Search Results for author: Allan Jepson

Found 13 papers, 3 papers with code

Efficient Flow-Guided Multi-frame De-fencing

no code implementations25 Jan 2023 Stavros Tsogkas, Fengjia Zhang, Allan Jepson, Alex Levinshtein

Taking photographs ''in-the-wild'' is often hindered by fence obstructions that stand between the camera user and the scene of interest, and which are hard or impossible to avoid.

Image Inpainting

Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations

no code implementations20 Apr 2022 Leila Pishdad, Ran Zhang, Konstantinos G. Derpanis, Allan Jepson, Afsaneh Fazly

Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching.

Image Retrieval Image-text matching +2

Approximate Policy Iteration with Bisimulation Metrics

1 code implementation6 Feb 2022 Mete Kemertas, Allan Jepson

Based on these results, we design an API($\alpha$) procedure that employs conservative policy updates and enjoys better performance bounds than the naive API approach.

Continuous Control Representation Learning

Representing 3D Shapes with Probabilistic Directed Distance Fields

no code implementations CVPR 2022 Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

On the other hand, implicit representations (occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability.

3D Reconstruction

GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks

no code implementations4 Nov 2021 Vineeth S. Bhaskara, Tristan Aumentado-Armstrong, Allan Jepson, Alex Levinshtein

Under such a class of discriminator (or critic) functions, we present Gradient Normalization (GraN), a novel input-dependent normalization method, which guarantees a piecewise K-Lipschitz constraint in the input space.

Image Generation

Dependency parsing with structure preserving embeddings

no code implementations EACL 2021 {\'A}kos K{\'a}d{\'a}r, Lan Xiao, Mete Kemertas, Federico Fancellu, Allan Jepson, Afsaneh Fazly

We do so by casting dependency parsing as a tree embedding problem where we incorporate geometric properties of dependency trees in the form of training losses within a graph-based parser.

Dependency Parsing Sentence

Disentangling Geometric Deformation Spaces in Generative Latent Shape Models

no code implementations27 Feb 2021 Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

In this work, we improve on a prior generative model of geometric disentanglement for 3D shapes, wherein the space of object geometry is factorized into rigid orientation, non-rigid pose, and intrinsic shape.

Disentanglement Pose Transfer +1

Probabilistic Multimodal Representation Learning

no code implementations1 Jan 2021 Leila Pishdad, Ran Zhang, Afsaneh Fazly, Allan Jepson

Learning multimodal representations is a requirement for many tasks such as image--caption retrieval.

Representation Learning Retrieval

Geometric Disentanglement for Generative Latent Shape Models

no code implementations ICCV 2019 Tristan Aumentado-Armstrong, Stavros Tsogkas, Allan Jepson, Sven Dickinson

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics.

3D Object Retrieval 3D Shape Generation +4

Cannot find the paper you are looking for? You can Submit a new open access paper.