Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning for Video-based Person Re-Identification: A Survey

Khawar Islam

TL;DR

This first comprehensive paper introduces a review of up-to-date advancements in deep learning approaches for video re-ID, and offers comparative performance analysis on various available datasets, guidance to improve videoRe-ID with valuable thoughts, and exciting research directions.

Abstract

Video-based person re-identification (video re-ID) has lately fascinated growing attention due to its broad practical applications in various areas, such as surveillance, smart city, and public safety. Nevertheless, video re-ID is quite difficult and is an ongoing stage due to numerous uncertain challenges such as viewpoint, occlusion, pose variation, and uncertain video sequence, etc. In the last couple of years, deep learning on video re-ID has continuously achieved surprising results on public datasets, with various approaches being developed to handle diverse problems in video re-ID. Compared to image-based re-ID, video re-ID is much more challenging and complex. To encourage future research and challenges, this first comprehensive paper introduces a review of up-to-date advancements in deep learning approaches for video re-ID. It broadly covers three important aspects, including brief video re-ID methods with their limitations, major milestones with technical challenges, and architectural design. It offers comparative performance analysis on various available datasets, guidance to improve video re-ID with valuable thoughts, and exciting research directions.

Deep Learning for Video-based Person Re-Identification: A Survey

TL;DR

This first comprehensive paper introduces a review of up-to-date advancements in deep learning approaches for video re-ID, and offers comparative performance analysis on various available datasets, guidance to improve videoRe-ID with valuable thoughts, and exciting research directions.

Abstract

Video-based person re-identification (video re-ID) has lately fascinated growing attention due to its broad practical applications in various areas, such as surveillance, smart city, and public safety. Nevertheless, video re-ID is quite difficult and is an ongoing stage due to numerous uncertain challenges such as viewpoint, occlusion, pose variation, and uncertain video sequence, etc. In the last couple of years, deep learning on video re-ID has continuously achieved surprising results on public datasets, with various approaches being developed to handle diverse problems in video re-ID. Compared to image-based re-ID, video re-ID is much more challenging and complex. To encourage future research and challenges, this first comprehensive paper introduces a review of up-to-date advancements in deep learning approaches for video re-ID. It broadly covers three important aspects, including brief video re-ID methods with their limitations, major milestones with technical challenges, and architectural design. It offers comparative performance analysis on various available datasets, guidance to improve video re-ID with valuable thoughts, and exciting research directions.
Paper Structure (25 sections, 7 equations, 2 figures, 3 tables)

This paper contains 25 sections, 7 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Contribution of this survey paper
  3. Review of existing survey papers
  4. Video re-ID Methods
  5. Global Appearance Methods
  6. Local Part Alignments Methods
  7. Attention Methods
  8. Graph Methods
  9. Transformer Methods
  10. Novel Architectures
  11. Loss Functions
  12. Attention and CL Loss
  13. Weighted Triple-Sequence Loss (WTSL)
  14. Symbolic Triplet Loss (STL)
  15. Weighted Contrastive Loss (WCL)
  16. ...and 10 more sections

Figures (2)

  • Figure 1: Timeline of the top-performing methods for video re-ID task.
  • Figure 2: Illustration of simple graph each line connected with two vertices. In a hypergraph, each edge is connected with more than two vertices. In a multi-granularity graph, each node models specific spatial granularity, and each hypergraph is connected with multiple nodes.