AAAI 2023 accepted papers on Vision-language and multimodal
88 of the 2,023 papers accepted at AAAI 2023 (4.3%) are on Vision-language and multimodal, compared with 4.5% at AAAI 2022. They fall into 5 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 39 papers
- TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models (488 citations)
- RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL (178 citations)
- MNER-QG: An End-to-End MRC Framework for Multimodal Named Entity Recognition with Query Grounding (60 citations)
- MMTN: Multi-Modal Memory Transformer Network for Image-Report Consistent Medical Report Generation (51 citations)
- Controllable Image Captioning via Prompting (40 citations)
- BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation (38 citations)
- KnowGL: Knowledge Generation and Linking from Text (23 citations)
- Referring Expression Comprehension Using Language Adaptive Inference (23 citations)
- Hierarchical ConViT with Attention-Based Relational Reasoner for Visual Analogical Reasoning (19 citations)
- Uncertainty-Aware Image Captioning (18 citations)
- Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues (17 citations)
- On Analyzing the Role of Image for Visual-Enhanced Relation Extraction (Student Abstract) (17 citations)
and 27 more in the interactive map.
Cross-modal learning · 23 papers
- Bootstrapping Multi-View Representations for Fake News Detection (123 citations)
- M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities (93 citations)
- Mutual-Enhanced Incongruity Learning Network for Multi-Modal Sarcasm Detection (70 citations)
- BridgeTower: Building Bridges between Encoders in Vision-Language Representation Learning (64 citations)
- Towards Good Practices for Missing Modality Robust Action Recognition (60 citations)
- See How You Read? Multi-Reading Habits Fusion Reasoning for Multi-Modal Fake News Detection (58 citations)
- Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis (51 citations)
- Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval (37 citations)
- Efficient Image Captioning for Edge Devices (28 citations)
- Multi-Modal Knowledge Hypergraph for Diverse Image Retrieval (28 citations)
- Multi-Modality Deep Network for Extreme Learned Image Compression (23 citations)
- Leveraging Modality-Specific Representations for Audio-Visual Speech Recognition via Reinforcement Learning (21 citations)
and 11 more in the interactive map.
CLIP and zero-shot · 13 papers
- Exploring CLIP for Assessing the Look and Feel of Images (693 citations)
- CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels (301 citations)
- CALIP: Zero-Shot Enhancement of CLIP with Parameter-Free Attention (117 citations)
- Revisiting Classifier: Transferring Vision-Language Models for Video Recognition (100 citations)
- DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (81 citations)
- Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer (57 citations)
- Semantic-Enhanced Image Clustering (27 citations)
- NLIP: Noise-Robust Language-Image Pre-training (24 citations)
- Debiased Fine-Tuning for Vision-Language Models by Prompt Regularization (19 citations)
- Zero-Shot Cross-Lingual Event Argument Extraction with Language-Oriented Prefix-Tuning (7 citations)
- Few-Shot Composition Learning for Image Retrieval with Prompt Tuning (6 citations)
- Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models (2 citations)
and 1 more in the interactive map.
Visual question answering · 11 papers
- SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (56 citations)
- COCA: COllaborative CAusal Regularization for Audio-Visual Question Answering (22 citations)
- FiTs: Fine-Grained Two-Stage Training for Knowledge-Aware Question Answering (16 citations)
- HybridPrompt: Bridging Language Models and Human Priors in Prompt Tuning for Visual Question Answering (12 citations)
- MPMQA: Multimodal Question Answering on Product Manuals (11 citations)
- A Question-Answering Approach to Key Value Pair Extraction from Form-Like Document Images (10 citations)
- Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA (9 citations)
- SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph (7 citations)
- Improving the Cross-Lingual Generalisation in Visual Question Answering (5 citations)
- RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering (5 citations)
- Inferential Knowledge-Enhanced Integrated Reasoning for Video Question Answering (1 citation)