检索结果-内蒙古大学图书馆

Robust Semi-Supervised Deep Nonnegative Matrix Factorization with Constraint Propagation for Data Representation

学校读者我要写书评

暂无评论

IEEE Transactions on Big Data 2025年

作者： Peng, Siyuan Yin, Jingxing Yang, Zhijing Nie, Feiping Chen, Badong Guangdong University of Technology School of Information Engineering 510006 China Northwestern Polytechnical University School of Computer Science Center for OPTical IMagery Analysis and Learning Xi'an710072 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China

Deep nonnegative matrix factorization (DNMF) technique has attached much great attention in recent year, since it can effectively discover the underlying hierarchical structure of complex data. However, most existing unsupervised and semi-supervised DNMF approaches not only suffer from the noisy data seriously, but also fail to enhance the decomposition quality of DNMF obviously by using the obtained supervisory information. To overcome these drawbacks, a robust semi-supervised DNMF method, called the correntropy based semi-supervised DNMF with constraint propagation (CSDCP), is proposed in this paper for learning a compact and meaningful data representation from the original data. Particularly, instead of adopting the traditional Frobenius norm, CSDCP employs the nonlinear and local similarity measure (e.g., correntropy) as the loss function in DNMF to enhance the robustness of DNMF for the noisy data. In addition, the hypergraph based constraint propagation (HCP) algorithm is adopted in CSDCP to exploit the limited supervisory information fully for capturing good data representation. Moreover, algorithm analysis of CSDCP is presented in this paper, including convergence analysis, robustness analysis supervised information analysis, and computational complexity. Extensive experimental results have illustrated that, in comparison to the most related DNMF approaches, CSDCP usually has better clustering results on six nonnegative datasets in clustering tasks. © 2015 IEEE.

关键词： Self-supervised learning

Temporally Consistent Stereo Matching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Jiaxi Yao, Chengtang Wu, Yuwei Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Horizon Robotics China

Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the estimation at the single-frame level. This commonly leads to temporally inconsistent results, especially in ill-posed regions. In this paper, we aim to leverage temporal information to improve the temporal consistency, accuracy, and efficiency of stereo matching. To achieve this, we formulate video stereo matching as a process of temporal disparity completion followed by continuous iterative refinements. Specifically, we first project the disparity of the previous timestamp to the current viewpoint, obtaining a semi-dense disparity map. Then, we complete this map through a disparity completion module to obtain a well-initialized disparity map. The state features from the current completion module and from the past refinement are fused together, providing a temporally coherent state for subsequent refinement. Based on this coherent state, we introduce a dual-space refinement module to iteratively refine the initialized result in both disparity and disparity gradient spaces, improving estimations in ill-posed regions. Extensive experiments demonstrate that our method effectively alleviates temporal inconsistency while enhancing both accuracy and efficiency. Currently, our method ranks second on the KITTI 2015 benchmark, while achieving superior efficiency compared to other state-of-the-art methods. The code is available at https://***/jiaxiZeng/Temporally-Consistent-Stereo-Matching. © 2024, CC BY-NC-ND.

关键词： Efficiency

Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Jiajun Lin, Jiacheng Zhong, Guojin Fu, Haolong Nai, Ke Yang, Kailun Li, Zhiyong School of Robotics Hunan University Changsha410082 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410011 China

Audio-guided Video Object Segmentation (A-VOS) and Referring Video Object Segmentation (R-VOS) are two highly related tasks that both aim to segment specific objects from video sequences according to expression prompts. However, due to the challenges of modeling representations for different modalities, existing methods struggle to strike a balance between interaction flexibility and localization precision. In this paper, we address this problem from two perspectives: the alignment of audio and text and the deep interaction among audio, text, and visual modalities. First, we propose a universal architecture, the Expression Prompt Collaboration Transformer, herein EPCFormer. Next, we propose an Expression Alignment (EA) mechanism for audio and text. The proposed EPCFormer exploits the fact that audio and text prompts referring to the same objects are semantically equivalent by using contrastive learning for both types of expressions. Then, to facilitate deep interactions among audio, text, and visual modalities, we introduce an Expression-Visual Attention (EVA) module. The knowledge of video object segmentation in terms of the expression prompts can seamlessly transfer between the two tasks by deeply exploring complementary cues between text and audio. Experiments on well-recognized benchmarks demonstrate that our EPCFormer attains state-of-the-art results on both tasks. The source code will be made publicly available at https://***/lab206/EPCFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Text-Guided Image Generation for Railway Intrusion Anomaly Detection

学校读者我要写书评

暂无评论

Text-Guided Image Generation for Railway Intrusion Anomaly D...

IEEE International Conference on Unmanned Systems (ICUS)

作者： Jinghang Chen Chi Zhang Xiaodan Feng Yuehu Liu Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China

Railway intrusion are characterized by strong suddenness, high unpredictability and many disturbing factors, which are key factors affecting railway safety. Currently, the deep neural network-based intrusion object detection algorithm relies on the diversity of training data. However, the data of railway intrusion image is scarce and difficult to obtain. Existing image generation methods face the problem of insufficient realism in the generated images and difficulty in generating large amounts of data. We aim to explore a text-guided image data generation framework for specific visual tasks by using an existing large language model combined with a text-to-image diffusion model. In this paper, we construct a framework for railway intrusion image generation guided by textual prompts and build a dataset of railway intrusion images based on this framework. The dataset generated in this paper contains a wide range of intrusion images and includes a variety of environmental factors such as weather and time, which provides better diversity than existing datasets. The evaluation results show that the intrusion images generated in this paper have high quality and realism.

