Research map / Video / Video-language understanding
MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX
Liuyue Xie, Avik Kuthiala, George Z Wei, Ce Zheng, Ananya Bal, Mosam Dabhi, Liting Wen, Taru Rustagi, Ethan Lai, Sushil Khyalia, Rohan Choudhury, Morteza Ziyadi and 3 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add audio to video input | Ola-7B · MAVERIX MCQ | accuracy (%): 37.6 -> 53.1 | Improved |
| add audio to video input | Qwen 2.5 Omni · MAVERIX MCQ | accuracy (%): 35.4 -> 49.5 | Improved |
| add audio to video input | Gemini 2.0-FL · MAVERIX MCQ | accuracy (%): 42.1 -> 50.2 | Improved |
| add audio to video input | VITA 1.5 · MAVERIX MCQ | accuracy (%): 20.2 -> 18.5 | Hurt |
| add audio to video input | Human · MAVERIX MCQ | accuracy (%): 81.4 -> 92.8 | Improved |
| add subtitles to video input | Claude Sonnet 3.5 · MAVERIX MCQ | accuracy (%): 42.0 -> 64.1 | Improved |
| add subtitles to video input | GPT-4o · MAVERIX MCQ | accuracy (%): 54.3 -> 64.0 | Improved |
| add subtitles to video input | Gemini 2.0-FL · MAVERIX MCQ | accuracy (%): 42.1 -> 41.1 | No clear effect |
| add subtitles to video input | VITA 1.5 · MAVERIX MCQ | accuracy (%): 20.2 -> 22.3 | Improved |
| add audio to video on easy vs hard questions | Gemini 2.0-FL · MAVERIX MCQ by difficulty | accuracy (%): +12.4% on easy items and +3.3% on hard items | Mixed |
| add audio to video on hard questions | Ola-7B · MAVERIX MCQ hard split | accuracy (%): 41.7 -> 41.1 | No clear effect |
| use localized clips instead of full-length videos | MLLMs · MAVERIX vs MAVERIX-Long | accuracy (%) | Improved |
Closest papers by meaning
- MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos (NeurIPS 2026 · similarity 0.89)
- MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models (ICLR 2025 · similarity 0.89)
- HAVE-Bench: Hierarchical Audio-Visual Evaluation from Perception to Interaction (CVPR 2026 · similarity 0.88)
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis (CVPR 2025 · similarity 0.88)
- JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation (ICLR 2026 · similarity 0.88)
- MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
