VLP: A Survey on Vision-Language Pre-training
arXiv:2202.09061 · doi:10.1007/s11633-022-1369-5
Abstract
In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey focused on VLP. We hope that this survey can shed light on future research in the VLP field.
arXiv commentA Survey on Vision-Language Pre-training
References in corpus (45)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Learning Transferable Visual Models From Natural Language Supervision
- A Survey on Visual Transformer
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- Pre-trained Models for Natural Language Processing: A Survey
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
- Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations
- ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
- Q8BERT: Quantized 8Bit BERT
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
- VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
- nocaps: novel object captioning at scale
- VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
- Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning
- Reducing Transformer Depth on Demand with Structured Dropout
- Visual Question Answering: Datasets, Algorithms, and Future Challenges
- Learning Video Representations using Contrastive Bidirectional Transformer
- You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
- Unifying Vision-and-Language Tasks via Text Generation
- UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
- Visual Entailment: A Novel Task for Fine-Grained Image Understanding
- ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data
- CLIP2Video: Mastering Video-Text Retrieval via Image CLIP
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
- Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions
- Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
- Fashion-Gen: The Generative Fashion Dataset and Challenge
- Multimodal Few-Shot Learning with Frozen Language Models
- DeVLBert: Learning Deconfounded Visio-Linguistic Representations
- InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
- Cascaded Revision Network for Novel Object Captioning
- Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
- OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
- Heterogeneous Graph Learning for Visual Commonsense Reasoning
- Visual Entailment Task for Visually-Grounded Language Learning
- Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
- Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning
- HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval
Cited by in corpus (7)
- Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review
- From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities
- Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
- Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detection
- AttriPrompter: Auto-Prompting with Attribute Semantics for Zero-shot Nuclei Detection via Visual-Language Pre-trained Models
- AI as a Tool for Fair Journalism: Case Studies from Malta
- Data-Driven Vision-Language Models for Remote Sensing: A Survey