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 Stephen Gould

Stephen Gould

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer


Dec 03, 2021
Frederic Z. Zhang, Dylan Campbell, Stephen Gould

Figure 1 for Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
Figure 2 for Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
Figure 3 for Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
Figure 4 for Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
* 14 pages, 14 figures and 5 tables 
  Access Paper or Ask Questions

A Regularized Wasserstein Framework for Graph Kernels


Oct 08, 2021
Asiri Wijesinghe, Qing Wang, Stephen Gould

Figure 1 for A Regularized Wasserstein Framework for Graph Kernels
Figure 2 for A Regularized Wasserstein Framework for Graph Kernels
Figure 3 for A Regularized Wasserstein Framework for Graph Kernels
Figure 4 for A Regularized Wasserstein Framework for Graph Kernels
* 21st IEEE International Conference on Data Mining (ICDM 2021) 
  Access Paper or Ask Questions

Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models


Aug 09, 2021
Zheyuan Liu, Cristian Rodriguez-Opazo, Damien Teney, Stephen Gould

Figure 1 for Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Figure 2 for Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Figure 3 for Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Figure 4 for Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
* ICCV 2021. Dataset, code, and pre-trained models are released at https://cuberick-orion.github.io/CIRR/ 
  Access Paper or Ask Questions

DiGS : Divergence guided shape implicit neural representation for unoriented point clouds


Jun 21, 2021
Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, Stephen Gould

Figure 1 for DiGS : Divergence guided shape implicit neural representation for unoriented point clouds
Figure 2 for DiGS : Divergence guided shape implicit neural representation for unoriented point clouds
Figure 3 for DiGS : Divergence guided shape implicit neural representation for unoriented point clouds
Figure 4 for DiGS : Divergence guided shape implicit neural representation for unoriented point clouds

  Access Paper or Ask Questions

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?


Jun 10, 2021
Weijian Deng, Stephen Gould, Liang Zheng

Figure 1 for What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Figure 2 for What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Figure 3 for What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Figure 4 for What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
* ICML 2021 camera ready 
  Access Paper or Ask Questions

Semantics for Robotic Mapping, Perception and Interaction: A Survey


Jan 02, 2021
Sourav Garg, Niko Sünderhauf, Feras Dayoub, Douglas Morrison, Akansel Cosgun, Gustavo Carneiro, Qi Wu, Tat-Jun Chin, Ian Reid, Stephen Gould, Peter Corke, Michael Milford

Figure 1 for Semantics for Robotic Mapping, Perception and Interaction: A Survey
Figure 2 for Semantics for Robotic Mapping, Perception and Interaction: A Survey
* Foundations and Trends in Robotics: Vol. 8: No. 1-2, pp 1-224 (2020) 
 * 81 pages, 1 figure, published in Foundations and Trends in Robotics, 2020 
  Access Paper or Ask Questions

Fine-grained Classification via Categorical Memory Networks


Dec 12, 2020
Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng

Figure 1 for Fine-grained Classification via Categorical Memory Networks
Figure 2 for Fine-grained Classification via Categorical Memory Networks
Figure 3 for Fine-grained Classification via Categorical Memory Networks
Figure 4 for Fine-grained Classification via Categorical Memory Networks
* 10 pages, 9 figures, 7 tables; this version is not fully edited and will be updated soon 
  Access Paper or Ask Questions

Spatio-attentive Graphs for Human-Object Interaction Detection


Dec 11, 2020
Frederic Z. Zhang, Dylan Campbell, Stephen Gould

Figure 1 for Spatio-attentive Graphs for Human-Object Interaction Detection
Figure 2 for Spatio-attentive Graphs for Human-Object Interaction Detection
Figure 3 for Spatio-attentive Graphs for Human-Object Interaction Detection
Figure 4 for Spatio-attentive Graphs for Human-Object Interaction Detection

  Access Paper or Ask Questions

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking


Dec 10, 2020
Fatemeh Saleh, Sadegh Aliakbarian, Hamid Rezatofighi, Mathieu Salzmann, Stephen Gould

Figure 1 for Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Figure 2 for Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Figure 3 for Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Figure 4 for Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

