ViCAN: Co-attention network for Vietnamese visual question answering

Số trang: 7 Loại file: pdf Dung lượng: 534.66 KB Lượt xem: 19 Lượt tải: 0

tailieu_vip

Báo xấu

Xem trước 2 trang đầu tiên của tài liệu này:

Thông tin tài liệu:

In recent years, the task of Visual Question Answering (VQA) has evolved into a very attractive research field. Normally, this task requires a simultaneous understanding of both the visual content of the image and the textual content of the question.
Nội dung trích xuất từ tài liệu:
ViCAN: Co-attention network for Vietnamese visual question answering

Tìm kiếm theo từ khóa liên quan:

Visual question answering Multimodal learning Attention-based learning Co-attention learning Deep learning Text modalities

Tài liệu có liên quan:

Ensemble of convolution neural networks for improving automatic modulation classification performance

8 trang 235 0 0
Application of convolutional neural network for detecting concrete cracks

4 trang 45 0 0
Improving hand posture recognition performance using multi-modalities

10 trang 40 0 0
EPSILON-CP: Using deep learning to combine information from multiple sources for protein contact prediction

11 trang 38 0 0
Modern approaches in natural language processing

25 trang 38 0 0
Application of convolution neural network in design and fabrication of robots for transporting goods in factories

8 trang 37 0 0
Luận văn tốt nghiệp Công nghệ thống tin: Xây dựng hệ thống nhận dạng kiểm soát khuôn mặt với Deep Learning

91 trang 35 0 0
Correlation between AI-based CT organ features and normal lung dose in adjuvant radiotherapy following breast-conserving surgery: A multicenter prospective study

8 trang 35 0 0
Research on traffic congestion detection from camera images in a location of Da Lat

13 trang 34 0 0
LSTM for human activity recognition based on feature extraction method using conformal geometric algebra

7 trang 33 0 0