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
Computer Science, Artificial Intelligence
Bingfeng Zhang et al.
Summary: In this paper, the authors propose an affinity attention graph neural network (A(2)GNN) for bounding box supervised semantic segmentation. They generate pseudo semantic-aware seeds and use an affinity Convolutional Neural Network (CNN) to form semantic graphs. The A2GNN utilizes an affinity attention layer to propagate semantic labels accurately. They also introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint. Experimental results show that their approach achieves state-of-the-art performances on Pascal VOC 2012 datasets and can be applied to other weakly supervised tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenbin Zhu et al.
Summary: This paper introduces a new problem setup called local-adaptive face recognition (LaFR), aiming to achieve optimal performance by training local-adapted models. Experimental results show that our proposed solution is more effective for adapting face recognition models in each specific environment.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Information Systems
Jeff Johnson et al.
Summary: This paper addresses the issue of better utilizing GPUs for similarity search tasks, proposing a novel design for k-selection which outperforms existing approaches by large margins. The implementation achieves up to 55 percent of theoretical peak performance and enables significantly faster nearest neighbor implementations on GPU. It also allows for the construction of high accuracy k-NN graphs on large datasets in a fraction of the time compared to prior methods.
IEEE TRANSACTIONS ON BIG DATA
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yifan Xing et al.
Summary: The paper proposes a hierarchical graph neural network model for clustering a set of images into an unknown number of identities. The Hi-LANDER method achieves a 49% improvement in F-score and a 7% increase in Normalized Mutual Information (NMI) compared to current GNN-based clustering algorithms. Additionally, the unified framework achieves a three-fold decrease in computational cost.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Junfu Liu et al.
Summary: In this paper, a new face clustering method is proposed, which formulates the task as a pairwise relationship classification to avoid memory-consuming learning on large-scale graphs, while enhancing the classifier by utilizing contextual information. Experimental results demonstrate that the method achieves outstanding performances in both speed and memory consumption.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ryan Razani et al.
Summary: In this study, a new computationally efficient LiDAR based panoptic segmentation framework, GP-S3Net, is proposed. It is a proposal-free approach that utilizes a novel instance-level network and graph convolutional network to identify objects and fuse them with background classes. Extensive experiments demonstrate that GP-S3Net outperforms current state-of-the-art approaches, ranking 1st on competitive public leaderboard.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Biplob Debnath et al.
Summary: The study reveals that existing clustering algorithms fail to improve clustering quality when dealing with uncertainty in face images, mainly due to excessive false-positives and false-negatives. The proposed uncertainty-aware clustering algorithm, UAC, significantly enhances clustering results by reducing false-positives and false-negatives.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuan-Bac Nguyen et al.
Summary: The research introduces a Transformer-based method called Clusformer, which achieves automatic visual clustering through unsupervised attention mechanism. It can handle noisy or hard samples and collaborates flexibly and effectively with different deep network models.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zheng Zhu et al.
Summary: This paper introduces a large-scale face benchmark dataset and evaluation protocol, which significantly reduces failure rates and achieves high ranks in benchmark competitions. The cleaned dataset also serves as a valuable resource for building baseline models for face recognition systems.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Computer Science, Artificial Intelligence
Wanhua Li et al.
Summary: This paper investigates facial kinship verification problem through hierarchical reasoning graph networks, proposing S-RGN and H-RGN for this purpose. S-RGN constructs a star-shaped graph for relational reasoning, while H-RGN introduces hierarchical graph structure and performs bottom-up comparative information abstraction and top-down comprehensive signal propagation. Experimental results show competitive performance of the proposed methods on kinship databases.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Information Systems
Wei-Lin Chiang et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhongdao Wang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Lei Yang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Computer Science, Theory & Methods
Yichun Shi et al.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2018)
Article
Computer Science, Artificial Intelligence
Charles Otto et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Proceedings Paper
Computer Science, Information Systems
Brianna Maze et al.
2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Wei-An Lin et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Qiong Cao et al.
PROCEEDINGS 2018 13TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE & GESTURE RECOGNITION (FG 2018)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Weiyang Liu et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Ira Kemelmacher-Shlizerman et al.
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Yandong Guo et al.
COMPUTER VISION - ECCV 2016, PT III
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Article
Computer Science, Information Systems
Enrique Amigo et al.
INFORMATION RETRIEVAL
(2009)
