# F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

arXiv: https://arxiv.org/abs/2407.12435 · HTML: https://mlsanity.com/paper/2407.12435/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 94 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 30 of 76)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [Text-to-3D using Gaussian Splatting](https://mlsanity.com/paper/2309.16585/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)

## Built on by (most cited first, 24 of 24)

- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2509.09555/) (2025)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations](https://mlsanity.com/paper/2505.02094/) (2025)
- [Guiding Human-Object Interactions with Rich Geometry and Relations](https://mlsanity.com/paper/2503.20172/) (2025)
- [TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions](https://mlsanity.com/paper/2412.06334/) (2024)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions](https://mlsanity.com/paper/2503.15898/) (2025)
- [HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance](https://mlsanity.com/paper/2506.07209/) (2025)
- [Unleashing Guidance Without Classifiers for Human-Object Interaction Animation](https://mlsanity.com/paper/2603.25734/) (2026)
- [KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension](https://mlsanity.com/paper/2411.01846/) (2024)
- [HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception](https://mlsanity.com/paper/2506.01579/) (2025)
- [ECHO: Ego-Centric modeling of Human-Object interactions](https://mlsanity.com/paper/2508.21556/) (2025)
- [Decoupled Generative Modeling for Human-Object Interaction Synthesis](https://mlsanity.com/paper/2512.19049/) (2025)
- [ViHOI: Human-Object Interaction Synthesis with Visual Priors](https://mlsanity.com/paper/2603.24383/) (2026)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning](https://mlsanity.com/paper/2503.00382/) (2025)
- [GIRAF: Towards Generalizable Human Interactions with Articulated Objects](https://mlsanity.com/paper/2607.07880/) (2026)
- [KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model](https://mlsanity.com/paper/2507.11102/) (2025)
- [BRIC: Bridging Kinematic Plans and Physical Control at Test Time](https://mlsanity.com/paper/2511.20431/) (2025)
- [DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation](https://mlsanity.com/paper/2601.05844/) (2026)
- [Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D](https://mlsanity.com/paper/2603.12126/) (2026)
- [Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics](https://mlsanity.com/paper/2606.22806/) (2026)
- [LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction](https://mlsanity.com/paper/2609.19688/) (2026)

## Abstract (arXiv)

Existing 3D human object interaction (HOI) datasets and models simply align global descriptions with the long HOI sequence, while lacking a detailed understanding of intermediate states and the transitions between states. In this paper, we argue that fine-grained semantic alignment, which utilizes state-level descriptions, offers a promising paradigm for learning semantically rich HOI representations. To achieve this, we introduce Semantic-HOI, a new dataset comprising over 20K paired HOI states with fine-grained descriptions for each HOI state and the body movements that happen between two consecutive states. Leveraging the proposed dataset, we design three state-level HOI tasks to accomplish fine-grained semantic alignment within the HOI sequence. Additionally, we propose a unified model called F-HOI, designed to leverage multimodal instructions and empower the Multi-modal Large Language Model to efficiently handle diverse HOI tasks. F-HOI offers multiple advantages: (1) It employs a unified task formulation that supports the use of versatile multimodal inputs. (2) It maintains consistency in HOI across 2D, 3D, and linguistic spaces. (3) It utilizes fine-grained textual supervision for direct optimization, avoiding intricate modeling of HOI states. Extensive experiments reveal that F-HOI effectively aligns HOI states with fine-grained semantic descriptions, adeptly tackling understanding, reasoning, generation, and reconstruction tasks.