检索结果-内蒙古大学图书馆

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Jiahe Zhang, Jiawei Bai, Xiao Zhou, Jun Gu, Lin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China School of Information and Communication Technology Griffith University Australia RIKEN AIP Japan The University of Tokyo Japan

This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size. Our idea is to explicitly exploit the unequal contribution of spatial regions to guide talking portrait modeling. Specifically, to improve the accuracy of dynamic head reconstruction, a compact and expressive NeRF-based Tri-Plane Hash Representation is introduced by pruning empty spatial regions with three planar hash encoders. For speech audio, we propose a Region Attention Module to generate region-aware condition feature via an attention mechanism. Different from existing methods that utilize an MLP-based encoder to learn the cross-modal relation implicitly, the attention mechanism builds an explicit connection between audio features and spatial regions to capture the priors of local motions. Moreover, a direct and fast Adaptive Pose Encoding is introduced to optimize the head-torso separation problem by mapping the complex transformation of the head pose into spatial coordinates. Extensive experiments demonstrate that our method renders better high-fidelity and audio-lips synchronized talking portrait videos, with realistic details and high efficiency compared to previous methods. Code is availab.e at https://***/Fictionarry/ ER-NeRF. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

CLGT: A Graph Transformer for Student Performance Prediction in Collab.rative Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Peng, Tianhao Liang, Yu Wu, Wenjun Ren, Jian Pengrui, Zhao Pu, Yanjun State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Beijing Engineering Research Center for IoT Software and Systems Beijing University of Technology China Institute of Artificial Intelligence Beihang University China

Modeling and predicting the performance of students in collab.rative learning paradigms is an important task. Most of the research presented in literature regarding collab.rative learning focuses on the discussion forums and social learning networks. There are only a few works that investigate how students interact with each other in team projects and how such interactions affect their academic performance. In order to bridge this gap, we choose a software engineering course as the study subject. The students who participate in a software engineering course are required to team up and complete a software project together. In this work, we construct an interaction graph based on the activities of students grouped in various teams. Based on this student interaction graph, we present an extended graph transformer framework for collab.rative learning (CLGT) for evaluating and predicting the performance of students. Moreover, the proposed CLGT contains an interpretation module that explains the prediction results and visualizes the student interaction patterns. The experimental results confirm that the proposed CLGT outperforms the baseline models in terms of performing predictions based on the real-world datasets. Moreover, the proposed CLGT differentiates the students with poor performance in the collab.rative learning paradigm and gives teachers early warnings, so that appropriate assistance can be provided. Copyright © 2023, The Authors. All rights reserved.

关键词： Students

Heterophily-Aware Graph Attention Network

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Junfu Guo, Yuanfang Yang, Liang Wang, Yunhong State Key Laboratory of Software Development Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Artificial Intelligence Hebei University of Technology Tianjin300401 China

Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can hardly be effective in processing the networks with heterophily, in which the connected nodes usually possess different lab.ls or features. Existing heterophilic GNNs tend to ignore the modeling of heterophily of each edge, which is also a vital part in tackling the heterophily problem. In this paper, we firstly propose a heterophily-aware attention scheme and reveal the benefits of modeling the edge heterophily, i.e., if a GNN assigns different weights to edges according to different heterophilic types, it can learn effective local attention patterns, which enable nodes to acquire appropriate information from distinct neighbors. Then, we propose a novel Heterophily-Aware Graph Attention Network (HA-GAT) by fully exploring and utilizing the local distribution as the underlying heterophily, to handle the networks with different homophily ratios. To demonstrate the effectiveness of the proposed HA-GAT, we analyze the proposed heterophily-aware attention scheme and local distribution exploration, by seeking for an interpretation from their mechanism. Extensive results demonstrate that our HA-GAT achieves state-of-the-art performances on eight datasets with different homophily ratios in both the supervised and semi-supervised node classification tasks. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Link-identified Routing Architecture in Space

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hefan Wang, Zhiyuan Zhang, Shan Meng, Qingkai Luo, Hongbin The School of Computer Science and Engineering Beihang University Beijing100191 China The State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China The State Key Laboratory of Software Development Environment Beijing100191 China The Institute of Artificial Intelligence Beihang University Beijing100191 China The School of Cyber Science and Technology Beihang University Beijing100191 China

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient packet delivery. In this paper, we propose a Link-identified Routing (LiR) architecture for LEO satellite networks. The LiR architecture leverages the deterministic neighbor relation of LEO constellations, and identifies each inter-satellite link (ISL). Moreover, LiR architecture adopts source-route-style forwarding based on in-packet bloom filter (BF). Each satellite could efficiently encode multiple ISL identifiers via an in-packet BF to specify the end-to-end path for the packets. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwarding cases emerge. Based on the topology characteristics, we derive the expected forwarding overhead in a closed-form and propose the optimal encoding policy. To accommodate link-state changes in LEO satellite networks, we propose the on-demand rerouting scheme and the on-demand detouring scheme to address the intermittent ISLs. We also elab.rate how to take advantage of LiR architecture to achieve seamless handover for ground-satellite links (GSLs). Finally, we conduct extensive numerical experiments and packet-level simulations to verify our analytical results and evaluate the performance of the LiR architecture. © 2024, CC BY.

关键词： Satellite links

Large Language Model for science: A Study on P vs. NP

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dong, Qingxiu Dong, Li Xu, Ke Zhou, Guangyan Hao, Yaru Sui, Zhifang Wei, Furu Microsoft Research United States School of Computer Science Peking University China State Key Lab of Software Development Environment Beihang University China Department of Mathematics and Statistics Beijing Technology and Business University China

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous reasoning throughout 97 dialogue turns, concluding "P ≠ NP", which is in alignment with (Xu and Zhou, 2023). The investigation uncovers novel insights within the extensive solution space of LLMs, shedding light on LLM for science. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

Access Authentication for Mega-Constellation based on Hierarchical Consensus

学校读者我要写书评

暂无评论

Access Authentication for Mega-Constellation based on Hierar...

