检索结果-内蒙古大学图书馆

Task-Oriented 6-DoF Grasp Pose Detection in Clutters

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, An-Lan Chen, Nuo Lin, Kun-Yu Li, Yuan-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In general, humans would grasp an object differently for different tasks, e.g., "grasping the handle of a knife to cut" vs. "grasping the blade to hand over". In the field of robotic grasp pose detection research, some existing works consider this task-oriented grasping and made some progress, but they are generally constrained by low-DoF gripper type or non-cluttered setting, which is not applicable for human assistance in real life. With an aim to get more general and practical grasp models, in this paper, we investigate the problem named Task-Oriented 6-DoF Grasp Pose Detection in Clutters (TO6DGC), which extends the task-oriented problem to a more general 6-DOF Grasp Pose Detection in Cluttered (multi-object) scenario. To this end, we construct a large-scale 6-DoF task-oriented grasping dataset, 6-DoF Task Grasp (6DTG), which features 4391 cluttered scenes with over 2 million 6-DoF grasp poses. Each grasp is annotated with a specific task, involving 6 tasks and 198 objects in total. Moreover, we propose One-Stage TaskGrasp (OSTG), a strong baseline to address the TO6DGC problem. Our OSTG adopts a task-oriented point selection strategy to detect where to grasp, and a task-oriented grasp generation module to decide how to grasp given a specific task. To evaluate the effectiveness of OSTG, extensive experiments are conducted on 6DTG. The results show that our method outperforms various baselines on multiple metrics. Real robot experiments also verify that our OSTG has a better perception of the task-oriented grasp points and 6-DoF grasp poses. © 2025, CC BY.

关键词： Clutter (information theory)

Panorama Generation From NFoV Image Done Right

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Dian Zhang, Cheng Wu, Xiao-Ming Li, Cao Lv, Chengfei Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University China Monash University Australia Alibaba Group China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the generated panoramas with InceptionNet or CLIP based metrics, which tend to perceive the image quality and is not suitable for evaluating the distortion. In this work, we first propose a distortion-specific CLIP, named Distort-CLIP to accurately evaluate the panorama distortion and discover the "visual cheating" phenomenon in previous works (i.e., tending to improve the visual results by sacrificing distortion accuracy). This phenomenon arises because prior methods employ a single network to learn the distinct panorama distortion and content completion at once, which leads the model to prioritize optimizing the latter. To address the phenomenon, we propose PanoDecouple, a decoupled diffusion model framework, which decouples the panorama generation into distortion guidance and content completion, aiming to generate panoramas with both accurate distortion and visual appeal. Specifically, we design a DistortNet for distortion guidance by imposing panorama-specific distortion prior and a modified condition registration mechanism;and a ContentNet for content completion by imposing perspective image information. Additionally, a distortion correction loss function with Distort-CLIP is introduced to constrain the distortion explicitly. The extensive experiments validate that PanoDecouple surpasses existing methods both in distortion and visual metrics. Copyright © 2025, The Authors. All rights reserved.

关键词： Virtual reality

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

iManip: Skill-Incremental Learning for Robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Zexin Cai, Jia-Feng Wu, Xiao-Ming Wei, Yi-Lin Tang, Yu-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the previous methods on classification overlooking the characteristics of temporality and action complexity in robotic manipulation tasks. Towards this end, we propose an incremental Manipulation framework, termed iManip, to mitigate the above issues. We firstly design a temporal replay strategy to maintain the integrity of old skills when learning new skill. Moreover, we propose the extendable PerceiverIO, consisting of an action prompt with extendable weight to adapt to new action primitives in new skill. Extensive experiments show that our framework performs well in Skill-Incremental Learning. Codes of the skill-incremental environment with our framework will be open-source. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot learning

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gu, Shengbo Qiu, Yu-Kun Tang, Yu-Ming Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model. © 2025, CC BY.

