HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
arXiv:1709.09930
Abstract
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attention-based deep neural network, named as HydraPlus-Net (HP-net), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person re-identification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-the-art methods on various datasets.
Accepted by ICCV 2017
References in corpus (12)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- Multiple Object Recognition with Visual Attention
- Stacked Hourglass Networks for Human Pose Estimation
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks
- A Richly Annotated Dataset for Pedestrian Attribute Recognition
- Attention to Scale: Scale-aware Semantic Image Segmentation
- Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
- Learning a Discriminative Null Space for Person Re-identification
- Person Search with Natural Language Description
- PANDA: Pose Aligned Networks for Deep Attribute Modeling
- Scalable Metric Learning via Weighted Approximate Rank Component Analysis
Cited by in corpus (30)
- AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- Harmonious Attention Network for Person Re-Identification
- Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
- Re-ID done right: towards good practices for person re-identification
- The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
- Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
- Horizontal Pyramid Matching for Person Re-identification
- Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
- Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
- A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
- Dynamic Curriculum Learning for Imbalanced Data Classification
- Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
- Pedestrian Attribute Recognition: A Survey
- Pose-Normalized Image Generation for Person Re-identification
- Pose-guided Visible Part Matching for Occluded Person ReID
- Person Search via A Mask-Guided Two-Stream CNN Model
- Batch DropBlock Network for Person Re-identification and Beyond
- CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
- Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
- Person Re-identification with Deep Similarity-Guided Graph Neural Network
- Re-Identification with Consistent Attentive Siamese Networks
- Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
- Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
- Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
- In Defense of the Classification Loss for Person Re-Identification
- Self Attention Grid for Person Re-Identification
- Sparse Label Smoothing Regularization for Person Re-Identification
- Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
- Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
- Self-Referenced Deep Learning