Showing 31 publications by Siddharth Narayanaswamy
Capturing label characteristics in VAEs
Joy T, Schmon S, Torr P, Narayanaswamy S & Rainforth T (2021), Proceedings of the International Conference on Learning Representations (ICLR 2020)
BibTeX
@inproceedings{capturinglabelc-2021/3,
title={Capturing label characteristics in VAEs},
author={Joy T, Schmon S, Torr P, Narayanaswamy S & Rainforth T},
booktitle={International Conference on Learning Representations},
year = "2021"
}
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Shi Y, Paige B, Torr PHS & Siddharth N (2020)
BibTeX
@article{relatingbycontr-2020/7,
title={Relating by Contrasting: A Data-efficient Framework for Multimodal
Generative Models},
author={Shi Y, Paige B, Torr PHS & Siddharth N},
journal={},
year = "2020"
}
Capturing Label Characteristics in VAEs
Joy T, Schmon SM, Torr PHS, Siddharth N & Rainforth T (2020)
BibTeX
@article{capturinglabelc-2020/6,
title={Capturing Label Characteristics in VAEs},
author={Joy T, Schmon SM, Torr PHS, Siddharth N & Rainforth T},
journal={},
year = "2020"
}
Simulation-Based Inference for Global Health Decisions
de Witt CS, Gram-Hansen B, Nardelli N, Gambardella A, Zinkov R et al. (2020), ICML Workshop on Machine Learning for Global Health, Thirty-Seventh International Conference on Machine Learning (ICML 2020)
BibTeX
@article{simulationbased-2020/5,
title={Simulation-Based Inference for Global Health Decisions},
author={de Witt CS, Gram-Hansen B, Nardelli N, Gambardella A, Zinkov R et al.},
journal={ICML Workshop on Machine Learning for Global Health,
Thirty-Seventh International Conference on Machine Learning (ICML 2020)},
year = "2020"
}
DGPose: Deep Generative Models for Human Body Analysis
de Bem R, Ghosh A, Ajanthan T, Miksik O, Boukhayma A et al. (2020), International Journal of Computer Vision, 128(2020), 1537-1563
A Revised Generative Evaluation of Visual Dialogue
Massiceti D, Kulharia V, Dokania PK, Siddharth N & Torr PHS (2020)
Variational mixture-of-experts autoencoders for multi-modal deep generative models
Shi Y, Siddharth N, Paige B & Torr P (2019), Neural Information Processing Systems 2019
BibTeX
@inproceedings{variationalmixt-2019/12,
title={Variational mixture-of-experts autoencoders for multi-modal deep generative models},
author={Shi Y, Siddharth N, Paige B & Torr P},
year = "2019"
}
Multitask Soft Option Learning
Igl M, Gambardella A, He J, Nardelli N, Siddharth N et al. (2019)
BibTeX
@article{multitasksoftop-2019/4,
title={Multitask Soft Option Learning},
author={Igl M, Gambardella A, He J, Nardelli N, Siddharth N et al.},
journal={},
year = "2019"
}
Revisiting reweighted wake-sleep for models with stochastic control flow
Le TA, Kosiorek AR, Siddharth N, Teh YEE & Wood F (2019), 35th Conference on Uncertainty in Artificial Intelligence, UAI 2019
BibTeX
@inproceedings{revisitingrewei-2019/1,
title={Revisiting reweighted wake-sleep for models with stochastic control flow},
author={Le TA, Kosiorek AR, Siddharth N, Teh YEE & Wood F},
year = "2019"
}
A semi-supervised deep generative model for human body analysis
De Bem R, Ghosh A, Ajanthan T, Miksik O, Narayanaswamy S et al. (2019), ECCV 2018: Computer Vision ??? ECCV 2018 Workshops, 11130, 500-517
Disentangling disentanglement in variational autoencoders
Mathieu E, Rainforth T, Siddharth N & Teh YW (2019), 36th International Conference on Machine Learning, ICML 2019, 2019-June, 7744-7754
BibTeX
@inproceedings{disentanglingdi-2019/1,
title={Disentangling disentanglement in variational autoencoders},
author={Mathieu E, Rainforth T, Siddharth N & Teh YW},
pages={7744-7754},
year = "2019"
}
FLIPDIAL: A generative model for two-way visual dialogue
Massiceti D, Narayanaswamy S, Torr P & Dokania P (2018), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Salt Lake City, Utah, June 18-22, 2018
Learning disentangled representations with semi-supervised deep generative models
Siddharth N, Paige B, Van De Meent JW, Desmaison A, Goodman ND et al. (2018), Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), 30, 5927-5937
BibTeX
@inproceedings{learningdisenta-2018/6,
title={Learning disentangled representations with semi-supervised deep generative models},
author={Siddharth N, Paige B, Van De Meent JW, Desmaison A, Goodman ND et al.},
pages={5927-5937},
year = "2018"
}
Structured Disentangled Representations
Esmaeili B, Wu H, Jain S, Bozkurt A, Siddharth N et al. (2018)
BibTeX
@inproceedings{structureddisen-2018/4,
title={Structured Disentangled Representations},
author={Esmaeili B, Wu H, Jain S, Bozkurt A, Siddharth N et al.},
year = "2018"
}
Faithful inversion of generative models for effective amortized inference
Webb S, Goli??ski A, Zinkov R, RAINFORTH T, NARAYANASWAMY S et al. (2018), Advances in Neural Information Processing Systems
BibTeX
@inproceedings{faithfulinversi-2018/1,
title={Faithful inversion of generative models for effective amortized inference},
author={Webb S, Goli??ski A, Zinkov R, RAINFORTH T, NARAYANASWAMY S et al.},
booktitle={Neural Information Processing Systems (NIPS)},
year = "2018"
}
Playing Doom with SLAM-Augmented Deep Reinforcement Learning
Bhatti S, Desmaison A, Miksik O, Nardelli N, Siddharth N et al. (2016)
BibTeX
@article{playingdoomwith-2016/12,
title={Playing Doom with SLAM-Augmented Deep Reinforcement Learning},
author={Bhatti S, Desmaison A, Miksik O, Nardelli N, Siddharth N et al.},
journal={},
year = "2016"
}
Inducing Interpretable Representations with Variational Autoencoders
Siddharth N, Paige B, Desmaison A, Meent J-WVD, Wood F et al. (2016)
BibTeX
@article{inducinginterpr-2016/11,
title={Inducing Interpretable Representations with Variational Autoencoders},
author={Siddharth N, Paige B, Desmaison A, Meent J-WVD, Wood F et al.},
journal={},
year = "2016"
}
Saying What You're Looking For: Linguistics Meets Video Search.
