相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Engineering, Electrical & Electronic
Zhengxia Zou et al.
Summary: Object detection, a fundamental problem in computer vision, has received significant attention in recent years. This article reviews the rapid technological evolution of object detection over the past two decades and its impact on the entire computer vision field. It covers various topics such as milestone detectors, datasets, metrics, fundamental building blocks, speedup techniques, and state-of-the-art methods.
PROCEEDINGS OF THE IEEE
(2023)
Article
Engineering, Electrical & Electronic
Quanxin Zhang et al.
Summary: Deep neural networks are widely used but lack transparency and interpretability. Attackers can exploit this to insert backdoors and manipulate training data, posing a serious threat to the security of the network. This paper provides a comprehensive review of backdoor attacks, categorizing them into poisoning-based and non-poisoning-based attacks, and proposes a mathematical model to summarize different attack types.
CHINESE JOURNAL OF ELECTRONICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yizhou Zhao et al.
Summary: In this paper, a architecture called Semantic-aligned Fusion Transformer (SaFT) is proposed to address the issue of query-support semantic misalignment in one-shot object detection. By leveraging the attention mechanism, SaFT achieves significant performance gains on multiple benchmarks, lifting the state-of-the-art results to a higher level.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yanghao Li et al.
Summary: This paper investigates Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. The improved version of MViT incorporates decomposed relative positional embeddings and residual pooling connections. Evaluation on different tasks shows that MViTv2 outperforms prior work in terms of accuracy.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ziteng Gao et al.
Summary: This paper proposes a fast-converging query-based object detector named AdaMixer. By improving the adaptability of query-based decoding processes, the detector achieves higher detection performance. AdaMixer enjoys architectural simplicity and does not require extra network design, and it achieves satisfactory results on challenging benchmark tests.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Hardware & Architecture
Li Tan et al.
Summary: A new UAV image target detection algorithm is proposed, which improves the detection accuracy through techniques such as hollow convolution, ultra-lightweight subspace attention mechanism, and soft non-maximum suppression. Experimental results show a 5% improvement compared to the YOLOv4 algorithm.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Chaoqi Chen et al.
Summary: Recent research on two-stage cross-domain detection has focused on exploring local feature patterns to achieve more accurate adaptation results. This study introduces an Implicit Instance-Invariant Network (I(3)Net) tailored for adapting one-stage detectors, which implicitly learns instance invariant features by leveraging the natural characteristics of deep features in different layers. Experimental results demonstrate that I(3)Net outperforms the state-of-the-art on benchmark datasets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Chang Xu et al.
Summary: This paper proposes a new metric called Dot Distance (DotD) for tiny object detection, which significantly improves the performance of anchor-based detectors by calculating the normalized Euclidean distance between two bounding boxes.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jinwang Wang et al.
Summary: Object detection in Earth Vision has made progress, but tiny object detection in aerial images remains challenging and requires specialized detectors. Researchers introduced the AI-TOD dataset and M-CenterNet learning network, improving the performance of tiny object detection.
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
(2021)
Article
Computer Science, Artificial Intelligence
Kaiming He et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Hang Xu et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Engineering, Electrical & Electronic
Zhizhuo Sun et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2018)
Article
Computer Science, Information Systems
Yu Xiao et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Editorial Material
Computer Science, Information Systems
Milan Erdelj et al.
IEEE PERVASIVE COMPUTING
(2017)
Article
Computer Science, Artificial Intelligence
Shaoqing Ren et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Hardware & Architecture
Alex Krizhevsky et al.
COMMUNICATIONS OF THE ACM
(2017)
Article
Computer Science, Artificial Intelligence
Ross Girshick et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)