Object-Assisted Question Featurization and Multi-CNN Image Feature Fusion for Visual Question Answering

Article Computer Science, Artificial Intelligence

Learning joint relationship attention network for image captioning

Changzhi Wang et al.

Summary: This paper proposes a novel method for image captioning that generates complete and natural sentence descriptions of image content by exploring the relationships between image features. Experimental results demonstrate the superiority of this method compared to existing approaches both qualitatively and quantitatively.

EXPERT SYSTEMS WITH APPLICATIONS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

WTL-CNN: a news text classification method of convolutional neural network based on weighted word embedding

Weidong Zhao et al.

Summary: This paper proposes a method named WTL-CNN that combines word2vec, a topic-based TF-IDF algorithm, and an improved convolutional neural network to address the issue of word2vec model ignoring the importance of a single word. The WTL-CNN model has been evaluated and compared with seven contrast models, showing high accuracy in news text classification.

CONNECTION SCIENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multimodal feature-wise co-attention method for visual question answering

Sheng Zhang et al.

Summary: This paper introduces a novel neural network module named MulFA for feature-wise attention modeling, which shows promising experimental results in VQA. By introducing MulFA modules, an effective union feature-wise and spatial co-attention network UFSCAN model is constructed for VQA, achieving competitive performance with state-of-the-art models on VQA datasets.

INFORMATION FUSION (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Visual Question Answering with Textual Representations for Images

Yusuke Hirota et al.

Summary: This paper explores the effectiveness of textual representations for image understanding in the context of VQA. By comparing deep visual features with descriptive text, it reveals the potential advantages of textual representations in understanding images.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Re-Attention for Visual Question Answering

Wenya Guo et al.

Summary: In this paper, a re-attention framework is proposed to utilize answer information for describing visual contents in VQA. Experiments show that the proposed model performs favorably against state-of-the-art methods.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Geochemistry & Geophysics