| 25 July 2018 |
|
CVPR spotlight session |
Seeing Voices and Hearing Faces: Cross-modal biometric matching
Neural 3D Mesh Renderer
A Perceptual Measure for Deep Single Image Camera Calibration
Deep Depth Completion of a Single RGB-D Image
A Policy Blending Formalism for Shared Control
|
405, 66-72GS |
| 04 July 2018 |
|
CVPR spotlight session |
Real-Time Seamless Single Shot 6D Object Pose Prediction
Hybrid Camera Pose Estimation
Semi-parametric Image Synthesis
Who Let The Dogs Out? Modeling Dog Behavior From Visual Data
MoNet: Deep Motion Exploitation for Video Object Segmentation
UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
Fast and Accurate Online Video Object Segmentation via Tracking Parts
|
6.12a, MPEB |
| 27 June 2018 |
|
|
Spotlight session |
405, 66-72GS |
| 20 June 2018 |
Link |
David Walton |
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans |
405, 66-72GS |
| 6 June 2018 |
Link |
Stefano Blumberg |
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Oral at ICLR |
MPEB 6.12A |
| 30 May 2018 |
|
VRG Spotlight |
VRG Spotlight: 1 |
405, 66-72GS |
| 23 May 2018 |
Link |
Nafiseh Vahabi |
Learning to See in the Dark |
405, 66-72GS |
| 02 May 2018 |
Link |
Martin Rünz |
CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM |
6.12a, MPEB |
| 25 Apr 2018 |
Link |
Daniyar Turmukhambetov |
MobileNetV2: Inverted Residuals and Linear Bottlenecks |
405, 66-72GS |
| 11 Apr 2018 |
Link |
Tobias Ritschel |
Deep Appearance Maps |
6.12a, MPEB |
| 28 Mar 2018 |
Link |
Stephan Garbin |
The Numeric of GANs |
405, 66-72GS |
| 21 Mar 2018 |
Link |
Stratos Skordos |
Triplet-Center Loss for Multi-View 3D Object Retrieval |
6.12a, MPEB |
| 28 Feb 2018 |
Link |
Denis Tomé |
Image-based Synthesis for Deep 3D Human Pose Estimation |
6.12a, MPEB |
| 21 Feb 2018 |
Link |
Garoe Dorta |
The exploding gradient problem demystified - definition, prevalence, impact, origin, tradeoffs, and solutions |
405, 66-72GS |
| 27 Sept 2017 |
Link |
Daniyar Turmukhambetov |
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials |
6.12a, MPEB |
| 20 Sept 2017 |
|
|
BMVC and MICCAI roundup |
405, 66-72GS |
| 6 Sept 2017 |
|
Federico Monti |
Invited talk: Geometric Deep Learning, going beyond Euclidean structured data |
405, 66-72GS |
| 23 August 2017 |
Link |
Michael Firman |
Deep Active Learning |
6.12 MPEB |
| 19 July 2017 |
Link |
Rui Yu |
Inferring and Executing Programs for Visual Reasoning |
405, 66-72GS |
| 12 July 2017 |
Link |
Adrián Peñate Sanchez |
A Point Set Generation Network for 3D Object Reconstruction from a Single Image |
405, 66-72GS |
| 5 July 2017 |
Link |
Martin Rünz |
Towards Learned SLAM |
405, 66-72GS |
| 21 June 2017 |
Link |
Daniel Worrall |
Geodesic Convolutional Neural Networks on Riemannian Manifolds |
405, 66-72GS |
| 14 June 2017 |
Link |
Alina Bialkowski |
Learning Where to Attend Like a Human Driver |
405, 66-72GS |
| 7 June 2017 |
Link |
Stratos Skordos |
Deep Mutual Learning |
405, 66-72GS |
| 31 May 2017 |
|
VRG Spotlight |
Dilated residual networks,
Concrete Dropout
Categorical Reparameterization with Gumbel-Softmax
Discrete Variational Autoencoders
Deep Interactive Object Selection
Conditional Random Fields as Recurrent Neural Networks
Learning Shape Abstractions by Assembling Volumetric Primitives
Unsupervised Perceptual Rewards for Imitation Learning
| 405, 66-72GS |
| 17 May 2017 |
Link |
Michael Firman |
Image Colourisation: A Tutorial |
405, 66-72GS |
| 3 May 2017 |
Link |
Denis Tomé |
A Neural Representation of Sketch Drawings |
405, 66-72GS |
| 26 Apr 2017 |
|
Daniyar Turmukhambetov |
Towards Principled Methods for Training Generative Adversarial Networks |
405, 66-72GS |
| 12 Apr 2017 |
|
VRG Spotlight |
Sticking the Landing,
Scikit-Optimize,
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks,
DSAC - Differentiable RANSAC for Camera Localization,
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks,
Deep Bayesian Active Learning with Image Data,
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks |
405, 66-72GS |
| 5 Apr 2017 |
Link |
Stratos Skordos |
Synthesizing Training Images for Boosting Human 3D Pose Estimation |
405, 66-72GS |
| 29 Mar 2017 |
Link |
Garoe Dorta |
PixelVAE: A Latent Variable Model for Natural Images |
405, 66-72GS |
| 22 Mar 2017 |
|
Tom Haines |
- |
405, 66-72GS |
| 15 Mar 2017 |
|
ICCV Reading Party |
ICCV Reading Party |
405, 66-72GS |
| 8 Mar 2017 |
|
VRG Spotlight |
VRG Spotlight |
405, 66-72GS |
| 1 Mar 2017 |
Link |
Daniel Worrall |
Multiple-hypothesis affine region estimation with anisotropic LoG filters |
405, 66-72GS |
