TRINITY Benchmark

What is TRINITY?

Evaluates video highlight detection across three perspectives—Event, Emotion, and Nature—using precomputed CLIP features and corresponding annotations.

Released

2026-08-30

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.29577

TRINITY paper, code and dataset

• Paper https://arxiv.org/abs/2608.29577
• Code https://github.com/vanilladucky/TRINITY
• Dataset https://huggingface.co/datasets/vanilladucky/TRINITY

Which sources cite TRINITY?

• TRINITY

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench