ICLR 2022 accepted papers on Vision-language and multimodal
21 of the 1,095 papers accepted at ICLR 2022 (1.9%) are on Vision-language and multimodal, compared with 1.5% at ICLR 2021. They fall into 5 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 10 papers
- BEiT: BERT Pre-Training of Image Transformers (915 citations)
- Perceiver IO: A General Architecture for Structured Inputs & Outputs (205 citations)
- Domino: Discovering Systematic Errors with Cross-Modal Embeddings (38 citations)
- Natural Language Descriptions of Deep Visual Features (17 citations)
- Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream (12 citations)
- FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations (6 citations)
- Language-biased image classification: evaluation based on semantic representations (2 citations)
- Mapping Language Models to Grounded Conceptual Spaces
- RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
- Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling
CLIP and zero-shot · 6 papers
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision (338 citations)
- FILIP: Fine-grained Interactive Language-Image Pre-Training (205 citations)
- How Much Can CLIP Benefit Vision-and-Language Tasks? (150 citations)
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm (128 citations)
- HTLM: Hyper-Text Pre-Training and Prompting of Language Models (32 citations)
- Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation (14 citations)
Cross-modal learning · 2 papers
Visual question answering · 2 papers
- EntQA: Entity Linking as Question Answering (24 citations)
- Measuring CLEVRness: Black-box Testing of Visual Reasoning Models (1 citation)