  Access Paper or Ask Questions

How to train your conditional GAN: An approach using geometrically structured latent manifolds


Nov 30, 2020
Sameera Ramasinghe, Moshiur Farazi, Salman Khan, Nick Barnes, Stephen Gould

Figure 1 for How to train your conditional GAN: An approach using geometrically structured latent manifolds
Figure 2 for How to train your conditional GAN: An approach using geometrically structured latent manifolds
Figure 3 for How to train your conditional GAN: An approach using geometrically structured latent manifolds
Figure 4 for How to train your conditional GAN: An approach using geometrically structured latent manifolds

  Access Paper or Ask Questions

A Recurrent Vision-and-Language BERT for Navigation


Nov 26, 2020
Yicong Hong, Qi Wu, Yuankai Qi, Cristian Rodriguez-Opazo, Stephen Gould

Figure 1 for A Recurrent Vision-and-Language BERT for Navigation
Figure 2 for A Recurrent Vision-and-Language BERT for Navigation
Figure 3 for A Recurrent Vision-and-Language BERT for Navigation
Figure 4 for A Recurrent Vision-and-Language BERT for Navigation

  Access Paper or Ask Questions

Language and Visual Entity Relationship Graph for Agent Navigation


Oct 19, 2020
Yicong Hong, Cristian Rodriguez-Opazo, Yuankai Qi, Qi Wu, Stephen Gould

Figure 1 for Language and Visual Entity Relationship Graph for Agent Navigation
Figure 2 for Language and Visual Entity Relationship Graph for Agent Navigation
Figure 3 for Language and Visual Entity Relationship Graph for Agent Navigation
Figure 4 for Language and Visual Entity Relationship Graph for Agent Navigation

  Access Paper or Ask Questions

DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video


Oct 13, 2020
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen Gould

Figure 1 for DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
Figure 2 for DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
Figure 3 for DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
Figure 4 for DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video

  Access Paper or Ask Questions

Conditional Generative Modeling via Learning the Latent Space


Oct 09, 2020
Sameera Ramasinghe, Kanchana Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould

Figure 1 for Conditional Generative Modeling via Learning the Latent Space
Figure 2 for Conditional Generative Modeling via Learning the Latent Space
Figure 3 for Conditional Generative Modeling via Learning the Latent Space
Figure 4 for Conditional Generative Modeling via Learning the Latent Space

  Access Paper or Ask Questions

Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization


Jul 29, 2020
Dylan Campbell, Liu Liu, Stephen Gould

Figure 1 for Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
Figure 2 for Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
Figure 3 for Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
Figure 4 for Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
* Accepted at ECCV 2020 (Oral) 
  Access Paper or Ask Questions

Multiview Detection with Feature Perspective Transformation


Jul 14, 2020
Yunzhong Hou, Liang Zheng, Stephen Gould

Figure 1 for Multiview Detection with Feature Perspective Transformation
Figure 2 for Multiview Detection with Feature Perspective Transformation
Figure 3 for Multiview Detection with Feature Perspective Transformation
Figure 4 for Multiview Detection with Feature Perspective Transformation

  Access Paper or Ask Questions

The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose


Jul 01, 2020
Yizhak Ben-Shabat, Xin Yu, Fatemeh Sadat Saleh, Dylan Campbell, Cristian Rodriguez-Opazo, Hongdong Li, Stephen Gould

Figure 1 for The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
Figure 2 for The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
Figure 3 for The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
Figure 4 for The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

  Access Paper or Ask Questions

Bidirectional Self-Normalizing Neural Networks


Jun 22, 2020
Yao Lu, Stephen Gould, Thalaiyasingam Ajanthan

Figure 1 for Bidirectional Self-Normalizing Neural Networks
Figure 2 for Bidirectional Self-Normalizing Neural Networks
Figure 3 for Bidirectional Self-Normalizing Neural Networks
Figure 4 for Bidirectional Self-Normalizing Neural Networks

  Access Paper or Ask Questions

A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews


May 28, 2020
Edison Marrese-Taylor, Cristian Rodriguez-Opazo, Jorge A. Balazs, Stephen Gould, Yutaka Matsuo

