# OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios

arXiv: https://arxiv.org/abs/2511.16937 · HTML: https://mlsanity.com/paper/2511.16937/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models](https://mlsanity.com/paper/2407.12772/) (2024)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models](https://mlsanity.com/paper/2404.13013/) (2024)
- [Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences](https://mlsanity.com/paper/2001.06891/) (2020)
- [GroundingGPT:Language Enhanced Multi-modal Grounding Model](https://mlsanity.com/paper/2401.06071/) (2024)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [TRACE: Temporal Grounding Video LLM via Causal Event Modeling](https://mlsanity.com/paper/2410.05643/) (2024)
- [Human-centric Spatio-Temporal Video Grounding With Visual Transformers](https://mlsanity.com/paper/2011.05049/) (2020)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2501.08282/) (2025)
- [Context-Guided Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.01578/) (2024)
- [Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2209.13306/) (2022)
- [Capabilities of GPT-5 on Multimodal Medical Reasoning](https://mlsanity.com/paper/2508.08224/) (2025)
- [SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability](https://mlsanity.com/paper/2503.13983/) (2025)
- [Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2502.11168/) (2025)

## Built on by (most cited first, 5 of 5)

- [Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes](https://mlsanity.com/paper/2602.00593/) (2026)
- [AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models](https://mlsanity.com/paper/2607.02269/) (2026)
- [ID-VTG: Image-Disambiguated Video Temporal Grounding](https://mlsanity.com/paper/2608.20127/) (2026)
- [Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum](https://mlsanity.com/paper/2608.30584/) (2026)
- [OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding](https://mlsanity.com/paper/2610.18829/) (2026)

## Abstract (arXiv)

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. We attribute this to limited benchmark scope, causing models to exhibit category bias, oversimplified reasoning, and poor linguistic robustness. To address these limitations, we introduce OmniGround, a comprehensive benchmark with 3,475 videos spanning 81 categories and complex real-world queries. We propose the Forward-Backward-Refinement annotation pipeline that combines multi-directional tracking with intelligent error correction for high-quality labels. We further introduce DeepSTG, a systematic evaluation framework quantifying dataset quality across four complementary dimensions beyond superficial statistics. Evaluations reveal performance average drop of 10.4% on complex real-world scenes, particularly with small/occluded objects and intricate spatial relations. Motivated by these, we propose PG-TAF, a training-free two-stage framework decomposing STVG into high-level temporal grounding and fine-grained spatio-temporal propagation. Experiments demonstrate PG-TAF achieves 25.6% and 35.6% improvements in mtIoU and mvIoU on OmniGround with consistent gains across four benchmarks.