检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Tian, Chunwei Xu, Yong Zuo, Wangmeng Lin, Chia-Wen Zhang, David The Bio-Computing Research Center Harbin Institute of Technology ShenzhenShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition ShenzhenGuangdong518055 China The School of Computer Science and Technology Harbin Institute of Technology HarbinHeilongjiang150001 China The Peng Cheng Laboratory ShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen Guangdong518055 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan ShenzhenGuangdong518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of given application, which ignores the effects of local power pixel points and results in low training efficiency. In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. The AB utilizes one-dimensional asymmetric convolutions to intensify the square convolution kernels in horizontal and vertical directions for promoting the influences of local salient features for SISR. The MEB fuses all hierarchical low-frequency features from the AB via residual learning (RL) technique to resolve the long-term dependency problem and transforms obtained low-frequency features into high-frequency features. The HFFEB exploits low- and high-frequency features to obtain more robust super-resolution features and address excessive feature enhancement problem. Additionally, it also takes charge of reconstructing a high-resolution (HR) image. Extensive experiments show that our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems. The code of the ACNet is shown at https://***/hellloxiaotian/ACNet. © 2021, CC BY-NC-ND.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Acknowledging the Unknown for Multi-label Learning with Single Positive Labels

arXiv

引用

arXiv 2022年

作者： Zhou, Donghao Chen, Pengfei Wang, Qiong Chen, Guangyong Heng, Pheng-Ann Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China Tencent Technology Shenzhen China Zhejiang Lab Hangzhou China The Chinese University of Hong Kong Hong Kong

Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are assumed as negative labels in SPML, which introduces false negative labels and causes model training to be dominated by assumed negative labels. In this work, we choose to treat all unannotated labels from an alternative perspective, i.e. acknowledging they are unknown. Hence, we propose entropy-maximization (EM) loss to attain a special gradient regime for providing proper supervision signals. Moreover, we propose asymmetric pseudo-labeling (APL), which adopts asymmetric-tolerance strategies and a self-paced procedure, to cooperate with EM loss and then provide more precise supervision. Experiments show that our method significantly improves performance and achieves state-of-the-art results on all four benchmarks. Code is available at https://***/CorrerZhou/SPML-AckTheUnknown. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning

Skeleton-in-Context: Unified Skeleton Sequence Modeling with...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Xinshun Wang Zhongbin Fang Xia Li Xiangtai Li Chen Chen Mengyuan Liu Sun Yat-sen University National Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Department of Computer Science ETH Zurich S-Lab Nanyang Technological University Center for Research in Computer Vision University of Central Florida

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In-context learning provides a new perspective for multi-task modeling for vision and NLP. Under this setting, the model can perceive tasks from prompts and accomplish them without any extra task-specific head predictions or model fine-tuning. However, skeleton sequence modeling via in-context learning remains unexplored. Directly applying existing in-context models from other areas onto skeleton sequences fails due to the similarity between inter-frame and cross-task poses, which makes it exceptionally hard to perceive the task correctly from a subtle context. To address this challenge, we propose Skeleton-in-Context (SiC), an effective framework for in-context skeleton sequence modeling. Our SiC is able to handle multiple skeleton-based tasks simultaneously after a single training process and accomplish each task from context according to the given prompt. It can further generalize to new, unseen tasks according to customized prompts. To facilitate context perception, we additionally propose a task-unified prompt, which adaptively learns tasks of different natures, such as partial joint-level generation, sequence-level prediction, or 2D-to-3D motion prediction. We conduct extensive experiments to evaluate the effectiveness of our SiC on multiple tasks, including motion prediction, pose estimation, joint completion, and future pose estimation. We also evaluate its generalization capability on unseen tasks such as motion-in-between. These experiments show that our model achieves state-of-the-art multi-task performance and even outperforms single-task methods on certain tasks.

关键词： Training Solid modeling Three-dimensional displays Silicon carbide Computational modeling Pose estimation Predictive models

来源：评论

学校读者我要写书评

暂无评论

Object-oriented Map Exploration and Construction Based on Auxiliary Task Aided DRL

Object-oriented Map Exploration and Construction Based on Au...

引用

International Conference on Pattern Recognition

作者： Junzhe Xu Jianhua Zhang Shengyong Chen Honghai Liu College of Computer Science and Technology Zhejiang University of Technology Hangzhou China College of Computer Science and Technology Tianjin University of Technology Tianjin China State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China

Environment exploration by autonomous robots through deep reinforcement learning (DRL) based methods has attracted more and more attention. However, existing methods usually focus on robot navigation to single or multiple fixed goals, while ignoring the perception and construction of external environments. In this paper, we propose a novel environment exploration task based on DRL, which requires a robot fast and completely perceives all objects of interest, and reconstructs their poses in a global environment map, as much as the robot can do. To this end, we design an auxiliary task aided DRL model, which is integrated with the auxiliary object detection and 6-DoF pose estimation components. The outcome of auxiliary tasks can improve the learning speed and robustness of DRL, as well as the accuracy of object pose estimation. Comprehensive experimental results on the indoor simulation platform AI2-THOR have shown the effectiveness and robustness of our method.

