检索结果-内蒙古大学图书馆

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Yong Wang, Yuanzhi Cui, Zhen Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens In Minist EducPCA Lab Nanjing Peoples R China

ISBN: (纸本)9798350301298

Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and the contribution of different modalities varies significantly. In this work, we mitigate this issue by proposing a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation, aiming to enhance the discriminative features of each modality. Specially, the representation of each modality is decoupled into two parts, i.e., modality-irrelevant/-exclusive spaces, in a self-regression manner. DMD utilizes a graph distillation unit (GD-Unit) for each decoupled part so that each GD can be performed in a more specialized and effective manner. A GD-Unit consists of a dynamic graph where each vertice represents a modality and each edge indicates a dynamic knowledge distillation. Such GD paradigm provides a flexible knowledge transfer manner where the distillation weights can be automatically learned, thus enabling diverse crossmodal knowledge transfer patterns. Experimental results show DMD consistently obtains superior performance than state-of-the-art MER methods. Visualization results show the graph edges in DMD exhibit meaningful distributional patterns w.r.t. the modality-irrelevant/-exclusive feature spaces. Codes are released at https://***/mdswyz/DMD.

关键词： body gesture Humans: Face movement pose

来源：评论

学校读者我要写书评

暂无评论

Spectral-Spatial Attention-Guided Multi-Resolution Network for Pansharpening

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 7559-7571页

作者： Xu, Shen Zhong, Shengwei Li, Hui Gong, Chen Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Social Key Lab Intelligent Percept & Syst High Dimens Inf Minist EducSch Comp Sci & EngnPCA Lab Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Zhengzhou Tobacco Res Inst CNTC Zhengzhou 450001 Peoples R China

Pansharpening is a technique that combines high-resolution panchromatic (PAN) images with low-resolution multispectral (MS) images to produce high-resolution MS (HRMS) images. Deep learning-based pansharpening have outperformed traditional methods on detail injection and spectral preserving. However, existing methods often directly learn the mapping between PAN, MS, and fused HRMS, without considering the spectral-spatial feature correlation in separate bands among PAN, low-resolution PAN (LRPAN), and MS. To address this limitation, we propose a novel network called spectral-spatial attention-guided multiresolution network (SSA-MRN). Initially, SSA-MRN incorporates LRPAN images to capture the intermediate features between MS and PAN images. It also uses the individual bands of MS to learn band-specific features. Based on the comprehensive features, the spectral-spatial attention integration (SSAI) module is introduced at various scales. SSAI leverages a dot-product attention mechanism to selectively enhance the associative spectral-spatial features between PAN images and MS images across different spectral bands. The features learned by the SSAI are progressively fused at each resolution to produce the final output. Experiments on two benchmark datasets are conducted at both reduced-resolution and full-resolution. Results demonstrate that our SSA-MRN significantly enhances pansharpening quality compared to five classical methods and four state-of-the-art deep learning-based methods.

关键词： Feature extraction Pansharpening Attention mechanisms Interpolation Spatial resolution Learning systems Image reconstruction Correlation US Government Training Multi-resolution multi-spectral (MS) feature pansharpening spectral-spatial attention integration (SSAI)

来源：评论

学校读者我要写书评

暂无评论

Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance 23

Implicit Obstacle Map-driven Indoor Navigation Model for Rob...

引用

31st ACM International Conference on Multimedia (MM)

作者： Xie, Wei Jiang, Haobo Gu, Shuo Xie, Jin Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Key Lab Intelligent Percept & Syst High Dimens In Sch Comp Sci & EngnMinist EducPCA Lab Nanjing Peoples R China

ISBN: (纸本)9798400701085

Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks. Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness. To mitigate it, in this paper, we propose a novel implicit obstacle map-driven indoor navigation framework for robust obstacle avoidance, where an implicit obstacle map is learned based on the historical trial-and-error experience rather than the visual image. In order to further improve the navigation efficiency, a non-local target memory aggregation module is designed to leverage a non-local network to model the intrinsic relationship between the target semantic and the target orientation clues during the navigation process so as to mine the most target-correlated object clues for the navigation decision. Extensive experimental results on AI2-Thor and RoboTHOR benchmarks verify the excellent obstacle avoidance and navigation efficiency of our proposed method. The core source code is available at https://***/xwaiyy123/object-navigation.

关键词： Object navigation Implicit obstacle map Non-local target memory aggregation

来源：评论

学校读者我要写书评

暂无评论

TRTST: Arbitrary High-Quality Text-Guided Style Transfer With Transformers

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 759-771页

作者： Chen, Haibo Wang, Zhoujie Zhao, Lei Li, Jun Yang, Jian Nanjing Univ Sci & Technol Minist Educ PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China

Text-guided style transfer aims to repaint a content image with the target style described by a text prompt, offering greater flexibility and creativity compared to traditional image-guided style transfer. Despite the potential, existing text-guided style transfer methods often suffer from many issues, including insufficient visual quality, poor generalization ability, or a reliance on large amounts of paired training data. To address these limitations, we leverage the inherent strengths of transformers in handling multimodal data and propose a novel transformer-based framework called TRTST that not only achieves unpaired arbitrary text-guided style transfer but also significantly improves the visual quality. Specifically, TRTST explores combining a text transformer encoder with an image transformer encoder to project the input text prompt and content image into a joint embedding space and extract the desired style and content features. These features are then input into a multimodal co-attention module to stylize the image sequence based on the text sequence. We also propose a new adaptive parametric positional encoding (APPE) scheme which can adaptively produce different positional encodings to optimally match different inputs with a position encoder. In addition, to further improve content preservation, we introduce a text-guided identity loss to our model. Extensive results and comparisons are conducted to demonstrate the effectiveness and superiority of our method.

