Recurrent Attention Models for Depth-Based Person Identification
We present an attention-based model that reasons on human body shape and motion dynamics to identify individuals in the absence of RGB information, hence in the dark. Our approach leverages unique 4D spatio-temporal signatures to address the identification problem across days. Formulated as a reinforcement learning task, our model is based on a combination of convolutional and recurrent neural networks with the goal of identifying small, discriminative regions indicative of human identity. We demonstrate that our model produces state-of-the-art results on several published datasets given only depth images. We further study the robustness of our model towards viewpoint, appearance, and volumetric changes. Finally, we share insights gleaned from interpretable 2D, 3D, and 4D visualizations of our model's spatio-temporal attention.
Code (0)
등록된 구현이 없습니다.
Tasks
Person Identificationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Recurrent Neural Networks for Person Re-identification Revisited
The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning. In particular, in the context of video-based re-identification, many…
Person Re-IdentificationReinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this problem by introducing split-rate RGB-to-…
Person Re-IdentificationReinforcement LearningCross Domain Knowledge Transfer for Person Re-identification
Person Re-Identification (re-id) is a challenging task in computer vision, especially when there are limited training data from multiple camera views. In this paper, we pro- pose a deep learning based person re-identific…
AttributeClassificationGeneral ClassificationPerson Re-Identification+1Cross-Modal Distillation for RGB-Depth Person Re-Identification
Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile r…
Autonomous DrivingCross-Modal Person Re-IdentificationCross-Modal Person Re-Identificationobject-detection+3See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification
Surveillance cameras have been widely used in different scenes. Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification. This topic has gained increasing i…
Metric LearningPerson Re-IdentificationVideo-Based Person Re-Identification