TPAMI 2023 papers on Vision-language and multimodal
33 of the 664 papers published in TPAMI 2023 (5.0%) are on Vision-language and multimodal, compared with 3.9% at TPAMI 2022. They fall into 6 topics.
See TPAMI 2023 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 · 11 papers
- Large Scale Visual Food Recognition (296 citations)
- DAN: A Segmentation-Free Document Attention Network for Handwritten Document Recognition (151 citations)
- Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features (151 citations)
- Automatic Gaze Analysis: A Survey of Deep Learning Based Approaches (132 citations)
- TransVG++: End-to-End Visual Grounding With Language Conditioned Vision Transformer (107 citations)
- Context Disentangling and Prototype Inheriting for Robust Visual Grounding (56 citations)
- Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition (37 citations)
- Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval (35 citations)
- Image Captioning With Controllable and Adaptive Length Levels (23 citations)
- Measuring Human Perception to Improve Open Set Recognition (14 citations)
- Still an Ineffective Method With Supertrials/ERPs—Comments on “Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features” (9 citations)
Cross-modal learning · 6 papers
- MURF: Mutually Reinforcing Multi-Modal Image Registration and Fusion (312 citations)
- Cross-Modal Retrieval With Partially Mismatched Pairs (116 citations)
- COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition (81 citations)
- Deep M2CDL: Deep Multi-Scale Multi-Modal Convolutional Dictionary Learning Network (44 citations)
- A Unified Multimodal De- and Re-Coupling Framework for RGB-D Motion Recognition (39 citations)
- Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval (14 citations)
Visual question answering · 5 papers
- Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering (377 citations)
- Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering (57 citations)
- Knowledge-Based Embodied Question Answering (45 citations)
- Transformer-Empowered Invariant Grounding for Video Question Answering (17 citations)
- NExT-OOD: Overcoming Dual Multiple-Choice VQA Biases (15 citations)
Multimodal LLMs · 5 papers
- Multimodal Image Synthesis and Editing: The Generative AI Era (197 citations)
- Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding (74 citations)
- Making a Bird AI Expert Work for You and Me (22 citations)
- PiGLET: Pixel-Level Grounding of Language Expressions With Transformers (9 citations)
- Visual Reasoning: From State to Transformation (9 citations)
CLIP and zero-shot · 4 papers
- X2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks (123 citations)
- DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations (42 citations)
- Universal Multimodal Representation for Language Understanding (39 citations)
- Enhancing Visual Grounding in Vision-Language Pre-Training With Position-Guided Text Prompts (17 citations)
