检索结果-内蒙古大学图书馆

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Fast Texture Synthesis via Pseudo Optimizer

学校读者我要写书评

暂无评论

Fast Texture Synthesis via Pseudo Optimizer

Conference on computer vision and Pattern Recognition (CVPR)

作者： Wu Shi Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Texture synthesis using deep neural networks can generate high quality and diversified textures. However, it usually requires a heavy optimization process. The following works accelerate the process by using feed-forward networks, but at the cost of scalability. diversity or quality. We propose a new efficient method that aims to simulate the optimization process while retains most of the properties. Our method takes a noise image and the gradients from a descriptor network as inputs, and synthesize a refined image with respect to the target image. The proposed method can synthesize images with better quality and diversity than the other fast synthesis methods do. Moreover, our method trained on a large scale dataset can generalize to synthesize unseen textures.

关键词： Neural networks Training Transforms Scalability Optimization methods Convolution

Learning Attentive Pairwise Interaction for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhuang, Peiqin Wang, Yali Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%). Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

Image saliency detection method based on multi-feature maps fusion 4

学校读者我要写书评

暂无评论

Image saliency detection method based on multi-feature maps ...

4th International Conference on computer Graphics, Image, and Virtualization, ICCGIV 2024

作者： Li, Xiaoli Liu, Yunpeng Zhao, Huaici Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Shenyang China The Key Lab of Image Understanding and Computer Vision Shenyang China Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510683242

In this research, we introduce an innovative saliency detection algorithm, comprising three essential steps. Firstly, leveraging fully convolutional networks with aggregation interaction modules, we generate an initial saliency map. Secondly, we extract hand-craft and deep features to express the image, then use manifold ranking method to construct saliency maps. Ultimately, by integrating the outcomes from preceding stages, we generate the final saliency map. Experimental findings demonstrate that our method surpasses twelve cutting-edge saliency detection techniques in terms of precision, recall, F-measure, and MAE value metrics." © 2024 SPIE.

关键词： Feature extraction

Local Gaussian Modifiers (LGMs): UAV Dynamic Trajectory Generation for Onboard Computation

学校读者我要写书评

暂无评论

Local Gaussian Modifiers (LGMs): UAV Dynamic Trajectory Gene...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Miguel Fernandez-Cortizas David Perez-Saura Rafael Perez-Segui Javier Rodriguez-Vazquez Juan S. Cely Pascual Campoy Computer Vision and Aerial Robotics group (CVAR) Centre for Automation and Robotics (CAR) Universidad Politécnica de Madrid (UPM) Madrid Spain Department of Artificial Intelligence Universidad Politécnica de Madrid Madrid Spain Intelligent Robotics Lab Rey Juan Carlos University Madrid Spain

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

Agile autonomous drones are becoming increasingly popular in research due to the challenges they represent in fields like control, state estimation, or perception at high speeds. When all algorithms are computed onboard the UAV, computational limitations make the task of agile flight even more difficult. One of the most computationally expensive tasks in agile flight is the generation of optimal trajectories. When these trajectories must be updated online due to changes in the environment or uncertainties, this high computational cost may result in insufficient time to reach the desired waypoints, which could cause a drone crash in cluttered environments. In this paper, we present Local Gaussian Modifiers (LGMs), a fast and lightweight way of modifying computationally heavy trajectories when recalculating them in time is not possible due to computational limitations. Moreover, we propose a strategy for deciding when is convenient to use these modifiers or recalculate the whole trajectory based on an estimation of the computational time of this trajectory generation. A trajectory blending procedure is also proposed to ensure smoothness in UAV control when a new trajectory is computed. Our approach was validated in simulation, being able to pass through a race circuit with moving gates, achieving speeds up to 16.0 m/s. Real flight validation was also performed achieving speeds up to 4.0 m/s in a fully autonomous pipeline using onboard computing.

关键词： Uncertainty Pipelines Logic gates Autonomous aerial vehicles Robustness Motion capture Trajectory

Learning Deep Sensorimotor Policies for vision-Based Autonomous Drone Racing

学校读者我要写书评

暂无评论

Learning Deep Sensorimotor Policies for Vision-Based Autonom...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jiawei Fu Yunlong Song Yan Wu Fisher Yu Davide Scaramuzza Department of Informatics Robotics and Perception Group University of Zurich Switzerland Department of Neuroinformatics University of Zurich and ETH Zurich Switzerland Visual Intelligence and Systems Group in the Computer Vision Lab ETH Zurich

