# CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2411.06869 · HTML: https://mlsanity.com/paper/2411.06869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2012.15175/) (2020)
- [Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs](https://mlsanity.com/paper/2404.07449/) (2024)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [Lenna: Language Enhanced Reasoning Detection Assistant](https://mlsanity.com/paper/2312.02433/) (2023)
- [A Graph-Based Approach for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2311.17891/) (2023)
- [LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model](https://mlsanity.com/paper/2406.04659/) (2024)
- [CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation](https://mlsanity.com/paper/2406.00384/) (2024)

## Built on by (most cited first, 2 of 2)

- [Edge Weight Prediction For Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2411.16665/) (2024)
- [GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2605.13151/) (2026)

## Abstract (arXiv)

Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse object categories. Recent efforts have explored the use of text queries, leveraging their enhanced stability and generalization capabilities. However, existing approaches often remain constrained by their reliance on support queries, their failure to fully utilize the rich priors embedded in pre-trained large language models, and the limitations imposed by their parametric distribution assumptions. To address these challenges, we introduce CapeLLM, the first multimodal large language model (MLLM) designed for CAPE. Our method only employs query image and detailed text descriptions as an input to estimate category-agnostic keypoints. Our method encompasses effective training strategies and carefully designed instructions for applying the MLLM to CAPE. Moreover, we propose an inference mechanism that further enhances the reasoning process for unseen keypoints. while flexibly modeling their underlying spatial distribution and uncertainty, allowing for adaptive refinement based on contextual cues. We conducted extensive experiments to apply the MLLM to CAPE effectively, focusing not only on the model architecture and prompt design but also on ensuring robustness across input variations. Our approach sets a new state-of-the-art on the MP-100 benchmark in the 1-shot and even 5-shot setting, marking a significant advancement in the field of category-agnostic pose estimation. Code is available at https://github.com/Junhojuno/CapeLLM.