SCHOLARLY PUBLICATION ✓ Open Access

Features for Multi-target Multi-camera Tracking and Re-identification

Ergys Ristani, Carlo Tomasi

📖 IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings 📅 2018-06-01 🔗 DOI: 10.1109/cvpr.2018.00632

⬇ Download PDF View Official Paper ↗

📄 Abstract

Multi-Target Multi-Camera Tracking (MTMCT) tracks many people through video taken from several cameras. Person Re-Identification (Re-ID) retrieves from a gallery images of people similar to a person query image. We learn good features for both MTMCT and Re-ID with a convolutional neural network. Our contributions include an adaptive weighted triplet loss for training and a new technique for hard-identity mining. Our method outperforms the state of the art both on the DukeMTMC benchmarks for tracking, and on the Market-1501 and DukeMTMC-ReID benchmarks for Re-ID. We examine the correlation between good Re-ID and good MTMCT scores, and perform ablation studies to elucidate the contributions of the main components of our system. Code is available1.

📄 Abstract

📤 Share this page

🔬 Related Research Papers

Explainability Methods for Graph Convolutional Neural Networks

Closed-Form Factorization of Latent Semantics in GANs

Attention Branch Network: Learning of Attention Mechanism for Visual Explanation

TopNet: Structural Point Cloud Decoder

Detecting Pedestrians by Learning Shapelet Features

DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection

End-to-End People Detection in Crowded Scenes

Learning Without Memorizing

ST++: Make Self-trainingWork Better for Semi-supervised Semantic Segmentation

A Hierarchical Deep Temporal Model for Group Activity Recognition

PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing

First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations