Radial Loss for Learning Fine-grained Video Similarity Metric

Abhinav Jain, Prerna Agarwal, Shashank Mujumdar, Nitin Gupta, Sameep Mehta, Chiranjoy ChattopadhyayICASSP 2019 · OpenReview

Abstract

In this paper, we propose the Radial Loss which utilizes category and sub-category labels to learn an order-preserving fine-grained video similarity metric. We propose an end-to-end quadlet-based Convolutional Neural Network (CNN) combined with Long Short-term Memory (LSTM) Unit to model video similarities by learning the pairwise distance relationships between samples in a quadlet generated using the category and sub-category labels. We showcase two novel applications of learning a video similarity metric - (i) fine-grained video retrieval, (ii) fine-grained event detection, along with simultaneous shot boundary detection, and correspondingly show promising results against those of the baselines on two new fine-grained video datasets.
BibTeX
@inproceedings{jain2019radial,
  author = {Abhinav Jain and Prerna Agarwal and Shashank Mujumdar and Nitin Gupta and Sameep Mehta and Chiranjoy Chattopadhyay},
  title = {{Radial Loss for Learning Fine-grained Video Similarity Metric}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2019},
  url = {https://openreview.net/forum?id=QC_baVHVGRA},
}

Loading related content...

Figure