The development of effective vision-based algorithms has been a significant challenge in achieving autonomous drones, which promise to offer immense potential for many real-world applications. This paper investigates learning deep sensorimotor policies for vision-based drone racing, which is a particularly demanding setting for testing the limits of an algorithm. Our method combines feature representation learning to extract task-relevant feature representations from high-dimensional image inputs with a learning-by-cheating framework to train a deep sensorimotor policy for vision-based drone racing. This approach eliminates the need for globally-consistent state estimation, trajectory planning, and handcrafted control design, allowing the policy to directly infer control commands from raw images, similar to human pilots. We conduct experiments using a realistic simulator and show that our vision-based policy can achieve state-of-the-art racing performance while being robust against unseen visual disturbances. Our study suggests that consistent feature embeddings are essential for achieving robust control performance in the presence of visual disturbances. The key to acquiring consistent feature embeddings is utilizing contrastive learning along with data augmentation. Video: https://***/AX_fcnW9yqE

关键词：

Learning Deep Sensorimotor Policies for vision-based Autonomous Drone Racing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Jiawei Song, Yunlong Wu, Yan Yu, Fisher Scaramuzza, Davide Robotics and Perception Group Department of Informatics University of Zurich Department of Neuroinformatics University of Zurich ETH Zurich Switzerland Visual Intelligence and Systems Group in the Computer Vision Lab at ETH Zurich Switzerland

unstructured environments, enabling various real-world applications. However, the lack of effective vision-based algorithms has been a stumbling block to achieving this goal. Existing systems often require hand-engineered components for state estimation, planning, and control. Such a sequential design involves laborious tuning, human heuristics, and compounding delays and errors. This paper tackles the vision-based autonomous-drone-racing problem by learning deep sensorimotor policies. We use contrastive learning to extract robust feature representations from the input images and leverage a two-stage learning-by-cheating framework for training a neural network policy. The resulting policy directly infers control commands with feature representations learned from raw images, forgoing the need for globally-consistent state estimation, trajectory planning, and handcrafted control design. Our experimental results indicate that our vision-based policy can achieve the same level of racing performance as the state-based policy while being robust against different visual disturbances and distractors. We believe this work serves as a stepping-stone toward developing intelligent vision-based autonomous systems that control the drone purely from image inputs, like human pilots. Copyright © 2022, The Authors. All rights reserved.

关键词： Drones

Millimeter-wave radar image analysis for the traffic sensing 2

学校读者我要写书评

暂无评论

Millimeter-wave radar image analysis for the traffic sensing

2nd Spring International Conference on Defence Technology, ICDT 2020

作者： Wu, H.M. Qi, F. Wang, J.K. Wang, Y. School of Communication Science and Engineering Northeastern University Liaoning Province Shenyang110819 China Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China

Millimeter-wave(MMW) radar sensing is one of the most promising technologies to provide safe navigation for autonomous vehicles due to its expected high-resolution imaging capability However, driverless cars have higher request for different environment and light conditions. Therefore, millimetre-wave imaging is of paramount importance for complex load scenario. In this paper, we have built models of pavement pits and bulges and analysed their with differences ways of antennas. A comparison of the imaging performance of experimental systems operating at a MMW radar and a Lidar is presented with the analysis of features for initial image interpretation Experimental images of the complex road surface are made by a 94GHz frequency-modulated continuous-wave (FMCW) radar technique with 3mm wavelength. © Published under licence by IOP Publishing Ltd.

关键词： Optical radar

Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Song, Siyang Shao, Zilong Jaiswal, Shashank Shen, Linlin Valstar, Michel Gunes, Hatice Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Computer Vision Institute Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Computer Vision Lab University of Nottingham Nottingham United Kingdom

This paper proposes to recognise the true (self-reported) personality from the learned simulation of the target subject’s cognition. This approach builds on two following findings in cognitive science: (i) human cognition partially determines expressed behaviour and is directly linked to true personality traits;and (ii) in dyadic interactions individuals’ nonverbal behaviours are influenced by their conversational partner’s behaviours. In this context, we hypothesise that during a dyadic interaction, a target subject’s facial reactions are driven by two main factors, i.e. their internal (person-specific) cognitive process, and the externalised nonverbal behaviours of their conversational partner. Consequently, we propose to represent the target subject’s (defined as the listener) person-specific cognition in the form of a person-specific CNN architecture that has unique architectural parameters and depth, which takes audio-visual non-verbal cues displayed by the conversational partner (defined as the speaker) as input, and is able to reproduce the target subject’s facial reactions. Each person-specific CNN is explored by the Neural Architecture Search (NAS) and a novel adaptive loss function, which is then represented as a graph representation for recognising the target subject’s true personality. Experimental results not only show that the produced graph representations are well associated with target subjects’ personality traits in both human-human and human-machine interaction scenarios, and outperform the existing approaches with significant advantages, but also demonstrate that the proposed novel strategies such as adaptive loss, and the end-to-end vertices/edges feature learning, help the proposed approach in learning more reliable personality representations. Building on our earlier version of this work, this paper further proposes: (i) assigning a unique depth for each CNN;(ii) a novel end-to-end graph vertex feature learning strategy;(iii) a transformer-bas

关键词： Cognitive systems