Alert button
Picture for Satwik Kottur

Satwik Kottur

Alert button

Situated and Interactive Multimodal Conversations

Jun 02, 2020
Seungwhan Moon, Satwik Kottur, Paul A. Crook, Ankita De, Shivani Poddar, Theodore Levin, David Whitney, Daniel Difranco, Ahmad Beirami, Eunjoon Cho, Rajen Subba, Alborz Geramifard

Figure 1 for Situated and Interactive Multimodal Conversations
Figure 2 for Situated and Interactive Multimodal Conversations
Figure 3 for Situated and Interactive Multimodal Conversations
Figure 4 for Situated and Interactive Multimodal Conversations
Viaarxiv icon

On Emergent Communication in Competitive Multi-Agent Teams

Mar 04, 2020
Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur

Figure 1 for On Emergent Communication in Competitive Multi-Agent Teams
Figure 2 for On Emergent Communication in Competitive Multi-Agent Teams
Figure 3 for On Emergent Communication in Competitive Multi-Agent Teams
Figure 4 for On Emergent Communication in Competitive Multi-Agent Teams
Viaarxiv icon

CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog

Mar 07, 2019
Satwik Kottur, José M. F. Moura, Devi Parikh, Dhruv Batra, Marcus Rohrbach

Figure 1 for CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
Figure 2 for CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
Figure 3 for CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
Figure 4 for CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
Viaarxiv icon

Visual Coreference Resolution in Visual Dialog using Neural Module Networks

Sep 06, 2018
Satwik Kottur, José M. F. Moura, Devi Parikh, Dhruv Batra, Marcus Rohrbach

Figure 1 for Visual Coreference Resolution in Visual Dialog using Neural Module Networks
Figure 2 for Visual Coreference Resolution in Visual Dialog using Neural Module Networks
Figure 3 for Visual Coreference Resolution in Visual Dialog using Neural Module Networks
Figure 4 for Visual Coreference Resolution in Visual Dialog using Neural Module Networks
Viaarxiv icon

Deep Sets

Apr 14, 2018
Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabas Poczos, Ruslan Salakhutdinov, Alexander Smola

Figure 1 for Deep Sets
Figure 2 for Deep Sets
Figure 3 for Deep Sets
Figure 4 for Deep Sets
Viaarxiv icon

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

Aug 20, 2017
Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra

Figure 1 for Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
Figure 2 for Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
Figure 3 for Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
Figure 4 for Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
Viaarxiv icon

Visual Dialog

Aug 01, 2017
Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, José M. F. Moura, Devi Parikh, Dhruv Batra

Figure 1 for Visual Dialog
Figure 2 for Visual Dialog
Figure 3 for Visual Dialog
Figure 4 for Visual Dialog
Viaarxiv icon

Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning

Mar 21, 2017
Abhishek Das, Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra

Figure 1 for Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Figure 2 for Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Figure 3 for Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Figure 4 for Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Viaarxiv icon

Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes

Jun 29, 2016
Satwik Kottur, Ramakrishna Vedantam, José M. F. Moura, Devi Parikh

Figure 1 for Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
Figure 2 for Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
Figure 3 for Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
Figure 4 for Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
Viaarxiv icon