关键词： Transformers Visualization Training Feature extraction Training data Image coding Data models Painting Impedance matching Encoding Text-guided style transfer transformer unpaired visual quality generalization ability

来源：评论

学校读者我要写书评

暂无评论

Progressive Bayesian Inference for Scribble-Supervised Semantic Segmentation 37

Progressive Bayesian Inference for Scribble-Supervised Seman...

引用

37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Zhou, Chuanwei Xu, Chunyan Cui, Zhen Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens In Minist EducSch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781577358800

The scribble-supervised semantic segmentation is an important yet challenging task in the field of computer vision. To deal with the pixel-wise sparse annotation problem, we propose a Progressive Bayesian Inference (PBI) framework to boost the performance of the scribble-supervised semantic segmentation, which can effectively infer the semantic distribution of these unlabeled pixels to guide the optimization of the segmentation network. The PBI dynamically improves the model learning from two aspects: the Bayesian inference module (i.e., semantic distribution learning) and the pixel-wise segmenter (i.e., model updating). Specifically, we effectively infer the semantic probability distribution of these unlabeled pixels with our designed Bayesian inference module, where its guidance is estimated through the Bayesian expectation maximization under the situation of partially observed data. The segmenter can be progressively improved under the joint guidance of the original scribble information and the learned semantic distribution. The segmenter optimization and semantic distribution promotion are encapsulated into a unified architecture where they could improve each other with mutual evolution in a progressive fashion. Comprehensive evaluations of several benchmark datasets demonstrate the effectiveness and superiority of our proposed PBI when compared with other state-of-the-art methods applied to the scribble-supervised semantic segmentation task.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Edge-Enhanced Heterogeneous Graph Transformer With Priority-Based Feature Aggregation for Multi-Agent Trajectory Prediction

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION SYSTEMS 2025年第2期26卷 2266-2281页

作者： Zhou, Xiangzheng Chen, Xiaobo Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA Lab Minist EducKey Lab Intelligent Percept & Syst Hig Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Social Nanjing 210094 Peoples R China Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Shandong Peoples R China

Trajectory prediction, which aims to predict the future positions of all agents in a crowd scene, given their past trajectories, plays a vital role in improving the safety of autonomous driving vehicles. For heterogeneous agents, it is imperative to account for the gap in feature distribution differences between agents in different categories. Besides, exploring the reference relationship between the future motions of agents is crucial yet overlooked in previous trajectory prediction methods. To tackle these challenges, we propose an edge-enhanced heterogeneous graph Transformer with priority-based feature aggregation for multi-modal trajectory prediction. Specifically, a new edge-enhanced heterogeneous interaction module that carries relative position information via edges is proposed to explore the complex interaction among agents. Additionally, we propose the concept of priority during the decoding phase and the corresponding measuring method, based on which a priority-based feature aggregation module is presented to enable referencing between agents, allowing for a more reasonable trajectory generation process. Additionally, we design an effective feature fusion method based on state refinement LSTM so that temporal and social features can be well integrated while accounting for their roles in trajectory prediction. Extensive experimental results on public datasets demonstrate that our approach outperforms the state-of-the-art baseline methods, confirming the effectiveness of our proposed method. The source code of our EPHGT model will be publicly released at https://***/xbchen82/EPHGT.

关键词： Trajectory Transformers Decoding Predictive models Feature extraction Pedestrians Computational modeling Long short term memory Attention mechanisms Adaptation models Trajectory prediction priority-based feature aggregation heterogeneous interaction modeling multi-modal prediction

来源：评论

学校读者我要写书评

暂无评论

Graph Spectral Perturbation for 3D Point Cloud Contrastive Learning 23

Graph Spectral Perturbation for 3D Point Cloud Contrastive L...

