Talking Papers Podcast
🎙️ Welcome to the Talking Papers Podcast: Where Research Meets Conversation 🌟
Are you ready to explore the fascinating world of cutting-edge research in computer vision, machine learning, artificial intelligence, graphics, and beyond? Join us on this podcast by researchers, for researchers, as we venture into the heart of groundbreaking academic papers.
At Talking Papers, we've reimagined the way research is shared. In each episode, we engage in insightful discussions with the main authors of academic papers, offering you a unique opportunity to dive deep into the minds behind the innovation.
📚 Structure That Resembles a Paper 📝
Just like a well-structured research paper, each episode takes you on a journey through the academic landscape. We provide a concise TL;DR (abstract) to set the stage, followed by a thorough exploration of related work, approach, results, conclusions, and a peek into future work.
🔍 Peer Review Unveiled: "What Did Reviewer 2 Say?" 📢
But that's not all! We bring you an exclusive bonus section where authors candidly share their experiences in the peer review process. Discover the insights, challenges, and triumphs behind the scenes of academic publishing.
🚀 Join the Conversation 💬
Whether you're a seasoned researcher or an enthusiast eager to explore the frontiers of knowledge, Talking Papers Podcast is your gateway to in-depth, engaging discussions with the experts shaping the future of technology and science.
🎧 Tune In and Stay Informed 🌐
Don't miss out on the latest in research and innovation.
Subscribe and stay tuned for our enlightening episodes. Welcome to the future of research dissemination – welcome to Talking Papers Podcast!
Enjoy the journey! 🌠
#TalkingPapersPodcast #ResearchDissemination #AcademicInsights
Talking Papers Podcast
Yicong Hong - VLN BERT
PAPER TITLE:
"VLN BERT: A Recurrent Vision-and-Language BERT for Navigation"
AUTHORS:
Yicong Hong, Qi Wu, Yuankai Qi, Cristian Rodriguez-Opazo, Stephen Gould
ABSTRACT:
Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language (V&L) BERT. However, its application for the task of vision and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously.
CODE:
💻 https://github.com/YicongHong/Recurrent-VLN-BERT
LINKS AND RESOURCES
👱Yicong's page
RELATED PAPERS:
📚 Attention is All You Need
📚 Towards learning a generic agent for vision-and-language navigation via pre-training
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
This episode was recorded on April, 16th 2021.
SUBSCRIBE AND FOLLOW:
🎧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
#talkingpapers #CVPR2021 #VLNBERT
#VLN #VisionAndLanguageNavigation #VisionAndLanguage #machinelearning #deeplearning #AI #neuralnetworks #research #computervision #artificialintelligence
🎧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
