# VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration

arXiv: https://arxiv.org/abs/2609.21521 · HTML: https://mlsanity.com/paper/2609.21521/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding](https://mlsanity.com/paper/2406.14515/) (2024)
- [Kwai Keye-VL 1.5 Technical Report](https://mlsanity.com/paper/2509.01563/) (2025)
- [CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness](https://mlsanity.com/paper/2502.14914/) (2025)
- [VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation](https://mlsanity.com/paper/2505.14640/) (2025)
- [Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?](https://mlsanity.com/paper/2505.14321/) (2025)
- [ALLVB: All-in-One Long Video Understanding Benchmark](https://mlsanity.com/paper/2503.07298/) (2025)
- [TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs](https://mlsanity.com/paper/2602.00288/) (2026)
- [TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos](https://mlsanity.com/paper/2505.20124/) (2025)
- [HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning](https://mlsanity.com/paper/2511.20515/) (2025)
- [NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding](https://mlsanity.com/paper/2601.01095/) (2026)

## Abstract (arXiv)

While Video Large Language Models (Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained video understanding remains challenging. Existing benchmarks often rely on question answering or ground-truth caption matching, where models may succeed through superficial cues and incomplete annotations. To this end, we introduce VidOmni-Bench, a benchmark that requires models to verify whether each event in dense video captions is supported by the video. VidOmni-Bench consists of 500 videos spanning five complexity types and diverse durations from 4 seconds to 90 minutes. After collecting videos along these axes, we use diverse Video-LLMs to generate dense captions and obtain human-verified sentence-level labels, where sentences containing incorrect events serve as hard negatives for evaluation. Our experiments on VidOmni-Bench reveal three key findings: (i) Video-LLMs frequently generate hallucinated descriptions in dense video captioning; (ii) they also struggle as verifiers, failing to reliably detect plausible but incorrect event descriptions; and (iii) model weaknesses vary across video complexity and duration, revealing diverse, model-specific bottlenecks in current Video-LLMs.