Gait recognition, which aims at identifying individuals by their walking patterns, has recently drawn increasing research attention. However, gait recognition still suffers from the conflicts between the limited binary visual clues of the silhouette and numerous covariates with diverse scales, which brings challenges to the model’s adaptiveness. In this paper, we address this conflict by developing a novel MetaGait that learns to learn an omni sample adaptive representation. Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives. Specifically, we leverage the meta-knowledge across the entire process, where Meta Triple Attention and Meta Temporal Pooling are presented respectively to adaptively capture omni-scale dependency from spatial/channel/temporal dimensions simultaneously and to adaptively aggregate temporal information through integrating the merits of three complementary temporal aggregation methods. Extensive experiments demonstrate the state-of-the-art performance of the proposed MetaGait. On CASIA-B, we achieve rank-1 accuracy of 98.7%, 96.0%, and 89.3% under three conditions, respectively. On OU-MVLP, we achieve rank-1 accuracy of 92.4%. 

MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition

Gait recognition is one of the most critical long-distance identification technologies and increasingly gains popularity in both research and industry communities. Despite the significant progress made in indoor datasets, much evidence shows that gait recognition techniques perform poorly in the wild. More importantly, we also find that some conclusions drawn from indoor datasets cannot be generalized to real applications. Therefore, the primary goal of this paper is to present a comprehensive benchmark study for better practicality rather than only a particular model for better performance. To this end, we first develop a flexible and efficient gait recognition codebase named OpenGait. Based on OpenGait, we deeply revisit the recent development of gait recognition by re-conducting the ablative experiments. Encouragingly,we detect some unperfect parts of certain prior woks, as well as new insights. Inspired by these discoveries, we develop a structurally simple, empirically powerful, and practically robust baseline model, GaitBase. Experimentally, we comprehensively compare GaitBase with many current gait recognition methods on multiple public datasets, and the results reflect that GaitBase achieves significantly strong performance in most cases regardless of indoor or outdoor situations. Code is available at https://github.com/ShiqiYu/OpenGait.

OpenGait: Revisiting Gait Recognition Toward Better Practicality

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 Memory-augmented 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-to-hard 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.

GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning

Age is an important human attribute that needs to be determined for various purposes, including security, health, human identification, and law enforcement. Hence, there is an increasing research interest in automatic age estimation using biometric traits such as face and gait. In recent years, gait analysis has received growing attention due to the pervasive nature of video surveillance. Gait signals that measure the manner of walking can be obtained using vision and sensor-based techniques. Individual gait patterns obtainable from videos, images, or sensors are shown unconsciously and are not easily obscured. Additionally, gait signals can be obtained unobtrusively with cameras placed at a long distance because gait does not require high-resolution images. However, the extraction of age-associated gait features is a challenging task due to various gait covariates. These covariates include clothing and view changes for vision-based gait; walking slope and footwear for sensor-based gait. This paper provides a survey of scientific literature on age estimation using gait features. We focus on the approaches to extracting age-associated gait features, namely, vision-based and sensor-based approaches, how they may be affected by the different covariates, and domain-specific applications. To make this work useful for as wide of an audience as possible, we also include discussions on key topics such as existing datasets, evaluation strategies, and open challenges that should be addressed in the future.

/pdf/learning-age-from-gait-a-survey-5eayap56yg.pdf

Learning Age From Gait: A Survey

Gait is one of the most promising biometrics that aims to identify pedestrians from their walking patterns. However, prevailing methods are susceptible to confounders, resulting in the networks hardly focusing on the regions that reflect effective walking patterns. To address this fundamental problem in gait recognition, we propose a Generative Counterfactual Intervention framework, dubbed GaitGCI, consisting of Counterfactual Intervention Learning (CIL) and Diversity-Constrained Dynamic Convolution (DCDC). CIL eliminates the impacts of confounders by maximizing the likelihood difference between factual/counterfactual attention while DCDC adaptively generates sample-wise factual/counterfactual attention to efficiently perceive the sample-wise properties. With matrix decomposition and diversity constraint, DCDC guarantees the model to be efficient and effective. Extensive experiments indicate that proposed GaitGCI: 1) could effectively focus on the discriminative and interpretable regions that reflect gait pattern; 2) is model-agnostic and could be plugged into existing models to improve performance with nearly no extra cost; 3) efficiently achieves state-of-the-art performance on arbitrary scenarios (in-the-lab and in-the-wild).

GaitGCI: Generative Counterfactual Intervention for Gait Recognition

Domain Generalizable Person Re-Identification (DG-ReID) is a more practical ReID task that is trained from multiple source domains and tested on the unseen target domains. Most existing methods are challenged for dealing with the shared and specific characteristics among different domains, which is called the domain conflict problem. To address this problem, we present an Adaptive Cross-domain Learning (ACL) framework equipped with a CrOss-Domain Embedding Block (CODE-Block) to maintain a common feature space for capturing both the domain-invariant and the domain-specific features, while dynamically mining the relations across different domains. Moreover, our model adaptively adjusts the architecture to focus on learning the corresponding features of a single domain at a time without interference from the biased features of other domains. Specifically, the CODE-Block is composed of two complementary branches, a dynamic branch for extracting domain-adaptive features and a static branch for extracting the domain-invariant features. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performances on the popular benchmarks. Under Protocol-2, our method outperforms previous SOTA by 7.8% and 7.6% in terms of mAP and rank-1 accuracy. 

Adaptive Cross-domain Learning for Generalizable Person Re-identification

With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of 11,000 subjects with fine-grained attributes in various complicated scenarios. Compared with existing real gait datasets with limited samples and simple scenarios, the proposed VersatileGait dataset possesses several nice properties, including huge dataset size, high sample diversity, high-quality annotations, multi-pitch angles, small domain gap with the real one, etc. Furthermore, we investigate the effectiveness of our dataset (e.g., domain transfer after pretraining). Then, we use the fine-grained attributes from VersatileGait to promote gait recognition in both accuracy and speed, and meanwhile justify the gait recognition performance under multi-pitch angle settings. Additionally, we explore a variety of potential applications for research.Extensive experiments demonstrate the value and effective-ness of the proposed VersatileGait in gait recognition along with its associated applications. We will release both VersatileGait and its corresponding data generation toolkit for further studies.

VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios.

Although the impressive performance in visual grounding, the prevailing approaches usually exploit the visual backbone in a passive way, i.e., the visual backbone extracts features with fixed weights without expression-related hints. The passive perception may lead to mismatches (e.g., redundant and missing), limiting further performance improvement. Ideally, the visual backbone should actively extract visual features since the expressions already provide the blueprint of desired visual features. The active perception can take expressions as priors to extract relevant visual features, which can effectively alleviate the mismatches. Inspired by this, we propose an active perception Visual Grounding framework based on Language Adaptive Weights, called VG-LAW. The visual backbone serves as an expression-specific feature extractor through dynamic weights generated for various expressions. Benefiting from the specific and relevant visual features extracted from the language-aware visual backbone, VG-LAW does not require additional modules for cross-modal interaction. Along with a neat multi-task head, VG-LAW can be competent in referring expression comprehension and segmentation jointly. Extensive experiments on four representative datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, and ReferItGame, validate the effectiveness of the proposed framework and demonstrate state-of-the-art performance.

Huanzhang Dou

Papers

MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition

GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning

Adaptive Cross-domain Learning for Generalizable Person Re-identification

VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios.

Language Adaptive Weight Generation for Multi-task Visual Grounding