检索结果-内蒙古大学图书馆

Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Jingwei Xue, Bohuan Feng, Yi Wang, Deming Fan, Rui Chen, Qijun The College of Electronics & Information Engineering 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 The Department of Computer Science & Engineering The Hong Kong University of Science and Technology Hong Kong SAR Hong Kong

This article introduces three-filters-to-normal+ (3F2N+), an extension of our previous work three-filters-to-normal (3F2N), with a specific focus on incorporating discontinuity discrimination capability into surface normal estimators (SNEs). 3F2N+ achieves this capability by utilizing a novel discontinuity discrimination module (DDM), which combines depth curvature minimization and correlation coefficient maximization through conditional random fields (CRFs). To evaluate the robustness of SNEs on noisy data, we create a large-scale synthetic surface normal (SSN) dataset containing 20 scenarios (ten indoor scenarios and ten outdoor scenarios with and without random Gaussian noise added to depth images). Extensive experiments demonstrate that 3F2N+ achieves greater performance than all other geometry-based surface normal estimators, with average angular errors of 7.85◦, 8.95◦, 9.25◦, and 11.98◦ on the clean-indoor, clean-outdoor, noisy-indoor, and noisy-outdoor datasets, respectively. We conduct three additional experiments to demonstrate the effectiveness of incorporating our proposed 3F2N+ into downstream robot perception tasks, including freespace detection, 6D object pose estimation, and point cloud completion. Our source code and datasets are publicly available at https://***/3F2Nplus. Note to Practitioners—The primary motivation behind this work arises from the need to develop a high-performing surface normal estimator for practical robotics and computer vision applications. While geometry-based surface normal estimators have been widely used in these domains, the existing solutions focus merely on discontinuity discrimination. To tackle this problem, this article introduces a plug-and-play module that leverages both depth curvature and correlation coefficient to quantify discontinuity levels, thereby optimizing surface normal estimation, particularly near or on discontinuous regions. Moreover, this article also introduces a large-scale public dataset wit

关键词： Gaussian noise (electronic)

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gong, Haisong Xu, Weizhi Wu, Shu Liu, Qiang Wang, Liang Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China ByteDance Inc

Fact checking aims to predict claim veracity by reasoning over multiple evidence pieces. It usually involves evidence retrieval and veracity reasoning. In this paper, we focus on the latter, reasoning over unstructured text and structured table information. Previous works have primarily relied on fine-tuning pretrained language models or training homogeneous-graph-based models. Despite their effectiveness, we argue that they fail to explore the rich semantic information underlying the evidence with different structures. To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC. Our approach leverages a heterogeneous evidence graph, with words as nodes and thoughtfully designed edges representing different evidence properties. We perform information propagation via a relational graph neural network, facilitating interactions between claims and evidence. An attention-based method is utilized to integrate information, combined with a language model for generating predictions. We introduce a multitask loss function to account for potential inaccuracies in evidence retrieval. Comprehensive experiments on the large fact checking dataset FEVEROUS demonstrate the effectiveness of HeterFC. Code will be released at: https://***/Deno-V/HeterFC. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Joint product numerical range and geometry of reduced density matrices

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2017年第2期60卷 9-17页

作者： Jianxin Chen Cheng Guo Zhengfeng Ji Yiu-Tung Poon Nengkun YU Bei Zeng Jie Zhou Joint Center for Quantum Information and Computer Science University of Maryland College Park 20740 USA Institute for Advanced Study Tsinghua University Beijing 100084 China Centre for Quantum Computation ＆ Intelligent Systems School of Software Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia State Key Laboratory of Computer Science.Institute of Software Chinese Academy of Sciences Beijing 100084 China Department of Mathematics Iowa State University Ames 50011-2140 USA Institute for Quantum Computing University of Waterloo Waterloo N2L 3G1 Canada Department of Mathematics ＆ Statistics University of Guelph Guelph N1G 2 W1 Canada Perimeter Institute for Theoretical Physics Waterloo N2L 2Y5 Canada

The reduced density matrices of a many-body quantum system form a convex set, whose three-dimensional projection is convex in R3. The boundary of may exhibit nontrivial geometry, in particular ruled surfaces. Two physical mechanisms are known for the origins of ruled surfaces： symmetry breaking and gapless. In this work, we study the emergence of ruled surfaces for systems with local Hamiltonians in infinite spatial dimension, where the reduced density matrices are known to be separable as a consequence of the quantum de Finetti＇s theorem. This allows us to identify the reduced density matrix geometry with joint product numerical range II of the Hamiltonian interaction terms. We focus on the case where the interaction terms have certain structures, such that a ruled surface emerges naturally when taking a convex hull of ∏. We show that, a ruled surface on sitting in ∏ has a gapless origin, otherwise it has a symmetry breaking origin. As an example, we demonstrate that a famous ruled surface, known as the oloid, is a possible shape of , with two boundary pieces of symmetry breaking origin separated by two gapless lines.

关键词： reduced density matrices quantum tomography numerical range quantum information oloid ruled surface

HDD4DBP: A Large-Scale Multi-Modal Benchmark on Driving Behavior Prediction

学校读者我要写书评

暂无评论

HDD4DBP: A Large-Scale Multi-Modal Benchmark on Driving Beha...

IEEE International Conference on systems, Man and Cybernetics

作者： Qinghui Dong Zhang Zhang Yubo Chang Wentao Chen Liang Wang Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Driving behavior prediction (DBP) plays an important role in autonomous driving. Accurately anticipating driving behaviors (e.g., left turn, right turn) of ego-vehicles 3–5 seconds before actual occurrences of maneuvers can help AI pilots planning safer trajectories or informing possible dangers to drivers. However, current DBP benchmark datasets, e.g., the Brain4Cars, are restricted by the limited amount of data samples and small number of behavior categories. Thus, there is an urgent need for creating a new larger-scale benchmark to help boost the studies of DBP. In this work, based on the annotations in the HRI Driving Dataset (HDD), we extract 5000+ clips from untrimmed multi-modal data sequences to form a new dataset, termed the HDD4DBP, as a convincing large-scale testbed for evaluating various DPB methods. Furthermore, inspired by the success of transformers on modeling long range dependence in sequences, we build a strong baseline with the vision transformer (ViT) backbone for predicting driving behaviors. Compared to previous representative baselines, a large margin performance gain can be achieved by our strong baseline on the HDD4DBP. Moreover, simply fine-tuning the pre-trained strong baseline can obtain the state-of-the-art performance on the Brain4Cars dataset, thereby futher confirming the benefits of the HDD4DBP. The dataset and source code will be released. Find data and code at https://***/HDD4DBP/MTL.

关键词： Accuracy Source coding Benchmark testing Predictive models Performance gain Transformers Trajectory Planning Driver behavior Vehicles

Notice of Retraction: An adaptive SVR modeling method based on VFS for robotic grinding

学校读者我要写书评

暂无评论

Notice of Retraction: An adaptive SVR modeling method based ...

International Conference on computer Science and Information Technology (CSIT)

作者： Yang Yang Yixu Song Jiaxin Wang Zhongxue Gan Lizhe Qi State Key Laboratory of Intelligent Technology and System Department of Computer S&T Tsinghua University Beijing China Research and Development Center InterSmart Robotic Systems Company Limited Langfang Hebei China

This article has been retracted by the publisher.

关键词：

VALID: A Comprehensive Virtual Aerial Image Dataset

学校读者我要写书评

暂无评论

VALID: A Comprehensive Virtual Aerial Image Dataset

IEEE International Conference on Robotics and Automation (ICRA)

作者： Lyujie Chen Feng Liu Yan Zhao Wufan Wang Xiaming Yuan Jihong Zhu Department of Computer Science and Technology State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing Department of Precision Instrument Tsinghua University Beijing