引用

31st ACM International Conference on Multimedia (MM)

作者： Han, Yuehui Chen, Jiaxin Qian, Jianjun Xie, Jin Nanjing Univ Sci & Technol Key Lab Intelligent Percept & Syst High Dimens In Jiangsu Key Lab Image & Video Understanding Socia PCA LabMinist EducSch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9798400701085

3D point cloud contrastive learning has attracted increasing attention due to its efficient learning ability. By distinguishing the similarity relationship between positive and negative samples in the feature space, it can learn effective point cloud feature representations without manual annotation. However, most point cloud contrastive learning methods construct contrastive samples by perturbing point clouds in data space or introducing multi-modality/format data, which may be difficult to control the intensity of the perturbation or introduce interference from different modalities/formats. To this end, in this paper, we propose a novel graph spectral perturbation based contrastive learning framework (GSPCon) for efficient and robust self-supervised 3D point cloud representation learning. It aims to perform perturbations in the graph spectral domain to construct contrastive samples of the point cloud. Specifically, we first naturally represent the point cloud as a k-nearest neighbors (KNN) graph, and adaptively transform the coordinates of the points into the graph spectral domain based on the graph Fourier transform (GFT). Then we implement data augmentation in the graph spectral domain by perturbing the spectral representations. Finally, the contrastive samples are generated by employing the inverse graph Fourier transform (IGFT) to transform the augmented spectral representations back to the point clouds. Experimental results show that our method achieves the state-of-the-art performance on various downstream tasks. Source code is available at https://***/yh-han/***.

关键词： 3D point clouds self-supervised representation learning contrastive learning graph spectral perturbation

来源：评论

学校读者我要写书评

暂无评论

A survey on deep learning for polyp segmentation: techniques, challenges and future trends

引用

Visual Intelligence 2025年第1期3卷 1-20页

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. © The Author(s) 2025.

关键词： Comprehensive evaluation Deep learning Medical imaging Polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

TranPulse: Remote Photoplethysmography Estimation With Time-Varying Supervision to Disentangle Multiphysiologically Interference

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Shao, Hang Luo, Lei Qian, Jianjun Chen, Shuo Hu, Chuanfei Yang, Jian Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Minist Educ Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Social Nanjing 210094 Peoples R China RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan Southeast Univ Sch Automat Key Lab Measurement & Control Complex Syst Engn Minist Educ Nanjing 211189 Peoples R China

Physical signs of the body that are too subtle to be observed by human eyes can reflect significant health indicators. Although many vision-based approaches have been devoted to recovery, they topically focus on recognizing explicit features such as colors, textures, and patches, and pay less attention to the entanglement and disentanglement among implicit biological characteristics. Meanwhile, existing deep networks for remote physiological detection are generally weak or deliberately neglectful in eliminating long-term time-varying interference and noise. To address these issues, we propose TranPulse, a novel remote estimation paradigm dedicated to video transformer-based polyphysiological disentanglement for robust heart rate (HR) prediction. Specifically, we improve existing single-stage transformer-based cardiac estimation backbones into a targeted two-stage architecture, which consists of a pair of asymmetric encoder and decoder. The encoder, which is the important module for heart waveform prediction, guides global attention to spatio-temporal enhancement and perception of periodic signals according to facial frame differences. The decoder, which is the core strategy pipeline for unwrapping time-varying disturbances, uses waveform gradient variations as the constraint for high-dimensional representations to separate spikes from multiple uncorrelated obstructions. Simultaneously, we integrate the synchronous computation of the encoder's fusion of appearance and frame difference to provide more detailed guidance for in-the-wild spatio-temporal modeling, and design a more reliable regression loss function to coordinate long-term temporal and frame-wise spatial supervision. We train, validate, and practice our proposed model on multiple publicly available datasets, where it achieves competitive performance in pulse estimation by extensive experimental results.

关键词： Frame-wise supervision heart rate (HR) remote biosignal estimation spatio-temporal modeling vision transformer (ViT) Frame-wise supervision heart rate (HR) remote biosignal estimation spatio-temporal modeling vision transformer (ViT)

来源：评论

学校读者我要写书评

暂无评论

Generalizable Neural Radiance Field with Hierarchical Geometry Constraint 6th

Generalizable Neural Radiance Field with Hierarchical Geomet...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Zhang, Qinyi Xie, Jin Yang, Hang Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China

ISBN: (纸本)9789819984312;9789819984329

The emergence of the generalized neural radiance field models has greatly expanded the applicability of novel view synthesis task. However, existing methods primarily rely on 2D features obtained from neighboring views to assist the rendering, which often leads to degradation in unseen viewpoints. Some approaches introduce cost volumes in the model to provide geometric priors, but such coarse geometric information fails to constrain the model effectively, resulting in rendered images with abundant artifacts. In this work, we propose to provide the model with hierarchical geometry constraints to achieve better rendering results. We introduce cascaded MVSNet to provide hierarchical scene structural features for inferring the underlying scene geometry. It constrains the model's rendering under unseen viewpoints. Also, the hierarchical features provide fine representations that helps the reconstruction of details. Additionally, we utilize the hierarchical depth maps generated by cascade MVSNet to constrain the sampling process, ensuring that the sampled points are concentrated near the scene surface. Such sampling strategy filtering out numerous useless sampling points and improving both the sampling efficiency and rendering quality. Unlike previous generalized methods, we employ a new weight function proposed by Neus to eliminate inherent biases in the density field, disentangling the prediction of color and density with a signed distance field. Extensive experiments have demonstrated that our proposed method significantly improves the rendering quality and outperforms previous methods.

关键词： Novel view synthesis Neural radiance field Generalization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：