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
Chunbin Gu et al.
Summary: This paper addresses the issue of cross-modal image retrieval through a new approach based on contrastive self-supervised learning methods to bridge the gap between modalities. The experiments demonstrate that the method achieves state-of-the-art retrieval performance on three large-scale benchmarks.
Article
Computer Science, Artificial Intelligence
Xu Yang et al.
Summary: This study proposes a novel approach for domain adaptation in the context of one labeled source domain and multiple unlabeled target domains. By employing deep semantic information propagation and a graph attention network, the method is able to conduct semantic propagation among multiple target domains and learn a unified subspace that is applicable to all domains. The results show that this approach outperforms other domain adaptation methods on multiple public datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Hao Wang et al.
Summary: This study proposes a novel approach for zero-shot sketch-based image retrieval, which improves the transferability of networks and introduces a learning strategy that combines coupled modules and independent modules. The approach achieves significant improvements in retrieval accuracy.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Automation & Control Systems
Kun Wei et al.
Summary: The goal of zero-shot learning is to recognize unseen classes without corresponding training samples. However, existing methods are not suitable for incrementally collected training data. Therefore, a novel approach called Incremental ZSL (IZSL) is introduced to accumulate historical knowledge and alleviate Catastrophic Forgetting to improve recognition in incremental training.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Fuxiang Huang et al.
Summary: This study introduces a new unsupervised hashing method for learning domain-invariant hashing representation to improve performance in unconstrained cross-domain visual retrieval. Experimental results demonstrate that the method outperforms many state-of-the-art hashing methods in both single- and cross-domain scenarios.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Guillaume Couairon et al.
Summary: FlexIT is a novel image editing method that allows editing of any input image with a user-defined text instruction, achieving flexible and natural editing through iterative transformations.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Akshay Chaturvedi et al.
Summary: Proposed a task-agnostic adversarial attack MaF that can mimic the image feature of the original image in computer vision tasks, achieving high success rates on different models. Additionally, showed the applicability of the attack for invertible architecture.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Wentao Jiang et al.
Summary: This paper focuses on the task of language-guided global image editing, proposing a method that creates a cycle with an image generator and utilizes the Editing Description Network (EDNet) model to predict editing embeddings. By introducing free augmentation strategies, the Image-Request Attention (IRA) module, and a new evaluation metric, it successfully addresses the issues of understanding language requests and handling imbalanced datasets present in existing approaches.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuxin Hou et al.
Summary: The research focuses on the issue of semantic disentanglement in interactive fashion retrieval, proposing a method that utilizes the semantics of attributes to train convolutional networks for obtaining disentangled representations. This approach demonstrates excellent performance in varying retrieval tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Sanghyuk Chun et al.
Summary: Cross-modal retrieval methods aim to build a common representation space for samples from different modalities, such as vision and language. This paper introduces Probabilistic Cross-Modal Embedding (PCME) to represent samples as probabilistic distributions, showing improved retrieval performance and providing uncertainty estimates for better interpretability. By evaluating on the CUB dataset with exhaustive annotations, PCME outperforms deterministic methods in capturing one-to-many correspondences.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Peng Hu et al.
Summary: This paper proposes a general Multimodal Robust Learning framework (MRL) to learn with multimodal noisy labels and mitigate noisy samples while correlating different modalities. The Robust Clustering loss (RC) is introduced to focus on clean samples instead of noisy ones, and the Multimodal Contrastive loss (MC) aims to maximize mutual information between different modalities to alleviate the interference of noisy samples and cross-modal discrepancy. Extensive experiments on four widely-used multimodal datasets show the effectiveness of the proposed approach compared to 14 state-of-the-art methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Computer Science, Artificial Intelligence
Yanhua Yang et al.
Summary: In this article, a new method for text-to-image synthesis called MA-GAN is proposed to improve generation quality and ensure generation similarity of related sentences by exploring semantic correlation between different sentences describing the same image. The MA-GAN outperforms state-of-the-art methods in extensive experiments on Oxford-102 and CUB datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Muhammad Umer Anwaar et al.
Summary: This paper investigates the problem of retrieving images from a database based on a multi-modal (image-text) query, and proposes an autoencoder based model, ComposeAE. By adopting deep metric learning and rotational symmetry constraint, our approach outperforms the state-of-the-art method TIRG on three benchmark datasets.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Jingkuan Song et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Review
Biochemical Research Methods
Elnaz Lashgari et al.
JOURNAL OF NEUROSCIENCE METHODS
(2020)
Article
Engineering, Electrical & Electronic
Ryo Takahashi et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuming Shen et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Information Systems
Bita Darvish Rouhani et al.
IEEE SECURITY & PRIVACY
(2019)
Article
Computer Science, Information Systems
Yangyang Guo et al.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2019)
Article
Computer Science, Theory & Methods
Connor Shorten et al.
JOURNAL OF BIG DATA
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Shupeng Su et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Aron Yu et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Xintong Han et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Computer Science, Artificial Intelligence
Shai Ben-David et al.