# SilLang: Improving Gait Recognition with Silhouette Language Encoding

arXiv: https://arxiv.org/abs/2603.23976 · HTML: https://mlsanity.com/paper/2603.23976/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [OpenGait: Revisiting Gait Recognition Toward Better Practicality](https://mlsanity.com/paper/2211.06597/) (2022)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [LidarGait: Benchmarking 3D Gait Recognition with Point Clouds](https://mlsanity.com/paper/2211.10598/) (2022)
- [A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges](https://mlsanity.com/paper/2206.13732/) (2022)
- [BigGait: Learning Gait Representation You Want by Large Vision Models](https://mlsanity.com/paper/2402.19122/) (2024)
- [DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition](https://mlsanity.com/paper/2303.14953/) (2023)
- [GaitGCI: Generative Counterfactual Intervention for Gait Recognition](https://mlsanity.com/paper/2306.03428/) (2023)
- [BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models](https://mlsanity.com/paper/2505.18132/) (2025)
- [Hierarchical Spatio-Temporal Representation Learning for Gait Recognition](https://mlsanity.com/paper/2307.09856/) (2023)
- [QAGait: Revisit Gait Recognition from a Quality Perspective](https://mlsanity.com/paper/2401.13531/) (2024)
- [Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition](https://mlsanity.com/paper/2407.12519/) (2024)
- [GLGait: A Global-Local Temporal Receptive Field Network for Gait Recognition in the Wild](https://mlsanity.com/paper/2408.06834/) (2024)
- [Generalized Inter-class Loss for Gait Recognition](https://mlsanity.com/paper/2210.06779/) (2022)
- [Free Lunch for Gait Recognition: A Novel Relation Descriptor](https://mlsanity.com/paper/2308.11487/) (2023)

## Abstract (arXiv)

Gait silhouettes, which can be encoded into binary gait codes, are widely adopted to representing motion patterns of pedestrian. Recent approaches commonly leverage visual backbones to encode gait silhouettes, achieving successful performance. However, they primarily focus on continuous visual features, overlooking the discrete nature of binary silhouettes that inherently share a discrete encoding space with natural language. Large Language Models (LLMs) have demonstrated exceptional capability in extracting discriminative features from discrete sequences and modeling long-range dependencies, highlighting their potential to capture temporal motion patterns by identifying subtle variations. Motivated by these observations, we explore bridging binary gait silhouettes and natural language within a binary encoding space. However, the encoding spaces of text tokens and binary gait silhouettes remain misaligned, primarily due to differences in token frequency and density. To address this issue, we propose the Contour-Velocity Tokenizer, which encodes binary gait silhouettes while reshaping their distribution to better align with the text token space. We then establish a dual-branch framework termed Silhouette Language Model, which enhances visual silhouettes by integrating discrete linguistic embeddings derived from LLMs. Implemented on mainstream gait backbones, SilLang consistently improves state-of-the-art methods across SUSTech1K, GREW, and Gait3D.