# ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos

arXiv: https://arxiv.org/abs/2512.03666 · HTML: https://mlsanity.com/paper/2512.03666/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 45 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 30 of 41)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [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)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [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)
- [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)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning](https://mlsanity.com/paper/2503.11495/) (2025)
- [Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video](https://mlsanity.com/paper/1906.02549/) (2019)
- [LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2501.08282/) (2025)
- [A Survey: Learning Embodied Intelligence from Physical Simulators and World Models](https://mlsanity.com/paper/2507.00917/) (2025)
- [Context-Guided Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.01578/) (2024)
- [Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.00901/) (2023)

## Built on by (most cited first, 8 of 8)

- [EgoSound: Benchmarking Sound Understanding in Egocentric Videos](https://mlsanity.com/paper/2602.14122/) (2026)
- [VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification](https://mlsanity.com/paper/2604.01569/) (2026)
- [ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding](https://mlsanity.com/paper/2607.28312/) (2026)
- [Listening with the Eyes: Benchmarking Egocentric Co-Speech Grounding across Space and Time](https://mlsanity.com/paper/2603.07966/) (2026)
- [AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models](https://mlsanity.com/paper/2607.02269/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)
- [EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos](https://mlsanity.com/paper/2610.17128/) (2026)
- [EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions](https://mlsanity.com/paper/2610.18499/) (2026)

## Abstract (arXiv)

A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG). Despite recent progress, existing STVG studies remain largely confined to object-centric and descriptive instructions, neglecting the task-oriented reasoning that is crucial for embodied agents to accomplish goal-directed interactions. To bridge this gap, we introduce ToG-Bench, the first task-oriented spatio-temporal video grounding benchmark for egocentric videos. ToG-Bench is characterized by three key features: (1) Task-oriented Grounding, which requires identifying and localizing objects based on intended tasks rather than straightforward descriptions; (2) Explicit-Implicit Dual Grounding, where target objects can be either explicitly mentioned or implicitly inferred by contextual reasoning; (3) One-to-Many Grounding, where a single instruction may correspond to multiple objects involved in task execution. Built upon videos sourced from ScanNet, ToG-Bench comprises 100 annotated clips with 2,704 task-oriented grounding instructions, constructed via a semi-automated pipeline that combines foundation model annotation and human refinement. In addition, we introduce a set of task-level evaluation metrics tailored for multi-object and explicit-implicit object grounding, and systematically benchmark seven state-of-the-art MLLMs. Extensive experiments reveal the intrinsic challenges of task-oriented STVG and substantial performance gaps across explicit-implicit and multi-object grounding, highlighting the difficulty of bridging perception and interaction in embodied scenarios. Data and code will be released at: hrefhttps://github.com/qaxuDev/ToG-Benchhttps://github.com/qaxuDev/ToG-Bench..