关键词：

Financial Forecasting Through Hybrid Algorithms of Machine Learning & Deep Learning 3

学校读者我要写书评

暂无评论

Financial Forecasting Through Hybrid Algorithms of Machine L...

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Raman, Ramakrishnan Kafila Gehlot, Anita Shah, Heli Sanjay, C.P. Ponnusamy, R. Institute of Business Management Maharashtra Pune India SR University School of Business Telangana Warangal India Uttaranchal University Uttaranchal Institute of Technology India Parul University Mechatronics & Robotics PIT India Sri Balaji University Department of IT& Business Analytics SBUP Pune India Chennai Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798350399264

This article serves as a primer where integration of different techniques related to machine learning in the realm of economic prediction, planning, and analysis (FP&A). With its ability to extract insights quickly and automatically from massive datasets, machine learning looks to be a natural fit for supporting FP&*** this article, we highlight the caveats of utilizing classic machine learning approaches for scheduling and data allocation, since most of these methods are designed for forecasting (prediction) (causal inference). Newly designed double machine cognitive approach may answer causal concerns of interest, although naïve use of machine learning often fails in this context. In this paper, we survey the existing literature on the use of machine learning to financial planning and analysis, and we utilize a case study from the field of simulation research to demonstrate the utility of this technique for both decision making and planning. We also look at how better predicting and planning may be achieved with more data sets. © 2023 IEEE.

关键词： Data mining

DeTrack: in-model latent denoising learning for visual object tracking 24

学校读者我要写书评

暂无评论

DeTrack: in-model latent denoising learning for visual objec...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xinyu Zhou Jinglun Li Lingyi Hong Kaixun Jiang Pinxue Guo Weifeng Ge Wenqiang Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China and Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

ISBN: (纸本)9798331314385

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词：

Hi-EF: Benchmarking Emotion Forecasting in Human-interaction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Haoran Mai, Xinji Tao, Zeng Wang, Yan Yu, Jiawen Zhou, Ziheng Tong, Xuan Yan, Shaoqi Zhao, Qing Gao, Shuyong Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Engineering Research Center of Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai China

Affective Forecasting, a research direction in psychology that predicts individuals' future emotions, is often constrained by numerous external factors like social influence and temporal distance. To address this, we transform Affective Forecasting into a Deep Learning problem by designing an Emotion Forecasting paradigm based on two-party interactions. We propose a novel Emotion Forecasting (EF) task grounded in the theory that an individual's emotions are easily influenced by the emotions or other information conveyed during interactions with another person. To tackle this task, we have developed a specialized dataset, Humaninteraction- based Emotion Forecasting (Hi-EF), which contains 3069 two-party Multilayered-Contextual Interaction Samples (MCIS) with abundant affectiverelevant labels and three modalities. Hi-EF not only demonstrates the feasibility of the EF task but also highlights its potential. Additionally, we propose a methodology that establishes a foundational and referential baseline model for the EF task and extensive experiments are provided. The dataset and code is available HERE. Copyright © 2024, The Authors. All rights reserved.

关键词： Prediction models

Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Muchacho, Rafael I Cabral Laha, Riddhiman Pokorny, Florian T. Figueredo, Luis F.C. Chakraborty, Nilanjan Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden Munich Institute of Robotics and Machine Intelligence TUM Germany School of Computer Science University of Nottingham United Kingdom Department of Mechanical Engineering Stony Brook University NY United States

Safety-critical whole-body robot control demands reactive methods that ensure collision avoidance in real-time. Complementarity constraints and control barrier functions (CBF) have emerged as core tools for ensuring such safety constraints, and each represents a well-developed field. Despite addressing similar problems, their connection remains largely unexplored. This paper bridges this gap by formally proving the equivalence between these two methodologies for sampled-data, first-order systems, considering both single and multiple constraint scenarios. By demonstrating this equivalence, we provide a unified perspective on these techniques. This unification has theoretical and practical implications, facilitating the cross-application of robustness guarantees and algorithmic improvements between complementarity and CBF frameworks. We discuss these synergistic benefits and motivate future work in the comparison of the methods in more general cases. Copyright © 2025, The Authors. All rights reserved.

关键词： Optimal control systems

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

学校读者我要写书评

暂无评论

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5520-5537页

作者： Jian Liu Wei Sun Hui Yang Pengchao Deng Chongpei Liu Nicu Sebe Hossein Rahmani Ajmal Mian National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics and the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computing and Communications Lancaster University Lancaster U.K. Department of Computer Science The University of Western Australia Crawley WA Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.

关键词： Shape Solid modeling Three-dimensional displays Pose estimation Training Robots Grasping Diffusion models Real-time systems Point cloud compression