Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Wenhao Wu et al.
Summary: Sufficient labeled training data may not be available for pedestrian detection in many real-world scenes. In this paper, a Scene-adaptive Pseudo Annotation (SaPA) approach is proposed to improve the generalization performance and pseudo annotation quality for training a more precise and scene-specific pedestrian detector, by exploiting both source data with sufficient supervision and unannotated target data with domain-specific information.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Gaihua Wang et al.
Summary: This paper introduces a cross self-attention network (CSANet) for raw point cloud classification and segmentation tasks. It has permutation invariance and can learn the coordinates and features of point cloud simultaneously. To capture features at different scales, a multi-scale fusion (MF) module is proposed, which adaptively considers information from different scales and brings richer gradient information, achieving competitive results.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Haotian Ren et al.
Summary: This survey provides a comprehensive review of the applications of graph convolutional networks (GCNs) in natural language processing and computer vision. It covers the principles of GCNs, various applications in these two fields, and discusses their limitations and future research directions.
KNOWLEDGE-BASED SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yukang Chen et al.
Summary: This paper introduces two new modules, focal sparse convolution (Focals Conv) and its multi-modal variant, to enhance the capability of Sparse CNNs for 3D object detection. These modules, which make feature sparsity learnable with position-wise importance prediction, can be jointly trained and readily substituted in existing Sparse CNNs, achieving state-of-the-art performance on benchmark datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Tianyu Guo et al.
Summary: This paper focuses on non-adversarial generative networks and proposes a method to optimize the generator on a Wasserstein ball. Experimental results demonstrate that this method can effectively learn image generators in a non-adversarial approach.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Giuseppina Andresini et al.
Summary: The paper introduces a novel deep learning methodology using convolutional neural networks for network intrusion detection, where network flows are represented as 2D images to analyze potential data patterns and achieve better predictive accuracy compared to competitive architectures.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Environmental Sciences
Yifei Tian et al.
Summary: In this study, a method named DGCB-Net was proposed for 3D object recognition, utilizing edge convolutional layers for local feature extraction and a broad architecture for extending point cloud feature aggregation. Compared to other algorithms, DGCB-Net showed better recognition performance on ModelNet10/40 and scanning point cloud datasets.
Article
Computer Science, Artificial Intelligence
Chongben Tao et al.
Summary: The paper proposed a stereo priori RCNN based car detection method for autonomous driving, which combines traditional RPN with a Mask-branch mechanism to improve the accuracy of 3D target detection and utilize RGB images for semantic information. Extensive numerical experiments on Kitti dataset and nuScenes dataset demonstrate the efficiency and effectiveness of the proposed algorithm.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Pengshuai Yin et al.
Summary: This paper presents a graph convolution neural network-based method for estimating the 6D pose of objects from a single RGB-D image. The proposed method fuses appearance features with geometry features to predict pixel-level pose and confidences for outlier predictions. The network includes a residual graph convolution module to learn discriminative features, allowing for end-to-end training and fast inference.
KNOWLEDGE-BASED SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Michael Meyer et al.
Summary: This research focuses on leveraging raw radar tensor data and utilizing a graph neural network to achieve a significant improvement of +10% in target detection accuracy, while increasing the maximum detection range for radar data from previously 20m to 100m.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Prarthana Bhattacharyya et al.
Summary: The paper proposes two variants of self-attention for contextual modeling in 3D object detection and demonstrates consistent improvement in performance across different detectors, showing enhanced accuracy and efficiency.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuning Chai et al.
Summary: The paper proposes a method to learn 3D representation from 2D perspective range images using a 2D convolutional network architecture. It introduces four different convolution kernels and explores cross-modality fusion. The method shows competitive performance in pedestrian detection and efficiency compared to existing models.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Qiuxiao Chen et al.
Summary: The proposed technique generates Sparse Activation Maps (SAM) to provide visual explanations for volumetric-based 3D object detection networks, helping to understand the network structures and effectiveness at different layers. Experimental results demonstrate the visual observations of SAM matching the detection results of three volumetric-based models on the KITTI dataset.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Article
Computer Science, Artificial Intelligence
Shaoshuai Shi et al.
Summary: This study proposes a novel point-cloud-based 3D object detection framework, Part-A(2) net, which includes two stages: part-aware and part-aggregation. By utilizing part supervisions from 3D ground-truth boxes and a new-designed RoI-aware point cloud pooling module, the framework achieves high-quality 3D proposals and accurate intra-object part locations prediction.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Engineering, Electrical & Electronic
Guojun Wang et al.
Summary: This study introduces a voxel-based background filtering method to improve vehicle detection with RSU LiDAR in mine environments. The method models average height and the number of points for each voxel as Gaussian distribution to generate a background table. Additionally, a multivariate Gaussian loss is proposed to address the impact of false negative points and improve the generalization ability of 3D detectors.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Pengfei Du et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Computer Science, Software Engineering
Yue Wang et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Engineering, Electrical & Electronic
Shuo Gu et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Yue Wang et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Lei Wang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Chemistry, Analytical
Yan Yan et al.
Article
Robotics
Yiming Zeng et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Mengye Ren et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Article
Robotics
John Leonard et al.
JOURNAL OF FIELD ROBOTICS
(2008)
