检索结果-内蒙古大学图书馆

Workshops for the 29th International Conference on Case-Based Reasoning, ICCBR-WS 2021

作者： Fröhlich, Moritz Römer, Leon Schriefer, Vanessa Kunold, Tim Gaal, Marcel Reuss, Pascal Althoff, Klaus-Dieter German Research Center for Artificial Intelligence Kaiserslautern Germany Institute of Computer Science Intelligent Information Systems Lab University of Hildesheim Hildesheim Germany

来源：评论

学校读者我要写书评

暂无评论

Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization

Learning Instructions with Unlabeled Data for Zero-Shot Cros...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Gu, Yuxian Ke, Pei Zhu, Xiaoyan Huang, Minlie The CoAI group Tsinghua University Beijing China Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks. However, IT relies on a large amount of human-annotated samples, which restricts its generalization. Unlike labeled data, unlabeled data are often massive and cheap to obtain. In this work, we study how IT can be improved with unlabeled data. We first empirically explore the IT performance trends versus the number of labeled data, instructions, and training tasks. We find it critical to enlarge the number of training instructions, and the instructions can be underutilized due to the scarcity of labeled data. Then, we propose Unlabeled Data Augmented Instruction Tuning (UDIT) to take better advantage of the instructions during IT by constructing pseudo-labeled data from unlabeled plain texts. We conduct extensive experiments to show UDIT's effectiveness in various scenarios of tasks and datasets. We also comprehensively analyze the key factors of UDIT to investigate how to better improve IT with unlabeled data. The code is publicly available at https://***/thu-coai/UDIT. © 2022 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition from an Open-Set Perspective

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Jun Xu, Chi Cheng, Li China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Vision and Learning Laboratory Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

Existing hand gesture recognition methods predominantly rely on a close-set assumption, which in essence limits the viewpoints, gesture categories, and hand shapes at test time to closely resemble those seen during training. This requirement is however rarely met in practice, as images are often captured from unconstrained viewpoints, with novel gestures and unseen hand shapes that can differ significantly from the training data. This motivates us to investigate an open-set hand gesture recognition problem, where hand gestures are still recognizable from unconstrained viewpoints, and novel gesture classes and hand shapes can be incrementally learned with just a few examples. To address this, we propose a viewpoint influence elimination network that extracts view-independent features, significantly improving performance in scenarios with unconstrained viewpoints. Moreover, a joint-weighted classification scheme is introduced to augment the cosine similarity metric for evaluating few-shot incremental learning of novel gestures and shapes. Finally, as existing hand gesture recognition datasets primarily adhere to the close-set assumption, a new hand gesture recognition dataset, OHG, is introduced in this paper, that includes a wide range of viewpoints, diverse gesture classes, and distinct hand shapes. Experimental hand gesture recognition results demonstrate the superior performance of our approach in both unconstrained viewpoint and few-shot incremental learning scenarios. The source code and the OHG dataset are to be made available at https://***/zhoujun-7/OSHGR. © 1999-2012 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

M2F2-Net: Multi-Modal Feature Fusion for Unstructured Off-Road Freespace Detection

M2F2-Net: Multi-Modal Feature Fusion for Unstructured Off-Ro...

引用

IEEE Symposium on intelligent Vehicle

作者： Hongliang Ye Jilin Mei Yu Hu The Research Center for Advanced Computing Systems Zhejiang Lab Hangzhou China The Research Center for Intelligent Computing Systems Institute of Computing Technology Beijing China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Freespace detection is an important part of autonomous driving technology. Compared with structured on-road scenes, unstructured off-road scenes face more challenges. Multi-modal fusion method is a viable solution to these challenges. But existing fusion methods do not fully utilize the multi-modal features. In this paper, we propose an effective multi-modal network named M2F2-Net for freespace detection in unstructured off-road scenes. We propose a multi-modal feature fusion strategy named Multi-modal Cross Fusion (MCF). MCF module is simple but effective in fusing the features of RGB images and surface normal maps. Meanwhile, a multi-modal segmentation decoder module is designed to decouple the segmentation of two modalities, and it further helps the features of both modalities to be fully utilized. In order to solve the problem that the road edge is difficult to extract in the unstructured scenes, we also propose an edge segmentation decoder module. Extensive experiments show that our approach can lead to significant improvements, which brings 6.1% F1 and 10.8% IoU improvements. Our code will be available at https://***/yhl1010/M2F2-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

Root Pose Decomposition Towards Generic Non-rigid 3D Reconst...

