Multimodal Intent Recognition
8 papers with code • 3 benchmarks • 3 datasets
Intent recognition on multimodal content.
Image source: MIntRec: A New Dataset for Multimodal Intent Recognition
Libraries
Use these libraries to find Multimodal Intent Recognition models and implementations
PhotoChat
MMDialog
MIntRec
Most implemented papers
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
google-research/bert
•
•
NAACL 2019
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
google-research/ALBERT
•
•
ICLR 2020
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
huggingface/transformers
•
•
arXiv 2019
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
dandelin/vilt
•
•
Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks.
MIntRec: A New Dataset for Multimodal Intent Recognition
thuiar/mintrec
•
•
This paper introduces a novel dataset for multimodal intent recognition (MIntRec) to address this issue.
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x.
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
alibabaresearch/damo-convai
•
•
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
AlibabaResearch/DAMO-ConvAI
•
•
It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data.
