Paper Reading AI Learner

Learning to Simplify Spatial-Temporal Graphs in Gait Analysis

2023-10-05 09:03:51
Adrian Cosma, Emilian Radoi


Gait analysis leverages unique walking patterns for person identification and assessment across multiple domains. Among the methods used for gait analysis, skeleton-based approaches have shown promise due to their robust and interpretable features. However, these methods often rely on hand-crafted spatial-temporal graphs that are based on human anatomy disregarding the particularities of the dataset and task. This paper proposes a novel method to simplify the spatial-temporal graph representation for gait-based gender estimation, improving interpretability without losing performance. Our approach employs two models, an upstream and a downstream model, that can adjust the adjacency matrix for each walking instance, thereby removing the fixed nature of the graph. By employing the Straight-Through Gumbel-Softmax trick, our model is trainable end-to-end. We demonstrate the effectiveness of our approach on the CASIA-B dataset for gait-based gender estimation. The resulting graphs are interpretable and differ qualitatively from fixed graphs used in existing models. Our research contributes to enhancing the explainability and task-specific adaptability of gait recognition, promoting more efficient and reliable gait-based biometrics.

Abstract (translated)

步态分析利用独特的步态模式跨多个领域进行人员识别和评估。在步态分析中使用的方法中,基于骨骼的方法表现出了很大的潜力,因为它们具有稳健和可解释的特点。然而,这些方法通常依赖于手工构建的空间和时间图形,这些图形是基于人类解剖学而不考虑数据集和任务特定性的。本文提出了一种新方法,以简化基于步态性别估计的空间和时间图形表示,同时提高解释性,而不会丢失性能。我们的方法和两个模型一起工作,一个向前,一个向后,可以调整每个行走实例的相邻矩阵,从而消除图形的固定性质。通过使用直穿 Gumbel-Softmax技巧,我们的模型可以 end-to-end 训练。我们使用 CASIA-B 数据集展示了我们方法的有效性, resulting 图形具有可解释性,与当前模型使用的固定图形 qualitative 不同。我们的研究有助于增强解释性和任务特定适应性的步态识别,促进更高效和可靠的基于步态的生物特征。



3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot