Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Asim Kadav

Asim Kadav

Hopper: Multi-hop Transformer for Spatiotemporal Reasoning


Mar 22, 2021
Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf

Figure 1 for Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
Figure 2 for Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
Figure 3 for Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
Figure 4 for Hopper: Multi-hop Transformer for Spatiotemporal Reasoning

  Access Paper or Ask Questions

S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation


May 23, 2020
Yizhe Zhu, Martin Renqiang Min, Asim Kadav, Hans Peter Graf

Figure 1 for S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
Figure 2 for S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
Figure 3 for S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
Figure 4 for S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
* to appear in CVPR2020 
  Access Paper or Ask Questions

15 Keypoints Is All You Need


Dec 05, 2019
Michael Snower, Asim Kadav, Farley Lai, Hans Peter Graf

Figure 1 for 15 Keypoints Is All You Need
Figure 2 for 15 Keypoints Is All You Need
Figure 3 for 15 Keypoints Is All You Need
Figure 4 for 15 Keypoints Is All You Need

  Access Paper or Ask Questions

Contextual Grounding of Natural Language Entities in Images


Nov 05, 2019
Farley Lai, Ning Xie, Derek Doran, Asim Kadav

Figure 1 for Contextual Grounding of Natural Language Entities in Images
Figure 2 for Contextual Grounding of Natural Language Entities in Images
Figure 3 for Contextual Grounding of Natural Language Entities in Images
Figure 4 for Contextual Grounding of Natural Language Entities in Images
* Accepted to NeurIPS 2019 workshop on Visually Grounded Interaction and Language (ViGIL) 
  Access Paper or Ask Questions

Tripping through time: Efficient Localization of Activities in Videos


Apr 25, 2019
Meera Hahn, Asim Kadav, James M. Rehg, Hans Peter Graf

Figure 1 for Tripping through time: Efficient Localization of Activities in Videos
Figure 2 for Tripping through time: Efficient Localization of Activities in Videos
Figure 3 for Tripping through time: Efficient Localization of Activities in Videos
Figure 4 for Tripping through time: Efficient Localization of Activities in Videos

  Access Paper or Ask Questions

Visual Entailment: A Novel Task for Fine-Grained Image Understanding


Jan 20, 2019
Ning Xie, Farley Lai, Derek Doran, Asim Kadav

Figure 1 for Visual Entailment: A Novel Task for Fine-Grained Image Understanding
Figure 2 for Visual Entailment: A Novel Task for Fine-Grained Image Understanding
Figure 3 for Visual Entailment: A Novel Task for Fine-Grained Image Understanding
Figure 4 for Visual Entailment: A Novel Task for Fine-Grained Image Understanding

  Access Paper or Ask Questions

Visual Entailment Task for Visually-Grounded Language Learning


Nov 26, 2018
Ning Xie, Farley Lai, Derek Doran, Asim Kadav

Figure 1 for Visual Entailment Task for Visually-Grounded Language Learning
Figure 2 for Visual Entailment Task for Visually-Grounded Language Learning
Figure 3 for Visual Entailment Task for Visually-Grounded Language Learning
Figure 4 for Visual Entailment Task for Visually-Grounded Language Learning
* 4 pages, accepted by NIPS 2018 Visually Grounded Interaction and Language (ViGIL) workshop 
  Access Paper or Ask Questions

Teaching Syntax by Adversarial Distraction


Oct 25, 2018
Juho Kim, Christopher Malon, Asim Kadav

Figure 1 for Teaching Syntax by Adversarial Distraction
Figure 2 for Teaching Syntax by Adversarial Distraction
Figure 3 for Teaching Syntax by Adversarial Distraction
* Juho Kim, Christopher Malon, and Asim Kadav. 2018. "Teaching Syntax by Adversarial Distraction." Proceedings of the EMNLP First Workshop on Fact Extraction and Verification 
 * To appear at the EMNLP 2018 First Workshop on Fact Extraction and Verification (FEVER) 
  Access Paper or Ask Questions

Attend and Interact: Higher-Order Object Interactions for Video Understanding


Mar 20, 2018
Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, Hans Peter Graf

Figure 1 for Attend and Interact: Higher-Order Object Interactions for Video Understanding
Figure 2 for Attend and Interact: Higher-Order Object Interactions for Video Understanding
Figure 3 for Attend and Interact: Higher-Order Object Interactions for Video Understanding
Figure 4 for Attend and Interact: Higher-Order Object Interactions for Video Understanding
* CVPR 2018 
  Access Paper or Ask Questions

Adaptive Memory Networks


Feb 01, 2018
Daniel Li, Asim Kadav

Figure 1 for Adaptive Memory Networks
Figure 2 for Adaptive Memory Networks
Figure 3 for Adaptive Memory Networks
Figure 4 for Adaptive Memory Networks

  Access Paper or Ask Questions

DeepConfig: Automating Data Center Network Topologies Management with Machine Learning


Dec 11, 2017
Christopher Streiffer, Huan Chen, Theophilus Benson, Asim Kadav

Figure 1 for DeepConfig: Automating Data Center Network Topologies Management with Machine Learning
Figure 2 for DeepConfig: Automating Data Center Network Topologies Management with Machine Learning
Figure 3 for DeepConfig: Automating Data Center Network Topologies Management with Machine Learning
Figure 4 for DeepConfig: Automating Data Center Network Topologies Management with Machine Learning

  Access Paper or Ask Questions

Grounded Objects and Interactions for Video Captioning


Nov 16, 2017
Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, Hans Peter Graf

Figure 1 for Grounded Objects and Interactions for Video Captioning
Figure 2 for Grounded Objects and Interactions for Video Captioning
Figure 3 for Grounded Objects and Interactions for Video Captioning
Figure 4 for Grounded Objects and Interactions for Video Captioning
* arXiv admin note: substantial text overlap with arXiv:1711.06330 
  Access Paper or Ask Questions

A Context-aware Attention Network for Interactive Question Answering


Sep 03, 2017
Huayu Li, Martin Renqiang Min, Yong Ge, Asim Kadav

Figure 1 for A Context-aware Attention Network for Interactive Question Answering
Figure 2 for A Context-aware Attention Network for Interactive Question Answering
Figure 3 for A Context-aware Attention Network for Interactive Question Answering
Figure 4 for A Context-aware Attention Network for Interactive Question Answering
* 9 pages 
  Access Paper or Ask Questions

Pruning Filters for Efficient ConvNets


Mar 10, 2017
Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf

Figure 1 for Pruning Filters for Efficient ConvNets
Figure 2 for Pruning Filters for Efficient ConvNets
Figure 3 for Pruning Filters for Efficient ConvNets
Figure 4 for Pruning Filters for Efficient ConvNets
* Published as a conference paper at ICLR 2017 
  Access Paper or Ask Questions

ASAP: Asynchronous Approximate Data-Parallel Computation


Dec 27, 2016
Asim Kadav, Erik Kruus

Figure 1 for ASAP: Asynchronous Approximate Data-Parallel Computation
Figure 2 for ASAP: Asynchronous Approximate Data-Parallel Computation
Figure 3 for ASAP: Asynchronous Approximate Data-Parallel Computation
Figure 4 for ASAP: Asynchronous Approximate Data-Parallel Computation

  Access Paper or Ask Questions