# HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation

arXiv: https://arxiv.org/abs/2503.23715 · HTML: https://mlsanity.com/paper/2503.23715/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Action Genome: Actions as Composition of Spatio-temporal Scene Graphs](https://mlsanity.com/paper/1912.06992/) (2019)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [COUCH: Towards Controllable Human-Chair Interactions](https://mlsanity.com/paper/2205.00541/) (2022)
- [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://mlsanity.com/paper/2303.14717/) (2023)
- [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://mlsanity.com/paper/2202.10304/) (2022)
- [InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction](https://mlsanity.com/paper/2209.12354/) (2022)
- [Compositional Human-Scene Interaction Synthesis with Semantic Control](https://mlsanity.com/paper/2207.12824/) (2022)
- [ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation](https://mlsanity.com/paper/2406.18522/) (2024)

## Built on by (most cited first, 26 of 26)

- [DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers](https://mlsanity.com/paper/2506.10568/) (2025)
- [FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion](https://mlsanity.com/paper/2507.00162/) (2025)
- [First Frame Is the Place to Go for Video Content Customization](https://mlsanity.com/paper/2511.15700/) (2025)
- [MV-S2V: Multi-View Subject-Consistent Video Generation](https://mlsanity.com/paper/2601.17756/) (2026)
- [Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework](https://mlsanity.com/paper/2606.19073/) (2026)
- [Generating Human Motion Videos using a Cascaded Text-to-Video Framework](https://mlsanity.com/paper/2510.03909/) (2025)
- [MATRIX: Mask Track Alignment for Interaction-aware Video Generation](https://mlsanity.com/paper/2510.07310/) (2025)
- [VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification](https://mlsanity.com/paper/2512.09646/) (2025)
- [TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection](https://mlsanity.com/paper/2512.10652/) (2025)
- [Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2601.04068/) (2026)
- [HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2607.17097/) (2026)
- [InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos](https://mlsanity.com/paper/2509.00767/) (2025)
- [Plan-X: Instruct Video Generation via Semantic Planning](https://mlsanity.com/paper/2511.17986/) (2025)
- [CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation](https://mlsanity.com/paper/2604.19636/) (2026)
- [VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model](https://mlsanity.com/paper/2602.09638/) (2026)
- [RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation](https://mlsanity.com/paper/2605.26241/) (2026)
- [StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation](https://mlsanity.com/paper/2607.20174/) (2026)
- [PhiZero: A World Model Built Around Physical Language](https://mlsanity.com/paper/2607.28624/) (2026)
- [SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2511.19319/) (2025)
- [FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning](https://mlsanity.com/paper/2606.19408/) (2026)
- [MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning](https://mlsanity.com/paper/2508.04549/) (2025)
- [ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization](https://mlsanity.com/paper/2606.14972/) (2026)
- [Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models](https://mlsanity.com/paper/2606.20233/) (2026)
- [SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation](https://mlsanity.com/paper/2607.05994/) (2026)
- [Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality](https://mlsanity.com/paper/2609.27493/) (2026)
- [Bootstrapping Video Interaction Generation with Synthetic State Transitions](https://mlsanity.com/paper/2610.01039/) (2026)

## Abstract (arXiv)

Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI. To address this issue, we introduce HOIGen-1M, the first largescale dataset for HOI Generation, consisting of over one million high-quality videos collected from diverse sources. In particular, to guarantee the high quality of videos, we first design an efficient framework to automatically curate HOI videos using the powerful multimodal large language models (MLLMs), and then the videos are further cleaned by human annotators. Moreover, to obtain accurate textual captions for HOI videos, we design a novel video description method based on a Mixture-of-Multimodal-Experts (MoME) strategy that not only generates expressive captions but also eliminates the hallucination by individual MLLM. Furthermore, due to the lack of an evaluation framework for generated HOI videos, we propose two new metrics to assess the quality of generated videos in a coarse-to-fine manner. Extensive experiments reveal that current T2V models struggle to generate high-quality HOI videos and confirm that our HOIGen-1M dataset is instrumental for improving HOI video generation. Project webpage is available at https://liuqi-creat.github.io/HOIGen.github.io.