Artwork

Content provided by Itzik Ben-Shabat. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Itzik Ben-Shabat or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Cristian Rodriguez-Opazo - DORi

27:07
 
Share
 

Manage episode 316761990 series 3300270
Content provided by Itzik Ben-Shabat. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Itzik Ben-Shabat or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Paper title:
"DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video"
Authors: Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen Gould
Abstract:
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key innovation is to learn a video feature embedding through a language-conditioned message-passing algorithm suitable for temporal moment localization which captures the relationships between humans, objects and activities in the video. These relationships are obtained by a spatial subgraph that contextualized the scene representation using detected objects and human features. Moreover, a temporal sub-graph captures the activities within the video through time. Our method is evaluated on three standard benchmark datasets, and we also introduce YouCook II as a new benchmark for this task. Experiments show our method outperforms state-of-the-art methods on these datasets, confirming the effectiveness of our approach
RESOURCES
-----------------
Cristian's page: https://crodriguezo.github.io/
Code:
https://github.com/crodriguezo/DORi
Related papers:
"Proposal free temporal moment localization" : https://bit.ly/3EX1qCM
"Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs" : https://bit.ly/3zt4aXA
Subscribe to the podcast: https://talking.papers.podcast.itzikbs.com
Subscribe to our mailing list: http://eepurl.com/hRznqb
Follow us on Twitter: https://twitter.com/talking_papers
YouTube Channel: https://bit.ly/3eQOgwP
CONTACT:
-----------------
If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com
Recorded on March, 26th 2021.

🎧Subscribe on your favourite podcast app: https://talking.papers.podcast.itzikbs.com

📧Subscribe to our mailing list: http://eepurl.com/hRznqb

🐦Follow us on Twitter: https://twitter.com/talking_papers

🎥YouTube Channel: https://bit.ly/3eQOgwP

  continue reading

Chapters

1. Cristian Rodriguez-Opazo - DORi (00:00:00)

2. Intro (00:00:02)

3. Abstract (00:01:09)

4. Motivation (00:01:55)

5. Related Work (00:05:03)

6. Approach (00:07:46)

7. Results (00:15:17)

8. Conclusions and future work (00:19:02)

9. What did reviewer 2 say? (00:22:10)

35 episodes

Artwork

Cristian Rodriguez-Opazo - DORi

Talking Papers Podcast

0-10 subscribers

published

iconShare
 
Manage episode 316761990 series 3300270
Content provided by Itzik Ben-Shabat. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Itzik Ben-Shabat or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Paper title:
"DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video"
Authors: Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen Gould
Abstract:
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key innovation is to learn a video feature embedding through a language-conditioned message-passing algorithm suitable for temporal moment localization which captures the relationships between humans, objects and activities in the video. These relationships are obtained by a spatial subgraph that contextualized the scene representation using detected objects and human features. Moreover, a temporal sub-graph captures the activities within the video through time. Our method is evaluated on three standard benchmark datasets, and we also introduce YouCook II as a new benchmark for this task. Experiments show our method outperforms state-of-the-art methods on these datasets, confirming the effectiveness of our approach
RESOURCES
-----------------
Cristian's page: https://crodriguezo.github.io/
Code:
https://github.com/crodriguezo/DORi
Related papers:
"Proposal free temporal moment localization" : https://bit.ly/3EX1qCM
"Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs" : https://bit.ly/3zt4aXA
Subscribe to the podcast: https://talking.papers.podcast.itzikbs.com
Subscribe to our mailing list: http://eepurl.com/hRznqb
Follow us on Twitter: https://twitter.com/talking_papers
YouTube Channel: https://bit.ly/3eQOgwP
CONTACT:
-----------------
If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com
Recorded on March, 26th 2021.

🎧Subscribe on your favourite podcast app: https://talking.papers.podcast.itzikbs.com

📧Subscribe to our mailing list: http://eepurl.com/hRznqb

🐦Follow us on Twitter: https://twitter.com/talking_papers

🎥YouTube Channel: https://bit.ly/3eQOgwP

  continue reading

Chapters

1. Cristian Rodriguez-Opazo - DORi (00:00:00)

2. Intro (00:00:02)

3. Abstract (00:01:09)

4. Motivation (00:01:55)

5. Related Work (00:05:03)

6. Approach (00:07:46)

7. Results (00:15:17)

8. Conclusions and future work (00:19:02)

9. What did reviewer 2 say? (00:22:10)

35 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide