1 code implementation • RC 2020 • Prateek Garg, Lakshya Singhal, Ashish Sardana
When we tried this in a semantic segmentation context, we found that the results were very underwhelming and in contrast with the seemingly good results by the STE optimizer even with much hyperparameter tuning.
1 code implementation • RC 2020 • Jishnu Jaykumar P, Ashish Sardana
In addition to making the codebase more modular and easy to navigate, we have made changes to incorporate different transformers in the question embedding module.
1 code implementation • 21 Nov 2020 • Ravindra Yadav, Ashish Sardana, Vinay P Namboodiri, Rajesh M Hegde
Indeed, just having the ability to generate a single talking face would make a system almost robotic in nature.
no code implementations • 14 Nov 2020 • Ravindra Yadav, Ashish Sardana, Vinay P Namboodiri, Rajesh M Hegde
Understanding the relationship between the auditory and visual signals is crucial for many different applications ranging from computer-generated imagery (CGI) and video editing automation to assisting people with hearing or visual impairments.
1 code implementation • WS 2020 • Aman Shenoy, Ashish Sardana
Sentiment Analysis and Emotion Detection in conversation is key in several real-world applications, with an increase in modalities available aiding a better understanding of the underlying emotions.
Ranked #7 on Multimodal Sentiment Analysis on MOSI
1 code implementation • arXiv preprint 2020 • Aman Shenoy, Ashish Sardana
Sentiment Analysis and Emotion Detection in conversation is key in several real-world applications, with an increase in modalities available aiding a better understanding of the underlying emotions.
Ranked #8 on Multimodal Sentiment Analysis on CMU-MOSEI (using extra training data)
Emotion Recognition in Conversation Multimodal Emotion Recognition +1