English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Generalized Many-Way Few-Shot Video Classification

Xian, Y., Korbar, B., Douze, M., Schiele, B., Akata, Z., & Torresani, L. (2020). Generalized Many-Way Few-Shot Video Classification. Retrieved from https://arxiv.org/abs/2007.04755.

Item is

Files

show Files
hide Files
:
arXiv:2007.04755.pdf (Preprint), 5MB
Name:
arXiv:2007.04755.pdf
Description:
File downloaded from arXiv at 2020-12-03 07:49
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Xian, Yongqin1, Author           
Korbar, Bruno2, Author
Douze, Matthijs2, Author
Schiele, Bernt1, Author           
Akata, Zeynep1, Author           
Torresani, Lorenzo2, Author
Affiliations:
1Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: Few-shot learning methods operate in low data regimes. The aim is to learn
with few training examples per class. Although significant progress has been
made in few-shot image classification, few-shot video recognition is relatively
unexplored and methods based on 2D CNNs are unable to learn temporal
information. In this work we thus develop a simple 3D CNN baseline, surpassing
existing methods by a large margin. To circumvent the need of labeled examples,
we propose to leverage weakly-labeled videos from a large dataset using tag
retrieval followed by selecting the best clips with visual similarities,
yielding further improvement. Our results saturate current 5-way benchmarks for
few-shot video classification and therefore we propose a new challenging
benchmark involving more classes and a mixture of classes with varying
supervision.

Details

show
hide
Language(s): eng - English
 Dates: 2020-07-092020
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2007.04755
BibTex Citekey: Xian_arXiv2007.04755
URI: https://arxiv.org/abs/2007.04755
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show