关键词： Navigation Object oriented modeling Pose estimation Semantics Object detection Reinforcement learning Robustness

来源：评论

学校读者我要写书评

暂无评论

Segment-Based Trajectory Prediction and Risk Assessment for RSU-assisted CAVs at Signalized Intersections

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-19页

作者： Cao, Yue Shangguan, Wei Visser, Arnoud Chen, Junjie Chai, Linguo Cai, Baigen School of Automation and Intelligence Beijing Jiaotong University Beijing China School of Automation and Intelligence and State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Intelligent Robotics and Computer Vision Lab of the Informatics Institute Faculty of Science University of Amsterdam The Netherlands

Detecting surrounding situations and reacting accordingly to avoid collisions remains a challenging task for autonomous driving. This task requires predicting the trajectories of surrounding agents and assessing the potential risk of future situations, which can be difficult to achieve solely through onboard vehicle devices. Therefore, this paper proposes a cooperative architecture for trajectory prediction and risk assessment conducted on roadside devices (RSUs) to assist Connected and Autonomous Vehicles (CAVs). Firstly, we develop a segmentbased prediction model (SegNet) tailored to hub signalized intersections. Intersections are divided into multiple segments, and the Curvilinear coordinates are utilized to indicate the geometric road features. The model leverages individual interaction cues in the ego segment and group features in the merging segments, while also incorporating traffic signal information to generate multimodal prediction results. In terms of risk assessment, we utilize the prediction results to provide hierarchical assistance, such as risk values, risk maps, and reference trajectories. Offline experimental results demonstrate that our SegNet model achieves competitive and well-balanced performance compared to stateof-the-art methods on the CitySim Database, with more accurate and smooth prediction trajectories. Through real-time CARLA and SUMO co-simulation, the performance of assisted CAVs indicates that they can safely and effectively navigate with the support of the proposed architecture. IEEE

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement

arXiv

引用

arXiv 2024年

作者： Shi, Haojie Li, Tingguang Zhu, Qingxu Sheng, Jiapeng Han, Lei Meng, Max Q.-H. Tencent Robotics X China The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Department of Electrical and Computer Engineering The University of Alberta Canada

Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an efficient model-based learning framework that combines a world model with a policy network. We train a differentiable world model to predict future states and use it to directly supervise a Variational Autoencoder (VAE)-based policy network to imitate real animal behaviors. This significantly reduces the need for real interaction data and allows for rapid policy updates. We also develop a high-level network to track diverse commands and trajectories. Our simulated results show a tenfold sample efficiency increase compared to reinforcement learning methods such as PPO. In real-world testing, our policy achieves proficient command-following performance with only a two-minute data collection period and generalizes well to new speeds and paths. Copyright © 2024, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

ORF-Net: Deep Omni-supervised Rib Fracture Detection from Chest CT Scans

arXiv

引用

arXiv 2022年

作者： Chai, Zhizhong Lin, Huangjing Luo, Luyang Heng, Pheng-Ann Chen, Hao Imsight AI Research Lab Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong

Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies have proposed weakly-supervised methods or semi-supervised methods, they could not handle different forms of supervision simultaneously. In this paper, we proposed a novel omni-supervised object detection network, which can exploit multiple different forms of annotated data to further improve the detection performance. Specifically, the proposed network contains an omni-supervised detection head, in which each form of annotation data corresponds to a unique classification branch. Furthermore, we proposed a dynamic label assignment strategy for different annotated forms of data to facilitate better learning for each branch. Moreover, we also design a confidence-aware classification loss to emphasize the samples with high confidence and further improve the model’s performance. Extensive experiments conducted on the testing dataset show our proposed method outperforms other state-of-the-art approaches consistently, demonstrating the efficacy of deep omni-supervised learning on improving rib fracture detection performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Dual-Teacher++: Exploiting intra-domain and Inter-domain knowledge with reliable transfer for cardiac segmentation

arXiv

引用

arXiv 2021年

作者： Li, Kang Wang, Shujun Yu, Lequan Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China The Department of Radiation Oncology Stanford University Palo AltoCA94306 United States

