Condition-Aware Comparison Scheme for Gait Recognition

Wu, Haoqian; Tian, Jian; Fu, Yongjian; Li, Bin; Li, Xi

doi:10.1109/tip.2020.3039888

Cited by 19 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The temperature τ is set to 0.1 and the momentum α, β are both set to 0.9. It's worth mentioning that we reproduce the results for GaitSet, GaitPart, and MT3D with the data augmentation proposed in [73], which are slightly higher than their original results [21], [23], [37].…”

Section: B Implementation Detailsmentioning

confidence: 64%

“…To verify the ability of GaitMPL under crosswalking-condition and cross-view scenarios, the comparison is conducted on CASIA-B. We compare the performance of GaitMPL with several state-of-the-art methods, including CNN-LB [74], GaitSet [21], GaitPart [23], GLN [22], MT3D [37], DynamicGait [73], CSTL [75], 3DLocal [76], and GaitGL [72]. All the results are averaged on the 11 gallery views and the identical views are excluded.…”

Section: Comparison With State-of-the-art Methods 1) Casia-bmentioning

confidence: 99%

See 1 more Smart Citation

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning

Dou

Zhang

Zhao

et al. 2024

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Gait recognition aims at identifying the pedestrians at a long distance by their biometric gait patterns. It is inherently challenging due to the various covariates and the properties of silhouettes (textureless and colorless), which result in two kinds of pair-wise hard samples: the same pedestrian could have distinct silhouettes (intra-class diversity) and different pedestrians could have similar silhouettes (inter-class similarity). In this work, we propose to solve the hard sample issue with a Memoryaugmented Progressive Learning network (GaitMPL), including Dynamic Reweighting Progressive Learning module (DRPL) and Global Structure-Aligned Memory bank (GSAM). Specifically, DRPL reduces the learning difficulty of hard samples by easy-tohard progressive learning. GSAM further augments DRPL with a structure-aligned memory mechanism, which maintains and models the feature distribution of each ID. Experiments on two commonly used datasets, CASIA-B and OU-MVLP, demonstrate the effectiveness of GaitMPL. On CASIA-B, we achieve the state-of-the-art performance, i.e., 88.0% on the most challenging condition (Clothing) and 93.3% on the average condition, which outperforms the other methods by at least 3.8% and 1.4%, respectively.

show abstract

Section: B Implementation Detailsmentioning

confidence: 64%

Section: Comparison With State-of-the-art Methods 1) Casia-bmentioning

confidence: 99%

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning

Dou

Zhang

Zhao

et al. 2024

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The standard of evidence admissibility in the United States also has been discussed [ 104 , 105 ] Furthermore, there are many papers that discuss the reliability of gait analysis [ 60 , 68 , 72 , 89 , 93 , 94 , 96 , 105 , 106 , 108 , 116 , 120 , 123 , 125 , 126 , 129 , 130 , 132 , 136 , 140 , 144 ].…”

Section: Gait Analysismentioning

confidence: 99%

Interpol review of forensic video analysis, 2019–2022

Geradts

Riphagen

2023

Forensic Science International: Synergy

View full text Add to dashboard Cite

“…Particularly, GaitSet [25] and GLN [26] considered a gait sequence as an unordered set, which mainly focused on spatial modeling and captured interframe dependency implicitly. GaitPart [8] and Wu et al [9] extracted local temporal clues by 1D convolutions and aggregated them in a summation or a concatenation manner. LSTM networks were applied in [10], [11] to achieve longshort temporal modeling, which fused temporal clues by temporal accumulation.…”

Section: Temporal Modelingmentioning

confidence: 99%

“…At present, multi-layer convolutions have been widely used in current methods to model multi-scale temporal information. And they aggregated multi-scale features in a summation [8], [9], [10], [11] or a concatenation way [12], [13]. However, since the aggregation methods are fixed, these manners are not flexible enough to adapt to variations of complex motion and realistic factors, i.e., self occlusion between body parts and change of camera viewpoints.…”

Section: Introductionmentioning

confidence: 99%

Context-Sensitive Temporal Feature Learning for Gait Recognition

Huang

Zhu

Wang

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Although gait recognition has drawn increasing research attention recently, it remains challenging to learn discriminative temporal representation, since the silhouette differences are quite subtle in spatial domain. Inspired by the observation that human can distinguish gaits of different subjects by adaptively focusing on temporal clips with different time scales, we propose a context-sensitive temporal feature learning (CSTL) network for gait recognition. CSTL produces temporal features in three scales, and adaptively aggregates them according to the contextual information from local and global perspectives. Specifically, CSTL contains an adaptive temporal aggregation module that subsequently performs local relation modeling and global relation modeling to fuse the multi-scale features. Besides, in order to remedy the spatial feature corruption caused by temporal operations, CSTL incorporates a salient spatial feature learning (SSFL) module to select groups of discriminative spatial features. Particularly, we utilize transformers to implement the global relation modeling and the SSFL module. To the best of our knowledge, this is the first work that adopts transformer in gait recognition. Extensive experiments conducted on three datasets demonstrate the state-of-the-art performance. Concretely, we achieve rank-1 accuracies of 98.7%, 96.2% and 88.7% under normal-walking, bag-carrying and coat-wearing conditions on CASIA-B, 97.5% on OU-MVLP and 50.6% on GREW.

show abstract

Condition-Aware Comparison Scheme for Gait Recognition

Cited by 19 publications

References 33 publications

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning

Interpol review of forensic video analysis, 2019–2022

Context-Sensitive Temporal Feature Learning for Gait Recognition

Contact Info

Product

Resources

About