30 citations · 80 across the 11 of their papers we have counts for
11 papers
Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision
Tzu-Jui Julius Wang, Jorma Laaksonen, Tomas Langer +2
Weakly-supervised vision-language (V-L) pre-training (W-VLP) aims at learning cross-modal alignment with little or no paired data, such as aligned images and captions. Recent W-VLP…
Learning to hash with semantic similarity metrics and empirical KL divergence
Heikki Arponen, Tom E. Bishop
Learning to hash is an efficient paradigm for exact and approximate nearest neighbor search from massive databases. Binary hash codes are typically extracted from an image by round…
SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing
Heikki Arponen, Tom E Bishop
Using class labels to represent class similarity is a typical approach to training deep hashing systems for retrieval; samples from the same or different classes take binary 1 or 0…
On the exact relationship between the denoising function and the data distribution
Heikki Arponen, Matti Herranen, Harri Valpola
We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the…
Easy Holography
Heikki Arponen
It is argued that the role of infinite dimensional asymptotic symmetry groups in gravity theories are essential for a holographic description of gravity and possibly to a resolutio…
On generalizations of asymptotically AdS_3 spaces and geometry of SL(N)
Heikki Arponen
In three and two dimensions the asymptotic symmetry groups of spaces are infinite dimensional. This can be explained easily by noting the relations and $…