Figure 1 for A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
Figure 2 for A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
Figure 3 for A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
Figure 4 for A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
* Second Grand Challenge and Workshop on Multimodal Language ACL 2020 
  Access Paper or Ask Questions

Inferring Temporal Compositions of Actions Using Probabilistic Automata


Apr 28, 2020
Rodrigo Santa Cruz, Anoop Cherian, Basura Fernando, Dylan Campbell, Stephen Gould

Figure 1 for Inferring Temporal Compositions of Actions Using Probabilistic Automata
Figure 2 for Inferring Temporal Compositions of Actions Using Probabilistic Automata
Figure 3 for Inferring Temporal Compositions of Actions Using Probabilistic Automata
Figure 4 for Inferring Temporal Compositions of Actions Using Probabilistic Automata
* Accepted in Workshop on Compositionality in Computer Vision at CVPR, 2020 
  Access Paper or Ask Questions

ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking


Apr 16, 2020
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Stephen Gould

Figure 1 for ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
Figure 2 for ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
Figure 3 for ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
Figure 4 for ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking

  Access Paper or Ask Questions

Sub-Instruction Aware Vision-and-Language Navigation


Apr 06, 2020
Yicong Hong, Cristian Rodriguez-Opazo, Qi Wu, Stephen Gould

Figure 1 for Sub-Instruction Aware Vision-and-Language Navigation
Figure 2 for Sub-Instruction Aware Vision-and-Language Navigation
Figure 3 for Sub-Instruction Aware Vision-and-Language Navigation
Figure 4 for Sub-Instruction Aware Vision-and-Language Navigation

  Access Paper or Ask Questions

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares


Mar 23, 2020
Yizhak Ben-Shabat, Stephen Gould

Figure 1 for DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
Figure 2 for DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
Figure 3 for DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
Figure 4 for DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
* arXiv admin note: text overlap with arXiv:1812.00709 
  Access Paper or Ask Questions

Learning to Structure an Image with Few Colors


Mar 17, 2020
Yunzhong Hou, Liang Zheng, Stephen Gould

Figure 1 for Learning to Structure an Image with Few Colors
Figure 2 for Learning to Structure an Image with Few Colors
Figure 3 for Learning to Structure an Image with Few Colors
Figure 4 for Learning to Structure an Image with Few Colors

  Access Paper or Ask Questions

Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization


Feb 26, 2020
Shihao Jiang, Dylan Campbell, Miaomiao Liu, Stephen Gould, Richard Hartley

Figure 1 for Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization
Figure 2 for Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization
Figure 3 for Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization
Figure 4 for Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization

  Access Paper or Ask Questions

Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior


Dec 18, 2019
Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann, Lars Petersson, Stephen Gould

Figure 1 for Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior
Figure 2 for Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior
Figure 3 for Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior
Figure 4 for Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior

  Access Paper or Ask Questions

Spectral-GANs for High-Resolution 3D Point-cloud Generation


Dec 04, 2019
Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould

Figure 1 for Spectral-GANs for High-Resolution 3D Point-cloud Generation
Figure 2 for Spectral-GANs for High-Resolution 3D Point-cloud Generation
Figure 3 for Spectral-GANs for High-Resolution 3D Point-cloud Generation
Figure 4 for Spectral-GANs for High-Resolution 3D Point-cloud Generation

  Access Paper or Ask Questions

Representation Learning on Unit Ball with 3D Roto-Translational Equivariance


Nov 30, 2019
Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould

Figure 1 for Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
Figure 2 for Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
Figure 3 for Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
Figure 4 for Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
* arXiv admin note: text overlap with arXiv:1901.00616 
  Access Paper or Ask Questions

Deep Declarative Networks: A New Hope


Sep 11, 2019
Stephen Gould, Richard Hartley, Dylan Campbell

Figure 1 for Deep Declarative Networks: A New Hope
Figure 2 for Deep Declarative Networks: A New Hope
Figure 3 for Deep Declarative Networks: A New Hope
Figure 4 for Deep Declarative Networks: A New Hope

  Access Paper or Ask Questions

Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes


Aug 24, 2019
Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould

Figure 1 for Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
Figure 2 for Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
Figure 3 for Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
Figure 4 for Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes

  Access Paper or Ask Questions