Spotlights

Page 1 Page 2 Page 3 next

October 5th, 2016

By: Johannes Hoffart & Dragan Milchevski & Gerhard Weikum

STICS – Search and Analysis with Strings, Things, and Cats

Understanding the meaning of a word in its current context is one of the big challenges when searching for information. STICS is a new kind of semantic search engine that not only searches for words, but for meaning: it understands concepts and categories.


June 1st, 2016

By: Piotr Didyk

Computational Fabrication

3D printing gives new opportunities in object replication. We built a computational model with which we will compare perceived properties of different materials and choose the one best suited for printing the desired object.


May 31st, 2016

By: Antonios Antoniadis and Sebastian Ott

Energy Efficient Algorithms

Energy consumption is a crucial aspect in computing. We developed an efficient algorithm whose output has an energy consumption arbitrarily close to the optimal one.


May 20th, 2016

By: Parinya Chalermsook and Kurt Mehlhorn

From Routing to Pricing and Learning: Why Are They Hard to Compute?

Computational aspects of routing and pricing problems share more similarities than one would imagine. Theoreticians as well as practitioners can benefit from our transfer of routing problem knowledge to pricing problems.


May 17th, 2016

By: Tobias Marschall

Structural Variation in Genoms

Comparing genomes of parents and children separates inherited genetic variants from new mutations. The rate of novo mutations is an important parameter in models of human evolution.


January 13th, 2016

By: Christian Theobalt

Advanced Video Processing

New algorithms facilitate complex video processing such as automatic dynamic background inpainting. New machine learning algorithms make possible the removal of compression artifacts from images and videos.


January 12th, 2016

By: Anna Rohrbach & Marcus Rohrbach

Describing Videos with Natural Language

With the work of Anna and Markus Rohrbach the automatic generation of subtitles or the automatic movie description for the blind becomes a realistic objective.


January 11th, 2016

By: Christian Theobalt

Markerless Reconstruction of Static and Dynamic Scenes

The 3D reconstruction of detailed models of persons in general apparel is, until now, possible in indoor sudios with controlled environment only. With new algorithms this seems it could succeed even in arbitrarily complex outdoor scenes with only a few camera.


January 11th, 2016

By: Rodrigo Benenson & Jan Hosang

Ten Years of Pedestrian Detection, What Have we Learned?

Instead of using a large variety of classifier types, it is possible to obtain best results in shortest time by precisely applying the sliding windows technique.


January 11th, 2016

By: Mykhaylo Andriluka & Leonid Pishchulin

Articulated Human Pose Estimation


Page 1 Page 2 Page 3 next