Benchmark RadarAI BENCHMARK PROFILE
Inter-X++
Large-scale benchmark with 11,388 interaction sequences for multimodal human-human interaction analysis, covering four task categories in generation and perception.
- Released
- 2026-08-20
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Provides standardized representations and evaluation protocols for human-human interaction, enabling fair comparison across generative and perceptive models.
Motivation
The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.