Talks and presentations

Talk about SinGAN

November 02, 2019

Presentation, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

Modeling the internal distribution of patches within a single natural image has been long recognized as a powerful prior to many computer vision tasks. However, capturing the distribution of highly diverse datasets with multiple object classes (e.g. ImageNet) is still considered a major challenge and often requires conditioning the generation on another input signal or training the model for a specific task (e.g. super-resolution, inpainting, retargeting).

Saliency Detection

July 27, 2019

Presentation, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

Humans are able to detect visually distinctive, so-called salient, scene regions effortlessly and rapidly in a pre-attentive stage. It helps to find the objects or regions that efficiently represent a scene, a useful step in complex vision problems such as scene understanding. Some topics that are closely or remotely related to visual saliency include salient object detection, fixation prediction, image quality assessment, scene attributes.

Topic Segmentation

May 11, 2019

Presentation, The University of Edinburgh, Scotland, UK

Determining the positions at which topics change in a stream of text or speech.