Multimodal Deep Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 1
Multimodal deep learning is a type of deep learning that combines information from multiple modalities, such as text, image, audio, and video, to make more accurate and comprehensive predictions. It involves training deep neural networks on data that includes multiple types of information and using the network to make predictions based on this combined data.
One of the key challenges in multimodal deep learning is how to effectively combine information from multiple modalities. This can be done using a variety of techniques, such as fusing the features extracted from each modality, or using attention mechanisms to weight the contribution of each modality based on its importance for the task at hand.
Multimodal deep learning has many applications, including image captioning, speech recognition, natural language processing, and autonomous vehicles. By combining information from multiple modalities, multimodal deep learning can improve the accuracy and robustness of models, enabling them to perform better in real-world scenarios where multiple types of information are present.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery
MalFake: A Multimodal Fake News Identification for Malayalam using Recurrent Neural Networks and VGG-16
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
HyMNet: a Multimodal Deep Learning System for Hypertension Classification using Fundus Photographs and Cardiometabolic Risk Factors
Multimodal Deep Learning for Scientific Imaging Interpretation
A multimodal deep learning architecture for smoking detection with a small data approach
Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices
Formalizing Multimedia Recommendation through Multimodal Deep Learning
Multimodal Guidance Network for Missing-Modality Inference in Content Moderation
Multimodal Foundation Models For Echocardiogram Interpretation
On the Adversarial Robustness of Multi-Modal Foundation Models
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
ARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal Methods Boosted by Ensemble Learning, Syntactical and Entity Features
A scoping review on multimodal deep learning in biomedical images and texts
Multimodal Deep Learning for Personalized Renal Cell Carcinoma Prognosis: Integrating CT Imaging and Clinical Data
A Novel Site-Agnostic Multimodal Deep Learning Model to Identify Pro-Eating Disorder Content on Social Media
MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning
Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning
Towards Balanced Active Learning for Multimodal Classification
ImageBind: One Embedding Space To Bind Them All
Multimodal Neural Databases
Open-World Social Event Classification
Performance Optimization using Multimodal Modeling and Heterogeneous GNN
Building Multimodal AI Chatbots
Towards Unified AI Drug Discovery with Multiple Knowledge Modalities
P-Transformer: A Prompt-based Multimodal Transformer Architecture For Medical Tabular Data
A Comprehensive and Versatile Multimodal Deep Learning Approach for Predicting Diverse Properties of Advanced Materials
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Multimodal Deep Learning to Differentiate Tumor Recurrence from Treatment Effect in Human Glioblastoma
Show me your NFT and I tell you how it will perform: Multimodal representation learning for NFT selling price prediction
Zorro: the masked multimodal transformer
Multimodal Deep Learning
Learning Multimodal Data Augmentation in Feature Space
Common Practices and Taxonomy in Deep Multi-view Fusion for Remote Sensing Applications
Medical Diagnosis with Large Scale Multimodal Transformers: Leveraging Diverse Data for More Accurate Diagnosis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.