Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Zhao-Min Chen et al.
Summary: The task of multi-label image recognition is to predict the set of object labels in an image, taking into account label dependencies. We propose graph convolutional networks (GCNs) based models for this task, which capture inter-dependent class level representations by constructing directed graphs and propagating information between classes. We design two models that approach multi-label classification from different perspectives, integrating prior knowledge and decomposing visual representations. Empirical results show that our models outperform state-of-the-art methods and have advantages in other multi-label classification applications.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Saadman Sakib et al.
Summary: This paper proposes a framework for recognizing pedestrian attributes in surveillance scenarios, which achieves high performance by using deep learning and transfer learning techniques. Different CNN architectures are utilized and fine-tuned, and data balancing techniques are applied to address the class imbalance problem of the dataset.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Shizhuo Xu et al.
Summary: The study introduces an anime image super-resolution method based on the Swin Transformer, utilizing shallow and deep feature extraction to reconstruct and upsample images. Experimental results demonstrate the superior performance of this approach compared to others.
Proceedings Paper
Computer Science, Artificial Intelligence
Ziwen Lan et al.
Summary: This study presents a multi-modal multi-label attribute classification model in anime illustration based on Graph Convolutional Networks (GCN) using domain-specific semantic features, which captures more comprehensive relationships between attributes and improves the accuracy of image captions in anime illustrations.
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Shuhong Chen et al.
Summary: Human pose information is critical for various image processing tasks. However, there is limited research on pose estimation for illustrations. This study aims to bridge this research gap by utilizing transfer learning and expanding existing datasets. The proposed state-of-the-art character pose estimator is then applied to pose-guided illustration retrieval.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Duhyeon Bang et al.
Summary: The paper introduces a new algorithm called manifold-guided generative adversarial network (MGGAN) to address mode collapse and enhance the diversity of data distribution. By leveraging a guidance network on existing GAN architecture, MGGAN is able to penalize mode imbalance and sample data distribution with greater diversity effectively.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Guoxing Yang et al.
Summary: A deep facial attribute editing model aims to meet the requirements of attribute correctness and irrelevance preservation, proposing a novel latent space factorization model called L2M-GAN that strikes a perfect balance between editing local and global attributes. Extensive experiments on CelebA-HQ demonstrate significant improvements over the state-of-the-arts.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Khoi Pham et al.
Summary: The paper introduces a large-scale in-the-wild visual attribute prediction dataset, posing challenges to existing methods in terms of label sparsity, data imbalance, and object occlusion. By proposing various techniques, including a base model, reweighting and resampling techniques, a negative label expansion scheme, and a supervised attribute-aware contrastive learning algorithm, significant improvements have been achieved.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lvmin Zhang et al.
Summary: The deep learning framework presented in this study aims to assist artists in filling line arts with flat colors in a user-guided manner. The framework effectively controls the influence areas of user color scribbles to avoid color leakage, utilizing a Split Filling Mechanism and Convolutional Neural Network. With over a million illustrations as training data, the framework can estimate and generate visually pleasing colors to enhance the daily work of artists.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuqing Hu et al.
Summary: This paper proposes a novel transfer-based method for few-shot classification, which preprocesses feature vectors and utilizes an optimal-transport inspired algorithm to achieve state-of-the-art accuracy. The methodology is demonstrated to perform well across various datasets, backbone architectures, and few-shot settings on standardized vision benchmarks.
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II
(2021)
Article
Computer Science, Artificial Intelligence
Yuanfei Dai et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhao-Min Chen et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Wei Huang et al.
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19)
(2019)
Article
Engineering, Electrical & Electronic
Fei Wu et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2017)
Article
Computer Science, Information Systems
Siddharth Gopal et al.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Ning Zhang et al.
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2014)
Article
Mathematics, Applied
Helyane Bronoski Borges et al.
COMPUTERS & MATHEMATICS WITH APPLICATIONS
(2013)
Article
Computer Science, Artificial Intelligence
Carlos N. Silla et al.
DATA MINING AND KNOWLEDGE DISCOVERY
(2011)