引用

International Conference on computer vision (ICCV)

作者： Yikai Wang Yinpeng Dong Fuchun Sun Xiao Yang Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology (BNRist) State Key Lab on Intelligent Technology and Systems Tsinghua University RealAI

This work focuses on the 3D reconstruction of non-rigid objects based on monocular RGB video sequences. Concretely, we aim at building high-fidelity models for generic object categories and casually captured scenes. To this end, we do not assume known root poses of objects, and do not utilize category-specific templates or dense pose priors. The key idea of our method, Root Pose Decomposition (RPD), is to maintain a per-frame root pose transformation, meanwhile building a dense field with local transformations to rectify the root pose. The optimization of local transformations is performed by point registration to the canonical space. We also adapt RPD to multi-object scenarios with object occlusions and individual differences. As a result, RPD allows non-rigid 3D reconstruction for complicated scenarios containing objects with large deformations, complex motion patterns, occlusions, and scale diversities of different individuals. Such a pipeline potentially scales to diverse sets of objects in the wild. We experimentally show that RPD surpasses state-of-the-art methods on the challenging DAVIS, OVIS, and AMA datasets. We provide video results in https://***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SLC2-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM

arXiv

引用

arXiv 2025年

作者： Ming, Yuhang Ma, Di Dai, Weichen Yang, Han Fan, Rui Zhang, Guofeng Kong, Wanzeng School of Computer Science Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou Dianzi University Hangzhou310018 China College of Electronics & Information Engineering Shanghai Institute of Intelligent Science and Technology Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China

Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC2-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as they are only used for better reconstruction. In this paper, we propose a simple yet effective way to detect potential loops using the same latent codes as local features. To further improve the loop detection performance, we use the semantic information, which are also decoded from the same latent codes to guide the aggregation of local features. Finally, with the potential loops detected, we close them with a graph optimization followed by bundle adjustment to refine both the estimated poses and the reconstructed scene. To evaluate the performance of our SLC2-SLAM, we conduct extensive experiments on Replica and ScanNet datasets. Our proposed semantic-guided loop closure significantly outperforms the pre-trained NetVLAD and ORB combined with Bag-of-Words, which are used in all the other NeRF SLAM with loop closure. As a result, our SLC2-SLAM also demonstrated better tracking and reconstruction performance, especially in larger scenes with more loops, like ScanNet. Copyright © 2025, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Development of Support Equipment for SATCOM Avionics

Development of Support Equipment for SATCOM Avionics

引用

International Automatic Testing Conference, AUTOTESTCON

作者： Christopher Guerra Miles Darnell Larry McDaniel Martin Wasiewicz Patrick Saenz Josh Anderson Space Science and Engineering Southwest Research Institute San Antonio USA Intelligent Systems Southwest Research Institute San Antonio USA Computer Vision Kitware San Antonio USA

ISBN: (数字)9781728154008

ISBN: (纸本)9781728154015

Demand for satellite communication (SATCOM) infrastructure has led to the development of a geosynchronous spacecraft to enable communications between ground and mobile terminals for video data. When fully loaded, the ground support equipment (GSE) provides handling for payload data of 1.2 Gbps distributed across more than 100 continuous carrier terminals or 1000 time division multiple access (TDMA) terminals. This paper assesses the implementation of GSE to verify the hardware design of this multi-radio, multi-terminal avionics unit. The GSE contains a unique design based around a communications slice, each of which provides one of four L-band interfaces to the unit under test (UUT) for both transmit and receive data. The GSE uses a channel emulator to impose impairments on the radio frequency (RF) signals to include noise, propagation delay, and dynamic frequency offset. For adjacent channel loading, the GSE contains an arbitrary waveform generator (A WG) that can implement simulated terminals in a composite waveform. This function complements the slices that contain servers connected to software defined radios (SDRs). The GSE employs an Ethernet backbone for subsystem control and to move the payload data to and from the SDRs and to the A WG. Test software in the test controller implements ETSI Digital Video Broadcast (DVB) standards for the baseband and high layer data. The test software is based around a Ground Support Equipment Operating System (GSEOS) environment, which provides test logging and automation for a traceable, repeatable environmental test campaign. The test software maintains compatibility with an embedded test software (ETS) on the UUT, which provides customized interfaces for moving higher rate data to and from the UUT.

关键词： Radio frequency Time division multiple access Runtime Loading Aerospace electronics Software Ground support

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Symbolic Regression in Precision Livestock Farming 11

Exploring the Potential of Symbolic Regression in Precision ...

