1 code implementation • NeurIPS 2021 • Prasad Gabbur, Manjot Bilkhu, Javier Movellan
We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference.
no code implementations • 6 Jun 2019 • Manjot Bilkhu, Siyang Wang, Tushar Dobhal
Video Captioning and Summarization have become very popular in the recent years due to advancements in Sequence Modelling, with the resurgence of Long-Short Term Memory networks (LSTMs) and introduction of Gated Recurrent Units (GRUs).
no code implementations • 18 Mar 2019 • Manjot Bilkhu, Hammababdullah Ayyubi
Architectures such as I3D and C3D networks have shown state-of-the-art performances for activity recognition.