Search Results for author:
Found 6 papers, 3 papers with code
Efficient multi-lens bokeh effect rendering and transformation
Our method can render Bokeh from an all-in-focus image, or transform the Bokeh of one lens to the effect of another lens without harming the sharp foreground regions in the image.
Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision
Moreover, in other V-L downstream tasks considered, our WFH models are on par with models trained with paired V-L data, revealing the utility of unpaired data.
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
On IAM we even surpass single line methods that use accurate localization information during training.
Learning to hash with semantic similarity metrics and empirical KL divergence
We address (ii) via a differentiable estimate of the KL divergence between network outputs and a binary target distribution, resulting in minimal information loss when the features are rounded to binary.
SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing
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 similarity values.
