Articles
Pages
Products
Research Papers
Blogs
Search Engines
Events
Webinar, Seminar, Live Classes

Research Papers by Category

Extracting textual overlays from social media videos using neural networks

Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important meta-data source, e.g. for content classification or retrieval tasks. In this work, we present a robust method for extracting textual overlays from videos that builds up on multiple neural network architectures. The proposed solution relies on several processing steps: keyframe extraction, text detection and text recognition. The main component of our system, i.e. the text recognition module, is inspired by a convolutional recurrent neural network architecture and we improve its performance using synthetically generated dataset of over 600,000 images with text prepared by authors specifically for this task. We also develop a filtering method that reduces the amount of overlapping text phrases using Levenshtein distance and further boosts system’s performance. The final accuracy of our solution reaches over 80% and is au pair with state-of-the-art methods.

Download PDF

Latest Upcoming Events

Tue Jul 23 @12:00AM
SIGIR 2019
Tue Jul 23 @ 8:00AM - 05:30PM
IETF 105
Tue Jul 23 @ 9:00AM - 11:30PM
16th Annual Qualitative Research Summer Intensive
Wed Jul 24 @12:00AM
SIGIR 2019
Wed Jul 24 @12:00AM
Twenty-sixth International Conference on Learning
Wed Jul 24 @ 8:00AM - 05:30PM
IETF 105
Wed Jul 24 @ 9:00AM - 11:30PM
16th Annual Qualitative Research Summer Intensive
Thu Jul 25 @12:00AM
SIGIR 2019
Thu Jul 25 @ 8:00AM - 05:30PM
IETF 105
Thu Jul 25 @ 9:00AM - 11:30PM
16th Annual Qualitative Research Summer Intensive

Get Exclusive Research Tips in Your Inbox

Receive Great tips via email, enter your email to Subscribe.
Please wait

airs logo

AIRS is the world's leading community for the Internet Research Specialist and provide a Unified Platform that delivers, Education, Training and Certification for Online Research.

Subscribe to AIRS Newsletter

Receive Great tips via email, enter your email to Subscribe.
Please wait

Follow Us on Social Media