Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
WizWand is now SOTA2 Research
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
Multimodal AI research – Page 26 · SOTA2 Research
Back to Research
Research domain
Multimodal
Search tasks
Search
2 benchmarks · 5 papers
Video Referring Segmentation
2 benchmarks · 1 papers
Multi-modal Response Generation
2 benchmarks · 12 papers
Multimodal Visual Perception
2 benchmarks · 2 papers
Long-context Multimodal Understanding
2 benchmarks · 1 papers
Multi-modal Dialog State Tracking
2 benchmarks · 1 papers
Multimodal Medical Image Segmentation
2 benchmarks · 1 papers
Multimodal Reasoning and Mathematics
2 benchmarks · 1 papers
Multi-interleaved Image-Text Retrieval
2 benchmarks · 1 papers
General Multimodal Question Answering
2 benchmarks · 2 papers
Visual Query Localization
2 benchmarks · 2 papers
Multimodal Video Retrieval
2 benchmarks · 1 papers
Visual Goal Generation
2 benchmarks · 1 papers
Crossmodal retrieval
2 benchmarks · 1 papers
Vision-Language Captioning
2 benchmarks · 1 papers
Audio-driven Digital Human Generation
2 benchmarks · 1 papers
Closed-ended Visual Question Answering
2 benchmarks · 3 papers
Multi-modal sarcasm detection
2 benchmarks · 1 papers
Medical Multi-discipline Multimodal Understanding
2 benchmarks · 1 papers
Modality Preference Steering
2 benchmarks · 4 papers
Direct Answer Visual Question Answering
2 benchmarks · 1 papers
QA performance by Gemini-2.5-Pro based on captions
2 benchmarks · 1 papers
Multimodal Learning
2 benchmarks · 1 papers
7-class emotion recognition
2 benchmarks · 1 papers
Universal multi-modal reasoning
2 benchmarks · 1 papers
Multi-modal Image-to-Image Translation
2 benchmarks · 2 papers
Music Question Answering
2 benchmarks · 1 papers
AV-ASR
2 benchmarks · 7 papers
Fine-Grained Sketch-Based Image Retrieval (FG-SBIR)
2 benchmarks · 4 papers
text-conditioned human interaction generation
2 benchmarks · 1 papers
Multi-modal preference alignment
2 benchmarks · 2 papers
Music Conditioned Dance Generation
2 benchmarks · 1 papers
Sketch-to-Real Person Re-identification
Page 26 of 83
Previous
Next