3.4k citations · 6.8k across the 36 of their papers we have counts for
5 papers · 1 filter
Video Action Transformer Network
Rohit Girdhar, João Carreira, Carl Doersch +1
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the…
The Visual QA Devil in the Details: The Impact of Early Fusion and Batch Norm on CLEVR
Mateusz Malinowski, Carl Doersch
Visual QA is a pivotal challenge for higher-level reasoning, requiring understanding language, vision, and relationships between many objects in a scene. Although datasets like CLE…
Learning Visual Question Answering by Bootstrapping Hard Attention
Mateusz Malinowski, Carl Doersch, Adam Santoro +1
Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all…
A Better Baseline for AVA
Rohit Girdhar, João Carreira, Carl Doersch +1
We introduce a simple baseline for action localization on the AVA dataset. The model builds upon the Faster R-CNN bounding box detection framework, adapted to operate on pure spati…
Kickstarting Deep Reinforcement Learning
Simon Schmitt, Jonathan J. Hudson, Augustin Zidek +8
We present a method for using previously-trained 'teacher' agents to kickstart the training of a new 'student' agent. To this end, we leverage ideas from policy distillation and po…