5 papers
A Revised Generative Evaluation of Visual Dialogue
Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania +2
Evaluating Visual Dialogue, the task of answering a sequence of questions relating to a visual input, remains an open research challenge. The current evaluation scheme of the VisDi…
Lessons from reinforcement learning for biological representations of space
Alex Muryy, N. Siddharth, Nantas Nardelli +2
Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in re…
Multitask Soft Option Learning
Maximilian Igl, Andrew Gambardella, Jinke He +4
We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational…
Visual Dialogue without Vision or Dialogue
Daniela Massiceti, Puneet K. Dokania, N. Siddharth +1
We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are r…
The Compositional Nature of Event Representations in the Human Brain
Andrei Barbu, N. Siddharth, Caiming Xiong +10
How does the human brain represent simple compositions of constituents: actors, verbs, objects, directions, and locations? Subjects viewed videos during neuroimaging (fMRI) session…