Category: Seminars

CVPR2018 Seminar

CVC Seminar CVPR 2018 Presentations (  consisting of five talks) Talk 1:  Objects as context for detecting their semantic parts, by Dr. Abel González. Talk 2:  On the Duality Between Retinex and Image Dehazing, by Dr. Javier Vázquez. Talk 3:  Depth-Based 3D Hand Pose Estimation:

Multi-level image understanding and beyond

Place: Large Lecture Room Abstract: In this talk, I will present our recent work on multi-level image understanding, including attribute learning, visual relationship detection and combinatorial visual semantic learning. More specifically, I will explain how we tackle the incompleteness nature of visual

ICLR 2018 presentations

Place: Large Lecture Room     TALK1: Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks by Victor Campos   Abstract: Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences

Lifelong learning seminar

Place: Large Lecture Room   TALK 1: Overcoming catastrophic forgetting with hard attention to the task by Dr. Joan Serra  BIO: Joan Serrà is a research scientist with Telefónica R&D in Barcelona. He works on machine learning and artificial intelligence,

Recent Applications of Deep Learning for Retinal Image Analysis

Affiliation: Postdoctoral Researcher at INESC TEC Porto Place: Large Lecture Room Abstract The human eye is an excellent source of biomarkers that are useful for the early detection of different diseases like diabetes or hypertension. Acquisition of images of the retinal fundus

Learning CNN filter resolution using multi-scale structured receptive fields

Affiliation: Assistant professor at the Technical University Delft Place: Large Lecture Room Abstract The design of filter layers in a CNNs is a matter of trail and error where the filter-size in a single layer is typically hard-coded. Here I question this

Active Decision Boundary Annotation with Deep Generative Models

Affiliation: Assistant professor at the Technical University Delft Place: Large Lecture Room Abstract This talk is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask

Deep Multimodal and contextual visual recognition

Affiliation: PostDoc Researcher at the Computer Vision Center Place: Large Lecture Room Abstract Visual recognition is often addressed only using RGB images. However, humans perceive and understand the world through multiple senses and leverage other sources of information such as prior

Historical Map Alignment and Toponym Recognition with Geographic and Style Models

Affiliation: Associate Professor. Department of Computer Science. Grinnell College. IA, USA. Place: Large Lecture Room Recognizing the place names within textual labels on historical maps is complicated by many factors, such as curvilinear baselines and dense overlap with other textual or graphical

Semantic segmentation of 3D textured meshes for urban scene analysis

Affiliation: Computer Scientist at Pixmap. Place: Large Lecture Room   Classifying 3D measurement data has become a core problem in photogrammetry and 3D computer vision, since the rise of modern multiview geometry techniques, combined with affordable range sensors. We introduce a