# Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps

arXiv: https://arxiv.org/abs/2509.19252 · HTML: https://mlsanity.com/paper/2509.19252/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation](https://mlsanity.com/paper/2209.09002/) (2022)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://mlsanity.com/paper/2107.13788/) (2021)
- [ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions](https://mlsanity.com/paper/2403.07392/) (2024)
- [A Survey on Robotics with Foundation Models: toward Embodied AI](https://mlsanity.com/paper/2402.02385/) (2024)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation](https://mlsanity.com/paper/2007.07227/) (2020)
- [DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition](https://mlsanity.com/paper/2210.05895/) (2022)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Understanding the Challenges and Opportunities of Pose-based Anomaly Detection](https://mlsanity.com/paper/2303.05463/) (2023)
- [Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance](https://mlsanity.com/paper/2201.05739/) (2022)
- [Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose](https://mlsanity.com/paper/2504.19970/) (2025)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)

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

- [From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Security](https://mlsanity.com/paper/2603.04723/) (2026)
- [Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting](https://mlsanity.com/paper/2606.06158/) (2026)

## Abstract (arXiv)

Continuous human motion understanding remains a core challenge in computer vision due to its high dimensionality and inherent redundancy. Efficient compression and representation are crucial for analyzing complex motion dynamics. In this work, we introduce an adversarially-refined VQ-GAN framework with dense motion tokenization for compressing spatio-temporal heatmaps while preserving the fine-grained traces of human motion. Our approach combines dense motion tokenization with adversarial refinement, which eliminates reconstruction artifacts like motion smearing and temporal misalignment observed in non-adversarial baselines. Our experiments on the CMU Panoptic dataset provide conclusive evidence of our method's superiority, outperforming the dVAE baseline by 9.31% SSIM and reducing temporal instability by 37.1%. Furthermore, our dense tokenization strategy enables a novel analysis of motion complexity, revealing that 2D motion can be optimally represented with a compact 128-token vocabulary, while 3D motion's complexity demands a much larger 1024-token codebook for faithful reconstruction. These results establish practical deployment feasibility across diverse motion analysis applications. The code base for this work is available at https://github.com/TeCSAR-UNCC/Pose-Quantization.