Pith. sign in

REVIEW 10 cited by

Exploring Deep Models for Practical Gait Recognition

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.03301 v3 pith:QBWLUYQF submitted 2023-03-06 cs.CV

Chao Fan , Saihui Hou , Yongzhen Huang , Shiqi Yu This is my paper
classification cs.CV
keywords gaitdeepmodelsrecognitionseriescnn-basedconstraineddatasets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Gait recognition is a rapidly advancing vision technique for person identification from a distance. Prior studies predominantly employed relatively shallow networks to extract subtle gait features, achieving impressive successes in constrained settings. Nevertheless, experiments revealed that existing methods mostly produce unsatisfactory results when applied to newly released real-world gait datasets. This paper presents a unified perspective to explore how to construct deep models for state-of-the-art outdoor gait recognition, including the classical CNN-based and emerging Transformer-based architectures. Specifically, we challenge the stereotype of shallow gait models and demonstrate the superiority of explicit temporal modeling and deep transformer structure for discriminative gait representation learning. Consequently, the proposed CNN-based DeepGaitV2 series and Transformer-based SwinGait series exhibit significant performance improvements on Gait3D and GREW. As for the constrained gait datasets, the DeepGaitV2 series also reaches a new state-of-the-art in most cases, convincingly showing its practicality and generality. The source code is available at https://github.com/ShiqiYu/OpenGait.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MMGait: Towards Multi-Modal Gait Recognition

    cs.CV 2026-04 conditional novelty 8.0 of 10

    MMGait provides a new multi-sensor gait dataset and OmniGait baseline to support single-modal, cross-modal, and unified multi-modal person identification from walking patterns.

  2. BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    BarbieGait is a new synthetic gait dataset with identity-consistent cloth changes paired with the GaitCLIF model that improves cross-clothing recognition on the new data and existing benchmarks.

  3. Probing Identity-Specific Motion Signatures: A Controlled Diagnostic Study

    cs.CV 2026-07 conditional novelty 6.5 of 10

    Identity-specific free-throw motion signatures exist and are learnable by video models, but models prefer static appearance shortcuts unless silhouettes or skeletons suppress them.

  4. Decoding Children's Gait Behavior

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A new 1,185-video pediatric gait dataset with EVGS labels, plus a VideoMAE-based model, reaches ~84% average accuracy on 34 clinical gait items — far above MLLMs and prior gait models.

  5. GaitFace: A Multimodal Dataset for Long-Range Person Identification

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A 70-subject public long-range face+gait dataset and protocols show SOTA models collapse on native low-res and elevated 100 m probes despite strong optical-zoom performance.

  6. The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    Transfer learning on a new clinical gait dataset shows selective freezing of low-level features in pretrained models yields stable frailty classification, with model attention aligning to lower-limb biomechanics.

  7. Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis

    cs.CV 2025-10 unverdicted novelty 6.0 of 10

    A transformer-based model that jointly processes 2D silhouettes and 3D SMPL features outperforms prior single-modality methods on the BRIAR dataset for gait recognition while also estimating age, BMI, and gender.

  8. DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Combining silhouettes with monocular depth estimates from the same RGB frames, fused through a multi-scale cross-level attention network, raises gait recognition rank-1 accuracy on CCPG, SUSTech1K, and CASIA-B.

  9. PCA-Guided Autoencoding for Structured Dimensionality Reduction in Active Infrared Thermography

    eess.IV 2025-08 unverdicted novelty 5.0 of 10

    A PCA-guided autoencoder with a distillation loss is claimed to give a more structured latent space and better defect characterization than existing dimensionality-reduction methods in active infrared thermography.

  10. Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction

    cs.CV 2025-07 reject novelty 5.0 of 10

    RG-Gait learns a residual correction to gait features for occluded inputs, adaptively weighted by an occlusion module, improving occluded recognition while retaining holistic performance.

Pith tools