检索结果-内蒙古大学图书馆

HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Jia-Qi Duan, Hao-Bin Chen, Jun-Long Shamir, Ariel Wang, Miao The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Efi Arazi School of Computer Science Reichman University Herzliya4610000 Israel The Zhongguancun Laboratory Beijing100195 China

The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic. However, it has been observed that the lanes have a geometrical structure that resembles a straight line, leading to improved lane detection results when utilizing this characteristic. To address this challenge, we propose a hierarchical Deep Hough Transform (DHT) approach that combines all lane features in an image into the Hough parameter space. Additionally, we refine the point selection method and incorporate a Dynamic Convolution Module to effectively differentiate between lanes in the original image. Our network architecture comprises a backbone network, either a ResNet or Pyramid Vision Transformer, a Feature Pyramid Network as the neck to extract multi-scale features, and a hierarchical DHT-based feature aggregation head to accurately segment each lane. By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features. Subsequently, the lane features are fed into the feature decoder, which predicts the final position of the lane. Our proposed network structure demonstrates improved performance in detecting heavily occluded or worn lane images, as evidenced by our extensive experimental results, which show that our method outperforms or is on par with state-of-the-art techniques. © 2023, CC BY-NC-SA.

关键词： Hough transforms

Few-Shot Open-Set Object Detection via Conditional Evidence Decoupling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Zhaowei Su, Binyi Zhang, Hua Zhou, Zhong The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300401 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Zhongguancun Laboratory Beijing100190 China

Few-shot Open-set Object Detection (FOOD) poses a significant challenge in real-world scenarios. It aims to train an open-set detector under the condition of scarce training samples, which can detect known objects while rejecting unknowns. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a two-stage open-set object detection framework with prompt learning, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we propose an Attribution-Gradient-based Pseudo-unknown Mining (AGPM) method to select region proposals with high uncertainty, which leverages the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we decouple known and unknown properties in pseudo-unknown samples to learn distinct knowledge with proposed Conditional Evidence Decoupling (CED), which enhances separability between knowns and unknowns. Additionally, we adjust the output probability distribution through Abnormal Distribution Calibration (ADC), which serves as a regularization term to establish robust decision boundaries for the unknown rejection. Our method has achieved superior performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model

学校读者我要写书评

暂无评论

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via...

International Conference on computer Vision (ICCV)

作者： Yin Wang Zhiying Leng Frederick W. B. Li Shun-Cheng Wu Xiaohui Liang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Technical University of Munich Germany Department of Computer Science University of Durham U.K. Zhongguancun Laboratory Beijing China

Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal and spatial relationships required to conform to a given text description. In this work, we propose a fine-grained method for generating high-quality, conditional human motion sequences supporting precise text description. Our approach consists of two key components: 1) a linguistics-structure assisted module that constructs accurate and complete language feature to fully utilize text information; and 2) a context-aware progressive reasoning module that learns neighborhood and overall semantic linguistics features from shallow and deep graph neural networks to achieve a multi-step inference. Experiments show that our approach outperforms text-driven motion generation methods on HumanML3D and KIT test sets and generates better visually confirmed motion to the text conditions.

关键词：

Why Go Full? Elevating Federated Learning Through Partial Network Updates

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024, CC BY.

关键词： Federated learning

Degradation Conditioned GAN for Degradation Generalization of Face Restoration Models

学校读者我要写书评

暂无评论

Degradation Conditioned GAN for Degradation Generalization o...

IEEE International Conference on Image Processing

作者： Song Qi Wu Shi Guojing Ge Liang Chang Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences School of Artificial Intelligence Beijing Normal University Institute of Automation Chinese Academy of Sciences

Face restoration models are usually trained on synthetic degraded data to output an image that matches the clean version of itself. Most previous methods use a single model to deal with all the degradation levels, resulting in a domain generalization problem. We explore the value of degradation information and propose a Degradation Conditioned GAN (DeCGAN). The architecture consists of modulated convolution, bias, and fusion modules, inspired by deblurring, denoising and super-resolution. The whole network can be modulated by the degradation levels to achieve delicate and precise restoration effects. Experiments are conducted on conventional and modulated face restoration tasks. DeCGAN can achieve more faithful restoration and better metrics (FID, LPIPS, etc.) than previous methods do. Moreover, our model performs well on real-world low-quality face images.

关键词：

Improving Multi-Person Pose Tracking with A Confidence Network

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fu, Zehua Zuo, Wenhang Hu, Zhenghui Liu, Qingjie Wang, Yunhong The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Hangzhou Innovation Institute Behang University Hangzhou310051 China

Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: human detection, pose estimation and tracking. Although promising results have been achieved, these methods rely heavily on high-performance detectors and may fail to track persons who are occluded or miss-detected. To overcome these problems, in this paper, we develop a novel keypoint confidence network and a tracking pipeline to improve human detection and pose estimation in top-down approaches. Specifically, the keypoint confidence network is designed to determine whether each keypoint is occluded, and it is incorporated into the pose estimation module. In the tracking pipeline, we propose the Bbox-revision module to reduce missing detection and the ID-retrieve module to correct lost trajectories, improving the performance of the detection stage. Experimental results show that our approach is universal in human detection and pose estimation, achieving state-of-the-art performance on both PoseTrack 2017 and 2018 datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

Sequential Texts Driven Cohesive Motions Synthesis with Natural Transitions

学校读者我要写书评

暂无评论

Sequential Texts Driven Cohesive Motions Synthesis with Natu...

International Conference on computer Vision (ICCV)

作者： Shuai Li Sisi Zhuang Wenfeng Song Xinyu Zhang Hejia Chen Aimin Hao State Key Laboratory of Virtual Reality Technology and Systems Beihang University P.R. China Zhongguancun Laboratory Beijing P.R. China Computer School Beijing Information Science and Technology University P.R. China

The intelligent synthesis/generation of daily-life motion sequences is fundamental and urgently needed for many VR/metaverse-related applications. However, existing approaches commonly focus on monotonic motion generation (e.g., walking, jumping, etc.) based on single instruction-like text, which is still not intelligent enough and can’t meet practical demands. To this end, we propose a cohesive human motion sequence synthesis framework based on free-form sequential texts while ensuring semantic connection and natural transitions between adjacent motions. At the technical level, we explore the local-to-global semantic features of previous and current texts to extract relevant information. This information is used to guide the framework in understanding the semantics of the current moment. Moreover, we propose learnable tokens to adaptively learn the influence range of the previous motions towards natural transitions. These tokens can be trained to encode the relevant information into well-designed transition loss. To demonstrate the efficacy of our method, we conduct extensive experiments and comprehensive evaluations on the public dataset as well as a new dataset produced by us. All the experiments confirm that our method outperforms the state-of-the-art methods in terms of semantic matching, realism, and transition fluency. Our project is public available. https://***/sequential-texts-to-motion/

关键词：

Early Prediction of Student Performance with LSTM-Based Deep Neural Network

学校读者我要写书评

暂无评论

Early Prediction of Student Performance with LSTM-Based Deep...

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Han Wan Mengying Li Zihao Zhong Xiaoyan Luo State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Image Processing Center School of Astronautics Beihang University Beijing China

The shift to hybrid teaching during the COVID-19 pandemic brought about a real challenge to predict student performance and conduct timely interventions on at-risk students. This study proposed a deep neural network supporting the early prediction of student performance. Bidirectional LSTM, Global Average Pooling, and TIME MASK structure were utilized in the improved GritNet model. Subsequently, this study optimized the hyperparameters with the aid of the hill-climbing algorithm. Finally, on-campus data sets were used in experiments to evaluate the model's performance. Data were collected from a course that carried out multiple iterations from Fall 2021 to Fall 2022. In Fall 2022, the proposed model achieved a ROC-AUC value of 95.47% in the 8th week, while the baseline model only achieved 91.44% in the same week. Besides, the proposed model achieved a ROC-AUC value of 89.67% in the 4th week, which meant it had acceptable prediction performance in the early stage. The experimental findings demonstrated that the model was capable of predicting the academic performance of students in hybrid courses early on.

关键词：

VR content creation and exploration with deep learning: A survey

学校读者我要写书评

暂无评论

Computational Visual Media 2020年第1期6卷 3-28页

作者： Miao Wang Xu-Quan Lyu Yi-Jun Li Fang-Lue Zhang State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China. Peng Cheng Laboratory Shenzhen 518000China School of Engineering and Computer Science Victoria University of WellingtonNew Zealand

virtual reality(VR)offers an artificial,computer generated simulation of a real life *** originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and *** deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion,they can build very powerful models which leverage large quantities of visual media *** of VR methods and applications has been significantly boosted by the recent developments in deep learning *** content creation and exploration relates to image and video analysis,synthesis and editing,so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed,designed specifically to handle panoramic images and video and virtual 3 D *** article surveys recent research that uses such deep learning methods for VR content creation and *** considers the problems involved,and discusses possible future directions in this active and emerging research area.

关键词： virtual reality deep learning neural networks 360°image and video virtual content