Talk by Dr. Cordelia Schmid: Learning visual human actions from movies
Dr. Cordelia Schmid
is giving a talk on "Learning visual human actions from movies" within our faculty on Friday July 18 at 12:00 am at MI 00.13.009 in Garching.
Abstract of the talk
We address the problem of recognizing natural human actions in diverse
and realistic video settings. This challenging but important subject
has mostly been ignored in the past due to several problems one of which is the
lack of realistic and annotated video datasets. Our first contribution is to
address this limitation and to investigate the use of movie scripts for
automatic annotation of human actions in videos. We evaluate alternative methods
for action retrieval from scripts and show benefits of a text-based classifier.
Using the retrieved action samples for visual learning, we next turn to the
problem of action classification in video. We present a new method for video
classification that builds upon and extends several recent ideas including
local space-time features, space-time pyramids and multi-channel non-linear
SVMs. The method is shown to improve state-of-the-art results on the standard
KTH action dataset by achieving 91.8% accuracy. Given the inherent problem
of noisy labels in automatic annotation, we particularly investigate and show
high tolerance of our method to annotation errors in the training set. We
finally apply the method to learning and classifying challenging action
classes in movies and show promising results.
This is joint work with I. Laptev, M. Marszalek and B. Rozenfeld.
Dr. Cordelia Schmid
Cordelia Schmid holds a M.S. degree in Computer Science from the University
of Karlsruhe and a Doctorate, also in Computer Science, from the Institut
National Polytechnique de Grenoble (INPG). Her doctoral thesis on "Local
Greyvalue Invariants for Image Matching and Retrieval" received the best
thesis award from INPG in 1996. She received the Habilitation degree in 2001
for her thesis entitled "From Image Matching to Learning Visual Models".
Dr. Schmid was a post-doctoral research assistant in the Robotics Research
Group of Oxford University in 1996--1997. Since 1997 she has held a
permanent research position at INRIA Rhone-Alpes, where she is a research
director and directs the INRIA team called LEAR for LEArning and Recognition
in Vision. Dr. Schmid is the author of over eighty technical publications.
She has been an Associate Editor for the IEEE Transactions on Pattern
Analysis and Machine Intelligence (2001--2005) and for the International
Journal of Computer Vision (2004---), and she was program chair of the 2005
IEEE Conference on Computer Vision and Pattern Recognition. In 2006, she was
awarded the Longuet-Higgins prize for fundamental contributions in computer
vision that have withstood the test of time. She is a senior member of IEEE.
| WebEventForm |
| Title: || Talk by Dr. Cordelia Schmid on Learning visual human actions from movies |
| Date: || 18 July 2008 |
| Location: || 12:00 am at MI 00.13.009 |
| Abstract: || Dr. Cordelia Schmid is giving a talk on Learning visual human actions from movies within our faculty on Friday July 18 at 12:00 am at MI 00.13.009 in Garching. |
| Imageurl: || |
| Type: || News |
| Videourl: || |