A Generic Object Re-identification System for Short Videos

02/10/2021
by   Tairu Qiu, et al.
0

Short video applications like TikTok and Kwai have been a great hit recently. In order to meet the increasing demands and take full advantage of visual information in short videos, objects in each short video need to be located and analyzed as an upstream task. A question is thus raised – how to improve the accuracy and robustness of object detection, tracking, and re-identification across tons of short videos with hundreds of categories and complicated visual effects (VFX). To this end, a system composed of a detection module, a tracking module and a generic object re-identification module, is proposed in this paper, which captures features of major objects from short videos. In particular, towards the high efficiency demands in practical short video application, a Temporal Information Fusion Network (TIFN) is proposed in the object detection module, which shows comparable accuracy and improved time efficiency to the state-of-the-art video object detector. Furthermore, in order to mitigate the fragmented issue of tracklets in short videos, a Cross-Layer Pointwise Siamese Network (CPSN) is proposed in the tracking module to enhance the robustness of the appearance model. Moreover, in order to evaluate the proposed system, two challenge datasets containing real-world short videos are built for video object trajectory extraction and generic object re-identification respectively. Overall, extensive experiments for each module and the whole system demonstrate the effectiveness and efficiency of our system.

READ FULL TEXT

page 2

page 4

page 6

page 8

research
02/21/2017

Object Detection in Videos with Tubelet Proposal Networks

Object detection in videos has drawn increasing attention recently with ...
research
03/19/2020

Foldover Features for Dynamic Object Behavior Description in Microscopic Videos

Behavior description is conducive to the analysis of tiny objects, simil...
research
08/19/2021

A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations

Videos captured using Transmission Electron Microscopy (TEM) can encode ...
research
05/21/2020

Joint Detection and Tracking in Videos with Identification Features

Recent works have shown that combining object detection and tracking tas...
research
08/24/2023

An All Deep System for Badminton Game Analysis

The CoachAI Badminton 2023 Track1 initiative aim to automatically detect...
research
11/23/2020

Siamese Tracking with Lingual Object Constraints

Classically, visual object tracking involves following a target object t...
research
07/25/2021

Transcript to Video: Efficient Clip Sequencing from Texts

Among numerous videos shared on the web, well-edited ones always attract...

Please sign up or login with your details

Forgot password? Click here to reset