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 2 · SOTA2 Research
Back to Research
Research domain
Multimodal
Search tasks
Search
47 benchmarks · 25 papers
Spatial Understanding
46 benchmarks · 72 papers
Multi-modal Understanding
45 benchmarks · 28 papers
Image Understanding
45 benchmarks · 25 papers
Captioning
44 benchmarks · 80 papers
Visual Perception
42 benchmarks · 46 papers
Audio-Visual Question Answering
42 benchmarks · 40 papers
Text-to-Audio Retrieval
42 benchmarks · 131 papers
Document Visual Question Answering
40 benchmarks · 28 papers
Audio Question Answering
39 benchmarks · 20 papers
General VQA
39 benchmarks · 33 papers
Visual Understanding
37 benchmarks · 70 papers
Visual Mathematical Reasoning
36 benchmarks · 20 papers
General Visual Question Answering
35 benchmarks · 39 papers
Multimodal Perception
33 benchmarks · 20 papers
Content Moderation
33 benchmarks · 30 papers
Multimodal Emotion Recognition
32 benchmarks · 20 papers
Self-Reenactment
31 benchmarks · 20 papers
Vision-Language Reasoning
31 benchmarks · 22 papers
Video Moment Retrieval
31 benchmarks · 18 papers
Object Hallucination Detection
30 benchmarks · 1 papers
Temporal OOD Detection
29 benchmarks · 23 papers
Scene Graph Detection
27 benchmarks · 32 papers
Vision-Language Understanding
27 benchmarks · 38 papers
Video Grounding
27 benchmarks · 18 papers
Spatio-Temporal Video Grounding
27 benchmarks · 31 papers
Knowledge-based Visual Question Answering
25 benchmarks · 15 papers
Multimodal Search
25 benchmarks · 17 papers
Utility Evaluation
24 benchmarks · 4 papers
Multimodal Time Series Forecasting
23 benchmarks · 6 papers
Visual Attribution
23 benchmarks · 43 papers
Multi-modal Reasoning
22 benchmarks · 18 papers
Multi-image Understanding
Page 2 of 83
Previous
Next