no code implementations • ICCV 2021 • Shivansh Patel, Saim Wani, Unnat Jain, Alexander Schwing, Svetlana Lazebnik, Manolis Savva, Angel X. Chang
We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment.
no code implementations • EMNLP 2021 • Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang
Prior work supervises the agent with actions based on the shortest path from the agent's location to the goal, but such goal-oriented supervision is often not in alignment with the instruction.
no code implementations • NeurIPS 2020 • Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang, Manolis Savva
We propose the multiON task, which requires navigation to an episode-specific sequence of objects in a realistic environment.
no code implementations • 13 Oct 2019 • Badri N. Patro, Shivansh Patel, Vinay P. Namboodiri
Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task.
no code implementations • ICCV 2019 • Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri
These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions.