AAAI 2021 accepted papers on Vision-language and multimodal
67 of the 1,654 papers accepted at AAAI 2021 (4.1%) are on Vision-language and multimodal, compared with 3.7% at AAAI 2020. They fall into 5 topics.
See AAAI 2021 in the interactive map
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 · 38 papers
- Similarity Reasoning and Filtration for Image-Text Matching (365 citations)
- ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs (220 citations)
- Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance (210 citations)
- Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network (183 citations)
- RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER (173 citations)
- Visual Pivoting for (Unsupervised) Entity Alignment (142 citations)
- Dual Compositional Learning in Interactive Image Retrieval (85 citations)
- Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution (73 citations)
- Learning Visual Context for Group Activity Recognition (71 citations)
- Humor Knowledge Enriched Transformer for Understanding Multimodal Humor (70 citations)
- Stratified Rule-Aware Network for Abstract Visual Reasoning (69 citations)
- LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching (53 citations)
and 26 more in the interactive map.
Cross-modal learning · 15 papers
- Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis (751 citations)
- SMIL: Multimodal Learning with Severely Missing Modality (297 citations)
- Deep Graph-neighbor Coherence Preserving Network for Unsupervised Cross-modal Hashing (197 citations)
- Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning (100 citations)
- Dual Adversarial Graph Neural Networks for Multi-label Cross-modal Retrieval (78 citations)
- Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition (67 citations)
- Robust Multi-Modality Person Re-identification (61 citations)
- Deep Mutual Information Maximin for Cross-Modal Clustering (58 citations)
- Enhancing Audio-Visual Association with Self-Supervised Curriculum Learning (22 citations)
- VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization (19 citations)
- Audio-Oriented Multimodal Machine Comprehension via Dynamic Inter- and Intra-modality Attention (16 citations)
- CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval (15 citations)
and 3 more in the interactive map.
Visual question answering · 10 papers
- Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering (115 citations)
- VisualMRC: Machine Reading Comprehension on Document Images (81 citations)
- Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering (72 citations)
- Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps (56 citations)
- Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation (42 citations)
- A Case Study of the Shortcut Effects in Visual Commonsense Reasoning (32 citations)
- TSQA: Tabular Scenario Based Question Answering (21 citations)
- HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions (20 citations)
- Regularizing Attention Networks for Anomaly Detection in Visual Question Answering (15 citations)
- REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement (8 citations)