引用

11th European Conference on Precision Livestock Farming

作者： Mayrhuber, E. Oczak, M. Iwersen, M. Brunner, D. Dorfer, V. Winkler, S.M. Bioinformatics Research Group PLFDoc University of Applied Sciences Upper Austria Hagenberg Austria Computer Vision Lab TU Wien Vienna Austria Precision Livestock Farming Hub The University of Veterinary Medicine Vienna Vienna Austria Center for Animal Nutrition and Welfare The University of Veterinary Medicine Vienna Vienna Austria Center for Veterinary Systems Transformation and Sustainability Clinical Unit for Herd Health Management The University of Veterinary Medicine Vienna Vienna Austria

ISBN: (纸本)9791221067361

The ability to predict farrowing time in pigs is crucial for optimal farm management and ensuring piglet survival. This study investigates the potential of explainable artificial intelligence for precision livestock farming, focusing on acceleration sensor data from sows around the time of farrowing. Accurately predicting farrowing allows farmers to balance both, piglet safety by avoiding piglet crushing events and the mother sow's welfare, by avoiding early crating. Traditional machine learning models often lack interpretability ("closed-box" problem). Explainable artificial intelligence offers a solution by revealing the decision-making processes within the models. This work is split into two stages. First the detection of nest building behaviour and second the prediction of the remaining time to farrowing. The nest building detection was possible for 166 out of 180 sows and successful within 48 hours before farrowing for 149 sows. The nest building detection is purely based on the change of a sow's activity level and uses no machine learning techniques. Further, this study utilizes symbolic regression, an open-box modelling technique that generates interpretable mathematical formulas, to predict the remaining time until the onset of farrowing. The results are compared with closed-box models, like support vector regression and artificial neural networks, for both explainability and performance. Notably, symbolic regression achieved a mean absolute error of 9.28 hours for the time-to-farrowing prediction, outperforming the closed-box models in terms of performance and interpretability. This research demonstrates that explainable artificial intelligence, specifically symbolic regression, can offer both interpretable results and competitive performance in precision livestock farming. © 2024 11th European Conference on Precision Livestock Farming. All rights reserved.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Two Novel Methods for Multiple Kinect v2 Sensor Calibration 6th

Two Novel Methods for Multiple Kinect v2 Sensor Calibration

引用

6th International Conference on computer vision and Image Processing, CVIP 2021

作者： Hazra, Sumit Pisipati, Manasa Puhan, Amrit Nandy, Anup Scherer, Rafal Machine Intelligence and Bio-Motion Research Lab Department of Computer Science and Engineering NIT Rourkela Odisha Rourkela769008 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad500075 India Department of Intelligent Computer Systems Czestochowa University of Technology al. Armii Krajowej 36 Czestochowa42-200 Poland

ISBN: (纸本)9783031113482

Camera calibration is an essential step for measuring an instrument’s accuracy by using its parameters. In this paper, we propose two methods for calibrating eight Kinect v2.0 sensors, namely, pairwise and simultaneous single-camera calibration. In the first method, an experimental setup is managed so that the eight Kinect cameras can view a 3D object on a treadmill in consecutive pairs. The novelty of this method infers pairwise calibration of eight Kinects using six steps, specifically: precalibration process, acquiring images from Kinect, exporting the parameters, generation of independent live point clouds, feeding exported parameters for point cloud matching and ensuring successful calibration through merged point clouds. In the second method, a novel octagonal model is developed to calibrate each of the eight cameras on the same experimental setup. We obtain an overall mean reprojection error of 1.37 pixels and 0.42 pixels for the first method and second method, respectively. The smallest reprojection error for the first method is reported to be 0.63 pixels and 0.27 pixels for the second method. The efficiency of the proposed methods is compared with the state-of-art techniques using the root mean square and the reprojection error metrics. We observed that the proposed methods outperform the existing techniques. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Grasp Diffusion Network: Learning Grasp Generators from Partial Point Clouds with Diffusion Models in SO(3) × R3

arXiv

引用

arXiv 2024年

作者： Carvalho, Joao Le, An T. Jahr, Philipp Sun, Qiao Urain, Julen Koert, Dorothea Peters, Jan Intelligent Autonomous Systems Lab Computer Science Department Technical University of Darmstadt Germany Centre for Cognitive Science Technical University of Darmstadt Germany Research Department: SAIROL Darmstadt Germany Hessian.AI Darmstadt Germany

Grasping objects successfully from a single-view camera is crucial in many robot manipulation tasks. An approach to solve this problem is to leverage simulation to create large datasets of pairs of objects and grasp poses, and then learn a conditional generative model that can be prompted quickly during deployment. However, the grasp pose data is highly multimodal since there are several ways to grasp an object. Hence, in this work, we learn a grasp generative model with diffusion models to sample candidate grasp poses given a partial point cloud of an object. A novel aspect of our method is to consider diffusion in the manifold space of rotations and to propose a collision-avoidance cost guidance to improve the grasp success rate during inference. To accelerate grasp sampling we use recent techniques from the diffusion literature to achieve faster inference times. We show in simulation and real-world experiments that our approach can grasp several objects from raw depth images with 90% success rate and benchmark it against several baselines. https://***/view/graspdiffusionnetwork Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

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：