| 22 Feb 2017 |
|
Thanapong Intharah |
Help, It Looks Confusing: GUI Task Automation Through Demonstration and Follow-up Questions |
405, 66-72GS |
| 15 Feb 2017 |
Link |
Stephan Garbin |
Tracking the World State with Recurrent Entity Networks |
405, 66-72GS |
| 8 Feb 2017 |
|
VRG Spotlight |
VRG Spotlight |
405, 66-72GS |
| 1 Feb 2017 |
Link |
Adrián Peñate Sanchez |
SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks |
405, 66-72GS |
| 25 Jan 2017 |
Link |
Alina Bialkowski |
Learning Deep Features for Discriminative Localization |
405, 66-72GS |
| 18 Jan 2017 |
Link |
Michael Firman |
Unsupervised Learning of 3D Structure from Images |
405, 66-72GS |
| 14 Dec 2016 |
|
VRG Spotlight |
Secret Santa Extreme Reading Group |
405, 66-72GS |
| 7 Dec 2016 |
Link |
Daniel Worrall |
Transformation Properties of Learned Visual Representations |
405, 66-72GS |
| 30 Nov 2016 |
|
Alina Bialkowski |
- |
405, 66-72GS |
| 16 Nov 2016 |
|
VRG Spotlight |
VRG Spotlight |
405, 66-72GS |
| 9 Nov 2016 |
|
Reading Party |
Reading Party |
405, 66-72GS |
| 2 Nov 2016 |
|
Corneliu Ilisescu |
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals |
405, 66-72GS |
| 19 Oct 2016 |
|
VRG Spotlight |
VRG Spotlight |
405, 66-72GS |
| 5 Oct 2016 |
Link |
Zbigniew Wojna |
The latest image recognition and image detection models |
405, 66-72GS |
| 5 Oct 2016 |
|
Prof. Lourdes Agapito |
**1730-1930** Lourdes Agapito Inaugural Lecture |
1.02 LT MPEB |
| 28 Sep 2016 |
Link |
Stephan Garbin |
Prioritized Experience Replay |
6.12 MPEB |
| 21 Sep 2016 |
|
VRG Spotlight |
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,
Live Texturing of Augmented Reality Characters from Colored Drawings,
Live Repetition Counting,
Sinkhorn Distances: Lightspeed Computation Of Optimal Transportation Distances,
Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains,
A Scalable Active Framework for Region Annotation in 3D Shape Collections,
Data-dependent Initializations of Convolutional Neural Networks,
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks,
Deep Kinematic Pose Regression,
Grid Long Short-Term Memory |
405, 66-72GS |
| 14 Sep 2016 |
Link |
Daniyar Turmukhambetov |
Auto-Encoding Variational Bayes |
405, 66-72GS |
| 7 Sep 2016 |
Link |
Adrián Peñate Sanchez |
Joint Embeddings of Shapes and Images via CNN Image Purification |
405, 66-72GS |
| 31 Aug 2016 |
Link |
Denis Tomé |
SMPL: A Skinned Multi-Person Linear Model |
405, 66-72GS |
| 24 Aug 2016 |
|
Chris Russell |
Dense Monocular Depth Estimation in Complex Dynamic Scenes |
405, 66-72GS |
| 17 Aug 2016 |
|
VRG Spotlight |
VRG Spotlight |
405, 66-72GS |
| 10 Aug 2016 |
Link |
Martin Rünz |
Efficient 3D Object Segmentation from Densely Sampled Light Fields with Applications to 3D Reconstruction |
405, 66-72GS |
| 3 Aug 2016 |
Link |
Rui Yu |
Fusion4D: Real-time Performance Capture of Challenging Scenes |
405, 66-72GS |
| 27 Jul 2016 |
- |
VRG Spotlight |
Layer Normalization,
A Deep Learning Framework for Character Motion Synthesis and Editing,
Texture Networks: Feed-forward Synthesis of Textures and Stylized Images,
Perceptual Losses for Real-Time Style Transfer and Super-Resolution,
Transfiguring Portraits,
gvnn: Neural Network Library for Geometric Computer Vision |
405, 66-72GS |
| 20 Jul 2016 |
Link |
Aytac Kanaci |
Multi-target tracking by continuous energy minimization |
405, 66-72GS |
| 13 Jul 2016 |
Link |
Dr. Gabriel Brostow |
HyperDepth: Learning Depth from Structured Light Without Matching |
405, 66-72GS |
| 06 Jul 2016 |
Link |
Thanapong Intharah |
Unsupervised learning from narrated instruction videos |
405, 66-72GS |
| 22 Jun 2016 |
Link |
Stephan Garbin |
Handling Large Datasets with Alembic and OpenExr |
405, 66-72GS |
| 15 Jun 2016 |
Link |
Daniel Worrall |
Topmoumoute Online Natural Gradient Algorithm |
405, 66-72GS |
| 8 Jun 2016 |
Link |
Alina Bialkowski |
Convolutional Two-Stream Network Fusion for Video Action Recognition |
405, 66-72GS |
| 01 Jun 2016 |
Link |
Stratos Skordos |
Siamese Instance Search For Tracking |
405, 66-72GS |
| 18 May 2016 |
- |
Daniyar Turmukhambetov |
Phase-based Video Motion Processing |
405, 66-72GS |
| 04 May 2016 |
- |
Stephan Garbin |
Neural Turing Machines |
405, 66-72GS |
| 20 Apr 2016 |
Link |
Oisin Mac Aodha |
Training Region-based Object Detectors with Online Hard Example Mining |
405, 66-72GS |
| 06 Apr 2016 |
Link |
Michael Firman |
Generative Image Modeling using Style and Structure Adversarial Networks |
405, 66-72GS |
| 23 Mar 2016 |
Link |
Daniel Worrall |
Group Equivariant Convolutional Networks |
405, 66-72GS |