关键词： Federated learning

Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年

作者： Meng, Jingke Tian, Huilin Lin, Ge Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Peng Cheng Laboratory Shenzhen518005 China Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Ministry of Education China

Weakly supervised anomaly detection is to identify the time window when an anomaly event happened based on the video-level label indicating whether the video contains anomaly event or not. Recent efforts have focused on leveraging multi-modal data, specifically combining visual and audio information, to enhance detection accuracy. While some studies have explored intra-video separation techniques, the primary emphasis remains on distinguishing potentially anomalous events scoring highest from those scoring lowest as normal events. Nevertheless, challenges persist in delineating boundaries between normal and abnormal events, particularly when visual differences are subtle. Our proposed framework, called Audio-Visual Collaborative Learning (AVCL), addresses the challenge of ambiguity in weakly supervised anomaly detection. Our core idea centers around utilizing both audio track variations and the perceptual robustness of visual information to detect and differentiate challenging cases, which composed of two essential modules: the Audio-Visual collaborative Hard cases Separation (AVHS) module and the Multi-modal Mutual Learning (MML) module. The AVHS module aims to address the challenge of discerning visually ambiguous clips in anomaly videos, differentiating between normal and abnormal events. To further improve detection accuracy, we introduce the Multi-modal Mutual Learning (MML) module, and this module enables a process of mutual learning to facilitate the exchange of knowledge and expertise between the single-modal branch and the multi-modal branch. We demonstrate that the proposed approach achieves state-of-the-art detection performance on benchmarks of XD-Violence and CCTV-Fightssub datasets. © 1999-2012 IEEE.

关键词： Self-supervised learning

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xiao, Junjin Zhang, Qing Nie, Yonewei Zhu, Lei Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China South China University of Technology China China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject optimization. Unlike previous methods that typically struggle with sparse views with few overlappings and are less effective in reconstructing complex human geometry, the proposed method enables robust reconstruction in such challenging conditions. Our key idea is to lift SMPL vertices to dense and reliable 3D prior points representing accurate human body geometry, and then regress human Gaussian parameters based on the points. To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians. To enhance the ability to capture high-frequency details, we further render depth maps from the coarse 3D Gaussians to help regress fine-grained pixel-wise Gaussians. Experiments on several benchmark datasets demonstrate that our method outperforms state-of-the-art methods in novel view synthesis and cross-dataset generalization. Our code is available at https: //***/iSEE-laboratory/RoGSplat. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

Complete Gait Phases Recognition Based on Muscle Synergy Using PSO-CNN-LSTM Algorithm

学校读者我要写书评

暂无评论

IEEE Sensors Journal 2025年第10期25卷 16775-16786页

作者： Zhang, Kewen Li, Xiaoling Chen, Xin Yu, Longjie Jin, Yinan Fan, Bingfei Du, Mingyu Bao, Guanjun Wu, Xinyu Cai, Shibo Zhejiang University of Technology College of Mechanical Engineering Key Laboratory of Special Purpose Equipment and Advanced Processing Technology Ministry of Education Hangzhou China Zhejiang University of Technology College of Mechanical Engineering Hangzhou China ZJUT Yinhu Research Institute of Innovation and Entrepreneurship ZJUT Yinhu Research Institute of Innovation and Entrepreneurship ZJUT Yinhu Research Institute of Innovation and Entrepreneurship Fuyang District Hangzhou311400 China Chinese Academy of Sciences Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen China Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Shenzhen China

Accurately recognizing gait phases, by applying proper instrumentation and measurement, is significant in walking rehabilitation training for patients with impaired mobility. In this study, seven phases of complete stand-walk-stand cycle as well as continuous daily walking were recognized based on muscle synergy and PSO-CNN-LSTM model. Firstly, the complete stand-walk-stand walking cycle were divided into starting phase, terminal swing phase, loading response phase, mid-stance phase, terminal stance phase, initial swing phase, and stopping phase, based on the features of surface electromyography (sEMG) collected by portable sEMG acquisition system and measured motion data of lower limb. Secondly, a muscle weight matrix and an activation sequence matrix were calculated by using non-negative matrix factorization (NMF). Finally, a PSO-CNN-LSTM network was designed to recognize the complete stand-walk-stand cycle by applying above mentioned matrices as input. Fourteen subjects volunteered to perform linear walking experiments under procedure to verify the feasibility of the proposed approach by comparing results with other classifiers and features. Experimental results show that the proposed approach was capable of achieving an average recognition accuracy of up to 85.384%. This work will offer promising gait recognition method for rehabilitation robots to achieve natural and flexible human-robot interaction. © 2001-2012 IEEE.

关键词： Non-negative matrix factorization

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

关键词：