Barrett DP, Barbu A, Siddharth N & Siskind JM (2016), IEEE transactions on pattern analysis and machine intelligence, 38(10), 2069-2081
Coarse-to-Fine Sequential Monte Carlo for Probabilistic Programs
Stuhlm??ller A, Hawkins RXD, Siddharth N & Goodman ND (2015)
BibTeX
@article{coarsetofineseq-2015/9,
title={Coarse-to-Fine Sequential Monte Carlo for Probabilistic Programs},
author={Stuhlm??ller A, Hawkins RXD, Siddharth N & Goodman ND},
journal={},
year = "2015"
}
Seeing is <i>Worse</i> than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions
Barbu A, Barrett DP, Chen W, Siddharth N, Xiong C et al. (2014), COMPUTER VISION - ECCV 2014, PT V, 8693, 612-627
BibTeX
@inproceedings{seeingisiworsei-2014/,
title={Seeing is <i>Worse</i> than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions},
author={Barbu A, Barrett DP, Chen W, Siddharth N, Xiong C et al.},
pages={612-627},
year = "2014"
}
The Compositional Nature of Verb and Argument Representations in the Human Brain
Barbu A, Siddharth N, Xiong C, Corso JJ, Fellbaum CD et al. (2013)
BibTeX
@article{thecompositiona-2013/6,
title={The Compositional Nature of Verb and Argument Representations in the
Human Brain},
author={Barbu A, Siddharth N, Xiong C, Corso JJ, Fellbaum CD et al.},
journal={},
year = "2013"
}
Video in sentences out
Barbu A, Bridge A, Burchill Z, Coroian D, Dickinson S et al. (2012), Uncertainty in Artificial Intelligence - Proceedings of the 28th Conference, UAI 2012, 102-112
BibTeX
@inproceedings{videoinsentence-2012/12,
title={Video in sentences out},
author={Barbu A, Bridge A, Burchill Z, Coroian D, Dickinson S et al.},
pages={102-112},
year = "2012"
}
Simultaneous Object Detection, Tracking, and Event Recognition
Barbu A, Michaux A, Narayanaswamy S & Siskind JM (2012), Advances in Cognitive Systems, 2, 203-220
BibTeX
@article{simultaneousobj-2012/12,
title={Simultaneous Object Detection, Tracking, and Event Recognition},
author={Barbu A, Michaux A, Narayanaswamy S & Siskind JM},
journal={Advances in Cognitive Systems},
volume={2},
pages={203-220},
year = "2012"
}
Large-Scale Automatic Labeling of Video Events with Verbs Based on Event-Participant Interaction
Barbu A, Bridge A, Coroian D, Dickinson S, Mussman S et al. (2012)
A visual language model for estimating object pose and structure in a generative visual domain
Narayanaswamy S, Barbu A & Siskind JM (2011), 4854-4860
BibTeX
@inproceedings{avisuallanguage-2011/5,
title={A visual language model for estimating object pose and structure in a generative visual domain},
author={Narayanaswamy S, Barbu A & Siskind JM},
booktitle={2011 IEEE International Conference on Robotics and Automation},
pages={4854-4860},
year = "2011"
}
Learning Physically-Instantiated Game Play Through Visual Observation
Barbu A, Narayanaswamy S & Siskind JM (2010), 1879-1886
A Compositional Framework for Grounding Language Inference, Generation, and Acquisition in Video
Yu H, Siddharth N, Barbu A & Siskind JM (0), Journal of Artificial Intelligence Research, 52, 601-713
BibTeX
@article{acompositionalf-/,
title={A Compositional Framework for Grounding Language Inference, Generation, and Acquisition in Video},
author={Yu H, Siddharth N, Barbu A & Siskind JM},
journal={Journal of Artificial Intelligence Research},
volume={52},
pages={601-713},
publisher={AI Access Foundation}
}
Recognize Human Activities from Partially Observed Videos
Cao Y, Barrett D, Barbu A, Narayanaswamy S, Yu H et al. (0), 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2658-2665
Seeing What You're Told: Sentence-Guided Activity Recognition In Video
Siddharth N, Barbu A & Siskind JM (0)
BibTeX
@inproceedings{seeingwhatyoure-/,
title={Seeing What You're Told: Sentence-Guided Activity Recognition In Video},
author={Siddharth N, Barbu A & Siskind JM},
booktitle={Computer Vision and Pattern Recognition (CVPR)}
}