Current Topics in Computer Vision and Machine Learning

Semester:
SS 2015
Type:
Seminar
Lecturer:
Credits:
4 ECTS credits

Seminar Description

Computer Vision is a very active research field with many interesting applications. Many of its recent successes are due to advances in Machine Learning research. It is therefore useful to study the two fields together and to draw cross-links between them.

The conferences with the strongest impact in Computer Vision are CVPR, ICCV, and ECCV, whereas NIPS and ICML have the strongest impact on the Machine Learning community. In this seminar we will discuss recent results presented at those conferences with a focus on the most interesting and innovative ideas. Participating students have the chance to get familiar with state-of-the-art solutions to problems in Computer Vision and Machine Learning and will get an insight into the involved techniques.

Successful participants will be awarded 4 ECTS credits.

Prerequisites

Master students: Bachelor degree Attendance of the lectures Computer Vision, Machine Learning, or Pattern Recognition and Neural Networks, or evidence of equivalent knowledge.

Material

  • Ethical Guidelines for the Authoring of Academic Work in German and English
  • Declaration of Compliance in German and English
  • LaTeX for the report (mandatory!): Template
  • Slide template (optional): PPT, Keynote, LaTeX

Schedule

  • Introductory Meeting: 9. April 2015 - mandatory for all participants - Slides
  • Outline due: May, 4th
  • Report due: June, 8th
  • Slides due: July, 13th
  • Presentations: July 21-23 - 3 days

Topics

ALL PRESENTATIONS in ROOM UMIC 025

  • Tuesday, 21.7. 09:00
    • Ji Hou Image Parsing via Stochastic Scene Grammar - Zhao et al., NIPS 2011.
    • Tong Su Understanding Indoor Scenes using 3D Geometric Phrases - Choi et al., CVPR 2013.
    • Muhammad Ali Syed To Aggregate or Not to aggregate - Tolias et al., ICCV 2013.
  • Tuesday, 21.7. 13:30
    • Alina Shigabutdinova Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding - Scharw├Ąchter et al., ECCV 2014.
    • Anton Kasyanov Pose Machines: Articulated Pose Estimation via Inference Machines - Ramakrishna et al., ECCV 2014.
    • Yevhen Kuznietsov Articulated Pose Estimation using Discriminative Armlet Classifiers - Gkioxari et al., CVPR 2013.
  • Wednesday, 22.7. 09:00
    • David Stutz Neural Codes for Image Retrieval - Babenko et al., ECCV 2014.
    • Julian Teige Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians - Collins et al., ECCV 2014.
    • Xiaoqing Zhao Context-Based Pedestrian Path Prediction - Kooij et al., ECCV 2014.
  • Wednesday, 22.7. 13:30
    • Tobias Pohlen Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation - Yamaguchi et al., ECCV 2014.
    • Pol Guerkinger Activity Forecasting - Kitani et al., ECCV 2012.
  • Thursday, 23.7. 09:00
    • Oleg Chernikov Re-ranking by Multi-feature Fusion with Diffusion for Image Retrieval - Yang et al.
    • Mohammed Hetnawi ImageNet Classification with Deep Convolutional Neural Networks - Krizhevsky et al., NIPS 2012.
    • Ilia Kulikov Pedestrian Detection with Unsupervised Multi-Stage Feature Learning - Sermanet et al., CVPR 2013.
Disclaimer Home Visual Computing institute RWTH Aachen University