Satellite Computing (Satellite), IEEE International Conference on

作者： Xin Lai Zhiyuan Wang Shan Zhang Qingkai Meng Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing China

Low earth orbit (LEO) constellation has the potential to provide low-latency Internet services with the global coverage. However, LEO satellite networks with open channels and dynamic topology are faced with crucial security issue on authenticating terrestrial users. In this paper, we propose an access authentication method for LEO satellite networks based on consensus protocol PBFT, aiming to achieve small communication overhead and high authentication accuracy. The PBFT consensus protocol tolerates Byzantine nodes with the ratio 1/3, but incurs a tremendous communication overhead, therefore, it is not deployable in mega-constellation. To address this challenge, we propose to divide the LEO constellation into multiple consensus groups and present the design of hierarchical PBFT (H-PBFT). We analytically derive the communication overhead incurred by PBFT and our proposed H - PBFT and analyze the authentication accuracy achieved by these two protocols given the faulty satellite probability. The analytical results allow us to properly optimize the scale of the consensus groups and attain the desired tradeoff between small communication overhead and high authentication accuracy. Simulation results show that our proposed access authentication method based on H - PBFT outperforms state-of-the-art consensus protocols (i.e., PBFT and double-layer PBFT) in terms of communication overhead and authentication accuracy.

关键词：

Optimizing Link-Identified Forwarding Framework in LEO Satellite Networks

学校读者我要写书评

暂无评论

Optimizing Link-Identified Forwarding Framework in LEO Satel...

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Hefan Zhang Zhiyuan Wang Shan Zhang Qingkai Meng Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing China

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient data delivery. In this paper, we analyze the topology characteristics of LEO satellite networks, and propose a source-route-style forwarding framework. Specifically, we leverage the deterministic neighbor relationship and identify all the unidi-rectional inter-satellite links (ISLs). Moreover, our framework utilizes the in-packet bloom filter (BF) to store the source-route-style forwarding information. This way, the source satellite could encode multiple ISL identifiers into the BF, which actually specifies the forwarding path. The intermediate satellites only need to check whether the outgoing ISLs are encoded and forward packets accordingly. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwardings emerge. To reduce forwarding overhead, we take into account segment encoding, allowing the source and intermediate satellites to encode part of ISLs towards the destination. Overall, segment encoding seeks the right balance between forwarding overhead and encoding delay. We characterize a wide range of segment encoding policy in a unified framework, and derive the expected forwarding overhead in a closed-form. The segment encoding design is formulated as a binary non-linear programming, which is NP-hard. To overcome the challenge, we leverage its decomposable structure, and propose an efficient algorithm to solve it optimally. Finally, we validate our analytical results via packet-level experiments. Results also show that our proposed segment encoding policy significantly reduces the queuing delay compared to source encoding.

关键词：

Routing in LEO Satellite Networks: How Many Link-state Updates Do We Need?

学校读者我要写书评

暂无评论

Routing in LEO Satellite Networks: How Many Link-State Updat...

Satellite Computing (Satellite), IEEE International Conference on

作者： Qian Shan Zhiyuan Wang Shan Zhang Qingkai Meng Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing China

Low earth orbit (LEO) satellite networks equipped with inter-satellite links (ISLs) will be an indispensable component of the future Internet. Routing protocol installed on LEO satellite networks plays a significant role on achieving efficient data delivery. LEO satellite networks exhibit two typical topology features, i.e., deterministic neighbor relationship and intermittent ISLs, which are different from terrestrial Internet. Hence the classic link-state routing protocols (e.g., OSPF) designed for terrestrial Internet are naturally unable to accommodate these topology features. In this paper, we present the design of localized fine-grained (LoFi) link-state routing protocol for LEO satellite networks. The key idea of LoFi is to reduce the dissemination range of coarse-grained link connectivity and incorporate fine-grained link-load awareness. Specifically, LoFi has two key parameters, i.e., state dissemination range and load variation threshold, which determine how far to disseminate link state update and how precise to detect the link load change, respectively. The two parameters allow the LEO satellite networks to flexibly achieve a desired tradeoff between good packet delivery performance and small control overhead. We evaluate the performance of LoFi via extensive packet-level experiments on OMNeT++ under Iridium constellation. Results show that LoFi improves the packet delivery performance (up to 94.4 %) and reduces the control overhead (up to 85.7 %) compared to state-of-the-art link-state protocol ELB.

关键词：

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Network for 3D Object Detection in LiDAR Point Clouds

学校读者我要写书评

暂无评论

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Net...

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Meng Liu Jianwei Niu Yu Liu China North Artificial Intelligence and Innovation Research Institute Beijing China China North Vehicle Research Institute Beijing China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

LiDAR 3D object detection for autonomous driving is an important issue. To address this issue, this paper provides a two-stage anchor-based solution. Firstly, voxel feature encoding and sparse convolution networks were employed for proposal generation. Secondly, we performed voxel feature aggregation and hierarchical feature learning in combination with the proposals, multi-level and multiscale voxel features, point encoding and voxel-wise ROI pooling. The aggregated object-wise voxel features were utilized to refine the proposals. Extensive experiments were conducted on three challenging datasets: KITTI, nuScenes and Waymo. Experimental results demonstrated that our SP-Net can effectively achieve multi-category 3D object detection in diverse scenarios offering satisfactory accuracy and speed (28.6 FPS).

关键词：