Annotation scarcity is a long-standing problem in medical image analysis area. To efficiently leverage limited annotations, abundant unlabeled data are additionally exploited in semi-supervised learning, while well-established cross-modality data are investigated in domain adaptation. In this paper, we aim to explore the feasibility of concurrently leveraging both unlabeled data and cross-modality data for annotation-efficient cardiac segmentation. To this end, we propose a cutting-edge semisupervised domain adaptation framework, namely Dual-Teacher++. Besides directly learning from limited labeled target domain data (e.g., CT) via a student model adopted by previous literature, we design novel dual teacher models, including an inter-domain teacher model to explore cross-modality priors from source domain (e.g., MR) and an intra-domain teacher model to investigate the knowledge beneath unlabeled target domain. In this way, the dual teacher models would transfer acquired inter- and intra-domain knowledge to the student model for further integration and exploitation. Moreover, to encourage reliable dual-domain knowledge transfer, we enhance the inter-domain knowledge transfer on the samples with higher similarity to target domain after appearance alignment, and also strengthen intra-domain knowledge transfer of unlabeled target data with higher prediction confidence. In this way, the student model can obtain reliable dual-domain knowledge and yield improved performance on target domain data. We extensively evaluated the feasibility of our method on the MM-WHS 2017 challenge dataset. The experiments have demonstrated the superiority of our framework over other semi-supervised learning and domain adaptation methods. Moreover, our performance gains could be yielded in bidirections, i.e., adapting from MR to CT, and from CT to MR. Our code will be available at https://***/kli-lalala/Dual-Teacher-. © 2021, CC0.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Line Drawing Guided Progressive Inpainting of Mural Damage

arXiv

引用

arXiv 2022年

作者： Li, Luxi Zou, Qin Zhang, Fan Yu, Hongkai Chen, Long Song, Chengfang Huang, Xianfeng Wang, Xiaoguang Li, Qingquan Department of Computer Science Technology United International College of Beijing Normal University HongKong Baptist University Zhuhai China Machine Vision and Robotics Laboratory School of Computer Science Wuhan University Wuhan China State Key Laboratory of Surveying Mapping and Remote Sensing Information Engineering Wuhan University Wuhan China Department of Electrical Engineering and Computer Science Cleveland State University OH United States Institute of Automation Chinese Academy of Sciences Beijing China Cultural Heritage Intelligent Computing Laboratory Wuhan University Wuhan China Guangming Laboratory Shenzhen University Shenzhen China

Mural image inpainting is far less explored compared to its natural image counterpart and remains largely unsolved. Most existing image-inpainting methods tend to take the target image as the only input and directly repair the damage to generate a visually plausible result. These methods obtain high performance in restoration or completion of some pre-defined objects, e.g., human face, fabric texture, and printed texts, etc., however, are not suitable for repairing murals with varying subjects and large damaged areas. Moreover, due to discrete colors in paints, mural inpainting may suffer from apparent color bias. To this end, in this paper, we propose a line drawing guided progressive mural inpainting method. It divides the inpainting process into two steps: structure reconstruction and color correction, implemented by a structure reconstruction network (SRN) and a color correction network (CCN), respectively. In structure reconstruction, SRN utilizes the line drawing as an assistant to achieve large-scale content authenticity and structural stability. In color correction, CCN operates a local color adjustment for missing pixels which reduces the negative effects of color bias and edge jumping. The proposed approach is evaluated against the current state-of-the-art image inpainting methods. Qualitative and quantitative results demonstrate the superiority of the proposed method in mural image inpainting. The codes and data are available at https://***/qinnzou/mural-image-inpainting . © 2022, CC BY-NC-ND.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation

HTML: Hybrid Temporal-scale Multimodal Learning Framework fo...

引用

International Conference on computer vision (ICCV)

作者： Mingfei Han Yali Wang Zhihui Li Lina Yao Xiaojun Chang Yu Qiao ReLER AAII UTS Data61 CSIRO Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shanghai AI Laboratory Shanghai China Shandong Artificial Intelligence Qilu University of Technology Department of Computer Vision Mohamed bin Zayed University of Artificial Intelligence

Referring Video Object Segmentation (RVOS) is to segment the object instance from a given video, according to the textual description of this object. However, in the open world, the object descriptions are often diversified in contents and flexible in lengths. This leads to the key difficulty in RVOS, i.e., various descriptions of different objects are corresponding to different temporal scales in the video, which is ignored by most existing approaches with single stride of frame sampling. To tackle this problem, we propose a concise Hybrid Temporal-scale Multimodal Learning (HTML) framework, which can effectively align lingual and visual features to discover core object semantics in the video, by learning multimodal interaction hierarchically from different temporal scales. More specifically, we introduce a novel inter-scale multimodal perception module, where the language queries dynamically interact with visual features across temporal scales. It can effectively reduce complex object confusion by passing video context among different scales. Finally, we conduct extensive experiments on the widely used benchmarks, including Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences, where our HTML achieves state-of-the-art performance on all these datasets.

关键词：

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：