Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks

  title={Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks},
  author={Z. He and Hangen He},
  • Z. He, Hangen He
  • Published 2018
  • Mathematics, Computer Science
  • Symmetry
  • Nowadays, video surveillance has become ubiquitous with the quick development of artificial intelligence. Multi-object detection (MOD) is a key step in video surveillance and has been widely studied for a long time. The majority of existing MOD algorithms follow the “divide and conquer” pipeline and utilize popular machine learning techniques to optimize algorithm parameters. However, this pipeline is usually suboptimal since it decomposes the MOD task into several sub-tasks and does not… CONTINUE READING
    A Framework for Automatic Building Detection from Low-Contrast Satellite Images
    • 7
    • Open Access
    Vessel Detection and Tracking Method Based on Video Surveillance
    • 2
    • Open Access


    Publications referenced by this paper.
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,218
    • Highly Influential
    • Open Access
    Adam: A Method for Stochastic Optimization
    • 49,185
    • Open Access
    Gradient-based learning applied to document recognition
    • 24,132
    • Open Access
    SSD: Single Shot MultiBox Detector
    • 8,151
    • Open Access
    Object Detection with Discriminatively Trained Part Based Models
    • 8,291
    • Highly Influential
    • Open Access
    Fast R-CNN
    • 8,732
    • Open Access
    Microsoft COCO: Common Objects in Context
    • 10,179
    • Open Access
    Support-Vector Networks
    • 30,068
    • Open Access