# Recurrent Attention Models for Depth-Based Person Identification

arXiv: https://arxiv.org/abs/1611.07212 · HTML: https://mlsanity.com/paper/1611.07212/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2016.

## Built on by (most cited first, 18 of 18)

- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification](https://mlsanity.com/paper/2303.06819/) (2023)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task](https://mlsanity.com/paper/2211.05039/) (2022)
- [SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification](https://mlsanity.com/paper/2107.01903/) (2021)
- [Cross Vision-RF Gait Re-identification with Low-cost RGB-D Cameras and mmWave Radars](https://mlsanity.com/paper/2207.07896/) (2022)
- [DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2411.07205/) (2024)
- [Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification](https://mlsanity.com/paper/2106.03069/) (2021)
- [SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2504.09549/) (2025)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey](https://mlsanity.com/paper/2304.08193/) (2023)
- [Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention](https://mlsanity.com/paper/2111.02018/) (2021)
- [A Little Bit Attention Is All You Need for Person Re-Identification](https://mlsanity.com/paper/2302.14574/) (2023)
- [Policy-based Foveated Imaging and Perception](https://mlsanity.com/paper/2606.02565/) (2026)
- [Person Re-identification based on Robust Features in Open-world](https://mlsanity.com/paper/2102.10798/) (2021)
- [Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments](https://mlsanity.com/paper/2211.01527/) (2022)
- [A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects](https://mlsanity.com/paper/2401.15296/) (2024)
- [MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities](https://mlsanity.com/paper/2609.11601/) (2026)

## Abstract (arXiv)

We present an attention-based model that reasons on human body shape and motion dynamics to identify individuals in the absence of RGB information, hence in the dark. Our approach leverages unique 4D spatio-temporal signatures to address the identification problem across days. Formulated as a reinforcement learning task, our model is based on a combination of convolutional and recurrent neural networks with the goal of identifying small, discriminative regions indicative of human identity. We demonstrate that our model produces state-of-the-art results on several published datasets given only depth images. We further study the robustness of our model towards viewpoint, appearance, and volumetric changes. Finally, we share insights gleaned from interpretable 2D, 3D, and 4D visualizations of our model's spatio-temporal attention.