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 17 · SOTA2 Research
Back to Research
Research domain
Multimodal
Search tasks
Search
3 benchmarks · 13 papers
Text-to-Motion Synthesis
3 benchmarks · 1 papers
Image Caption Evaluation
3 benchmarks · 1 papers
Multiple-choice VQA
3 benchmarks · 2 papers
Text Image Translation
3 benchmarks · 4 papers
Audio-Visual Scene-Aware Dialog
3 benchmarks · 1 papers
Vision-Centric Understanding
3 benchmarks · 5 papers
Visual Math
3 benchmarks · 3 papers
Multimodal Machine Unlearning Evaluation
3 benchmarks · 3 papers
Multi-image Visual Question Answering
3 benchmarks · 1 papers
Multi-image Medical Visual Question Answering
3 benchmarks · 2 papers
HSI-MSI Fusion
3 benchmarks · 2 papers
MLLM-as-a-judge evaluation
3 benchmarks · 1 papers
Spatial-Temporal Reasoning
3 benchmarks · 3 papers
Vision-Language Perception and Reasoning
3 benchmarks · 1 papers
Selective Visual Question Answering
3 benchmarks · 2 papers
Multi-modal Vehicle Re-Identification
3 benchmarks · 3 papers
Downstream evaluation
3 benchmarks · 5 papers
Audio-visual event recognition
3 benchmarks · 1 papers
Video-to-IMU Retrieval
3 benchmarks · 3 papers
Cross-modal verification
3 benchmarks · 2 papers
Audio-visual speech separation and enhancement
3 benchmarks · 1 papers
IMU-to-Video Retrieval
3 benchmarks · 4 papers
Music Captioning
3 benchmarks · 2 papers
Category-level Sketch-Based Image Retrieval
3 benchmarks · 3 papers
Visual puzzle solving
3 benchmarks · 1 papers
Multi-image Multimodal Understanding
3 benchmarks · 1 papers
Weakly Supervised Grounding
3 benchmarks · 2 papers
T-to-V Retrieval
3 benchmarks · 3 papers
Multimodal Medical Question Answering
3 benchmarks · 1 papers
Novel-view Sound Synthesis
3 benchmarks · 1 papers
Audio-Image Retrieval
3 benchmarks · 1 papers
Grounded VQA
Page 17 of 83
Previous
Next