# Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation

arXiv: https://arxiv.org/abs/2101.11223 · HTML: https://mlsanity.com/paper/2101.11223/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 52 references that are in the map.
- First posted on arXiv 27 Jan 2021.

## Builds on (most cited first, 30 of 42)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Attentive Single-Tasking of Multiple Tasks](https://mlsanity.com/paper/1904.08918/) (2019)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [PifPaf: Composite Fields for Human Pose Estimation](https://mlsanity.com/paper/1903.06593/) (2019)

## Built on by (most cited first, 30 of 30)

- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [DiffPose: Toward More Reliable 3D Pose Estimation](https://mlsanity.com/paper/2211.16940/) (2022)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/2210.11940/) (2022)
- [Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity](https://mlsanity.com/paper/2306.07879/) (2023)
- [From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction](https://mlsanity.com/paper/2602.01661/) (2026)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation](https://mlsanity.com/paper/2207.02425/) (2022)
- [BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations](https://mlsanity.com/paper/2112.10716/) (2021)
- [Bias-Compensated Integral Regression for Human Pose Estimation](https://mlsanity.com/paper/2301.10431/) (2023)
- [Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion](https://mlsanity.com/paper/2410.04574/) (2024)
- [Occluded Human Pose Estimation based on Limb Joint Augmentation](https://mlsanity.com/paper/2410.09885/) (2024)
- [SU-Net: Pose estimation network for non-cooperative spacecraft on-orbit](https://mlsanity.com/paper/2302.10602/) (2023)
- [BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation](https://mlsanity.com/paper/2309.14072/) (2023)
- [Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle](https://mlsanity.com/paper/2412.01562/) (2024)
- [MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model](https://mlsanity.com/paper/2302.08751/) (2023)
- [GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution](https://mlsanity.com/paper/2409.07752/) (2024)
- [VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation](https://mlsanity.com/paper/2504.19032/) (2025)
- [SHOP: A Deep Learning Based Pipeline for near Real-Time Detection of Small Handheld Objects Present in Blurry Video](https://mlsanity.com/paper/2203.15228/) (2022)
- [UV R-CNN: Stable and Efficient Dense Human Pose Estimation](https://mlsanity.com/paper/2211.02337/) (2022)
- [Survey of 3D Human Body Pose and Shape Estimation Methods for Contemporary Dance Applications](https://mlsanity.com/paper/2401.02383/) (2024)
- [Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach](https://mlsanity.com/paper/2405.20084/) (2024)
- [GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutions](https://mlsanity.com/paper/2409.07798/) (2024)
- [Refinement Module based on Parse Graph for Human Pose Estimation](https://mlsanity.com/paper/2501.11069/) (2025)
- [Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation](https://mlsanity.com/paper/2505.12130/) (2025)
- [Parse Graph-Based Visual-Language Interaction for Human Pose Estimation](https://mlsanity.com/paper/2509.07385/) (2025)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)
- [FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation](https://mlsanity.com/paper/2603.16596/) (2026)

## Abstract (arXiv)

A key assumption of top-down human pose estimation approaches is their expectation of having a single person/instance present in the input bounding box. This often leads to failures in crowded scenes with occlusions. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Instance Pose Network (MIPNet) allows for predicting multiple 2D pose instances within a given bounding box. We introduce a Multi-Instance Modulation Block (MIMB) that can adaptively modulate channel-wise feature responses for each instance and is parameter efficient. We demonstrate the efficacy of our approach by evaluating on COCO, CrowdPose, and OCHuman datasets. Specifically, we achieve 70.0 AP on CrowdPose and 42.5 AP on OCHuman test sets, a significant improvement of 2.4 AP and 6.5 AP over the prior art, respectively. When using ground truth bounding boxes for inference, MIPNet achieves an improvement of 0.7 AP on COCO, 0.9 AP on CrowdPose, and 9.1 AP on OCHuman validation sets compared to HRNet. Interestingly, when fewer, high confidence bounding boxes are used, HRNet's performance degrades (by 5 AP) on OCHuman, whereas MIPNet maintains a relatively stable performance (drop of 1 AP) for the same inputs.