A Siamese Long Short-Term Memory Architecture for Human Re-Identification

Abstract

Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction, representations are formed locally and independent of other regions. We present a novel siamese Long Short-Term Memory (LSTM) architecture that can process image regions sequentially and enhance the discriminative capability of local feature representation by leveraging contextual information. The feedback connections and internal gating mechanism of the LSTM cells enable our model to memorize the spatial dependencies and selectively propagate relevant contextual information through the network. We demonstrate improved performance compared to the baseline algorithm with no LSTM units and promising results compared to state-of-the-art methods on Market-1501, CUHK03 and VIPeR datasets. Visualization of the internal mechanism of LSTM cells shows meaningful patterns can be learned by our method.

References in corpus (4)

• Sequence to Sequence Learning with Neural Networks
• LSTM: A Search Space Odyssey
• Visualizing and Understanding Recurrent Networks
• DAG-Recurrent Neural Networks For Scene Labeling

Cited by in corpus (11)

• SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Batch DropBlock Network for Person Re-identification and Beyond
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• Knowledge Distillation for End-to-End Person Search
• Semantics-Aligned Representation Learning for Person Re-identification
• Support Neighbor Loss for Person Re-Identification
• Omni-directional Feature Learning for Person Re-identification
• Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification