assumption that the aligned feature map should be closer to the inputs of CIA when they belong to the same category. Accordingly, we establish Semantic Affinity Loss to supervise the feature alignment within each CIA block. Experimental results on four challenging datasets show that the proposed AENet achieves the state-of-the-art results over prior arts.
- 31 January 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 17  (1s) , 1-20
Open AccessAlignment Enhancement Network for Fine-grained Visual Categorization
Fine-grained visual categorization (FGVC) aims to automatically recognize objects from different sub-ordinate categories. Despite attracting considerable attention from both academia and industry, it remains a challenging task due to subtle visual differences among different classes. Cross-layer feature aggregation and cross-image pairwise learning become prevailing in improving the performance of FGVC by extracting discriminative class-specific features. However, they are still inefficient to fully use the cross-layer information based on the simple aggregation strategy, while existing pairwise learning methods also fail to explore long-range interactions between different images. To address these problems, we propose a novel Alignment Enhancement Network (AENet), including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Alignment (CIA). The CLA module exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross-layer feature aggregation to improve the capacity of feature representation for input images. The new CIA module is further introduced to produce the aligned feature map, which can enhance the relevant information as well as suppress the irrelevant information across the whole spatial region. Our method is based on an underlying assumption that the aligned feature map should be closer to the inputs of CIA when they belong to the same category. Accordingly, we establish Semantic Affinity Loss to supervise the feature alignment within each CIA block. Experimental results on four challenging datasets show that the proposed AENet achieves the state-of-the-art results over prior arts.
- 3 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31  (1) , 301-314
Attentional Kernel Encoding Networks for Fine-Grained Visual Categorization
Fine-grained visual categorization aims to recognize objects from different sub-ordinate categories, which is a challenging task due to subtle visual differences between images. It is highly desired to identify discriminative regions while achieving highly non-linear compact representation for fine-grained visual categorization. However, existing methods either rely on manually defined part-based annotations to indicate the distinctive regions or operate on longitudinal vectors to capture the non-linear information, which may lose important spatial layout information. In this paper, we propose the Attentional Kernel Encoding Networks (AKEN) for fine-grained visual categorization. Specifically, the AKEN aggregates feature maps from the last convolutional layer of ConvNets to obtain a holistic feature representation. By Fourier embedding, it encodes features from both the longitudinal and transverse directions, which largely retains the spatial layout information. Moreover, we incorporate a Cascaded Attention (Cas-Attention) module to highlight local regions that distinguish among subordinate categories, enabling the AKEN to extract the most discriminative features. Working in conjunction with the attention mechanism, the proposed AKEN combines the strengths of ConvNets and kernels for non-linear feature learning, which can establish discriminative and descriptive feature representations for fine-grained image categorization. Experiments on three benchmark datasets show that the proposed AKEN delivers highly competitive performance, surpassing most existed methods and achieving state-of-the-art results.
- 3 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31  (1) , 301-314
Attentional Kernel Encoding Networks for Fine-Grained Visual Categorization
Fine-grained visual categorization aims to recognize objects from different sub-ordinate categories, which is a challenging task due to subtle visual differences between images. It is highly desired to identify discriminative regions while achieving highly non-linear compact representation for fine-grained visual categorization. However, existing methods either rely on manually defined part-based annotations to indicate the distinctive regions or operate on longitudinal vectors to capture the non-linear information, which may lose important spatial layout information. In this paper, we propose the Attentional Kernel Encoding Networks (AKEN) for fine-grained visual categorization. Specifically, the AKEN aggregates feature maps from the last convolutional layer of ConvNets to obtain a holistic feature representation. By Fourier embedding, it encodes features from both the longitudinal and transverse directions, which largely retains the spatial layout information. Moreover, we incorporate a Cascaded Attention (Cas-Attention) module to highlight local regions that distinguish among subordinate categories, enabling the AKEN to extract the most discriminative features. Working in conjunction with the attention mechanism, the proposed AKEN combines the strengths of ConvNets and kernels for non-linear feature learning, which can establish discriminative and descriptive feature representations for fine-grained image categorization. Experiments on three benchmark datasets show that the proposed AKEN delivers highly competitive performance, surpassing most existed methods and achieving state-of-the-art results.