# Hulk: A Universal Knowledge Translator for Human-Centric Tasks

arXiv: https://arxiv.org/abs/2312.01697 · HTML: https://mlsanity.com/paper/2312.01697/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 136 of its 191 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Builds on (most cited first, 30 of 136)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)

## Built on by (most cited first, 22 of 22)

- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data](https://mlsanity.com/paper/2412.01383/) (2024)
- [Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants](https://mlsanity.com/paper/2501.01243/) (2025)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation](https://mlsanity.com/paper/2409.06535/) (2024)
- [HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding](https://mlsanity.com/paper/2410.06777/) (2024)
- [Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2404.17929/) (2024)
- [MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition](https://mlsanity.com/paper/2404.10210/) (2024)
- [CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition](https://mlsanity.com/paper/2410.07153/) (2024)
- [iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning](https://mlsanity.com/paper/2605.17179/) (2026)
- [Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle](https://mlsanity.com/paper/2412.01562/) (2024)
- [RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios](https://mlsanity.com/paper/2412.14643/) (2024)
- [Heatmap Pooling Network for Action Recognition from RGB Videos](https://mlsanity.com/paper/2512.03837/) (2025)
- [Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2512.22214/) (2025)
- [GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems](https://mlsanity.com/paper/2603.20310/) (2026)
- [FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World](https://mlsanity.com/paper/2509.16674/) (2025)
- [HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation](https://mlsanity.com/paper/2511.00468/) (2025)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)
- [Skarimva: Skeleton-based Action Recognition is a Multi-view Application](https://mlsanity.com/paper/2602.23231/) (2026)
- [Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition](https://mlsanity.com/paper/2604.17090/) (2026)
- [STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition](https://mlsanity.com/paper/2607.17342/) (2026)
- [Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates](https://mlsanity.com/paper/2608.21160/) (2026)

## Abstract (arXiv)

Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, they did not explore 3D and vision-language tasks for human-centric and required task-specific finetuning. These limitations restrict their application to more downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat diverse human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. Comprehensive evaluations of Hulk on 12 benchmarks covering 8 human-centric tasks demonstrate the superiority of our proposed method, achieving state-of-the-art performance in 11 benchmarks. The code will be available on https://github.com/OpenGVLab/Hulk.