Category: Seminars

Comparison and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to human behavior understanding

Place: Large Lecture Room Abstract: Developing intelligent systems dedicated to human behavior understanding has been a very hot research topic in the few recent decades. In this talk, we consider a novel space-time representation of human landmark sequences. We propose a

CVC Seminars: Dr. Daniela Rus

Place: Large Lecture Room Abstract: In this seminar, Dr. Daniela Rus, Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT and Professor of Electrical Engineering and Computer Science (MIT) will explain her research at MIT. Short Bio: Daniela

Multisensor multitemporal AI approaches to the detection and analysis of archaeological settlements at a continental scale

Place: Large Lecture Room Abstract: The last few years have seen an important increase of AI-based methods for the detection and analysis of non-readily visible archaeological sites and features. However, many of these methods’ results tend to overfit the training data

Learning to Reconstruct 3D Objects

Place: Large Lecture Room Abstract: I will talk about two recent results on learning-based 3D reconstruction. First, I will introduce Occupancy Networks as a new representation for learning-based 3D reconstruction. Occupancy networks implicitly represent the 3D surface as the continuous decision

Mining and Enriching Multilingual Scientific Text Collections: Challenges and Opportunities

Place: Large Lecture Room   Abstract: Scientists worldwide are confronted with an exponential growth in the number of scientific documents being made available, in this scenario of scientific information overload, natural language processing has a key role to play. Over the

Learning spatio-temporal video representations

Place: Large Lecture Room Abstract: The state-of-the-art models for action recognition and other video tasks are currently based on spatio-temporal (3D) convolutions. Although highly effective, such models are computationally expensive and usually require orders of magnitude more FLOPs than their 2D

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,