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Aerial imagery plays an important role in land-use planning, population analysis, precision agriculture, and unmanned aerial vehicle tasks. However, existing aerial image datasets generally suffer from the problem of inaccurate labeling, single ground truth type, and few category numbers. In this work, we implement a simulator that can simultaneously acquire diverse visual ground truth data in the virtual environment. Based on that, we collect a comprehensive Virtual AeriaL Image Dataset named VALID, consisting of 6690 high-resolution images, all annotated with panoptic segmentation on 30 categories, object detection with oriented bounding box, and binocular depth maps, collected in 6 different virtual scenes and 5 various ambient conditions (sunny, dusk, night, snow and fog). To our knowledge, VALID is the first aerial image dataset that can provide panoptic level segmentation and complete dense depth maps. We analyze the characteristics of VALID and evaluate state-of-the-art methods for multiple tasks to provide reference baselines. The experiment results demonstrate that VALID is well presented and challenging. The dataset is available at https://***/view/valid-dataset/.

关键词： Image segmentation Semantics Task analysis Object detection Image color analysis Benchmark testing Labeling

DFGET: Displacement-Field Assisted Graph Energy Transmitter for Gland Instance Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jian, Caiqing Qin, Yongbin Wang, Lihui Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

Gland instance segmentation is an essential but challenging task in the diagnosis and treatment of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a displacement-field assisted graph energy transmitter (DFGET) framework to solve these problems. Specifically, a novel message passing manner based on anisotropic diffusion is developed to update the node features, which can distinguish the isomorphic graphs and improve the expressivity of graph nodes for complex samples. Using such graph framework, the gland semantic segmentation map and the displacement field (DF) of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module based on diffusion theory is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands from the semantic segmentation maps. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the superiority of DFGET and effectiveness of the proposed anisotropic message passing manner and clustering method. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.5% and 3.4% respectively, while decreases the object-HD by 32.4%, achieving state-of-the-art performance. © 2023, CC BY-NC-ND.

关键词： Message passing

Delving deeper into the decoder for video captioning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Haoran Li, Jianmin Hu, Xiaolin State Key Laboratory of Intelligent Technology and Systems Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology THBI Department of Computer Science and Technology Tsinghua University Beijing100084 China

Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed to evaluate the performance of a model on a validation set so as to select the best checkpoint for testing. Finally, a new training strategy called professional learning is proposed which uses the strengths of a captioning model and bypasses its weaknesses. It is demonstrated in the experiments on Microsoft research Video Description Corpus (MSVD) and MSR-Video to Text (MSR-VTT) datasets that our model has achieved the best results evaluated by BLEU, CIDEr, METEOR and ROUGE-L metrics with significant gains of up to 18% on MSVD and 3.5% on MSR-VTT compared with the previous state-of-the-art *** Codes 68T45, 68T50. Copyright © 2020, The Authors. All rights reserved.

关键词： Decoding

LoRa on the Move: Performance Evaluation of LoRa in V2X Communications

学校读者我要写书评

暂无评论

LoRa on the Move: Performance Evaluation of LoRa in V2X Comm...

2018 IEEE intelligent Vehicles Symposium, IV 2018

作者： Li, Yuke Han, Shuangshuang Yang, Linyao Wang, Fei-Yue Zhang, Hui State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266109 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100049 China Qingdao Huituo Intelligent Machine Company Qingdao China Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha410073 China Computer Science Department School of Computer Science Carnegie Mellon University PittsburghPA15213 United States Conviva Inc. Silicon ValleyCA94404 United States

ISBN: (纸本)9781538644522

Recent years have witnessed much interest in Low Power Wide Area (LPWA) technologies, which are gaining unprecedented momentum and commercial interest towards the realisation of the Internet of Things (IoT). Long Range (LoRa), as a representative LPWA technology, has the potential to satisfy the growing demand for the longer range and larger amount connectivities in vehicular communication networks. In this paper, LoRa is firstly applied into two typical vehicular networks, namely Vehicle-to-Infrastructure (V2I)and Vehicle-to-Vehicle (V2V), and performance of LoRa schemes with different parameter configurations are evaluated and compared. Further, Monte Carlo simulations indicate that the schemes equipped with higher bandwidth or lower spreading factor exhibit significant advantages in combating the fast fading caused by Doppler effect in networks. © 2018 IEEE.

关键词： Monte Carlo methods