posted by user: dvazquez || 4206 views || tracked by 5 users: [display]

TASK-CV 2015 : 2nd Workshop on Transferring and Adapting Source Knowledge in Computer Vision

FacebookTwitterLinkedInGoogle

Link: http://www.cvc.uab.es/adas/task-cv2015
 
When Dec 17, 2015 - Dec 18, 2015
Where Santiago de Chile
Submission Deadline Sep 14, 2015
Notification Due Sep 27, 2015
Final Version Due Oct 12, 2015
Categories    computer vision   machine learning   domain adaptation   transfer learning
 

Call For Papers

TASK-CV 2015 - 2nd Workshop on Transferring and Adapting Source Knowledge in Computer Vision
Santiago de Chile, TBA
In conjunction with ICCV 2015

Web: http://www.cvc.uab.es/adas/task-cv2015
********************************************************

_________________
IMPORTANT DATES
_________________

Submission deadline: September 14th, 2015
Author notification: September 27th, 2015
Camera-ready: October 12th 2015
Workshop: TBA (17th or 18th December 2015)
________________
CALL FOR PAPERS
________________

This workshop aims at bringing together computer vision researchers interested in the domain adaptation and knowledge transfer techniques, which are receiving increasing attention in computer vision research.

During the first decade of the XXI century, progress in machine learning has had an enormous impact in computer vision. The ability to learn models from data has been a fundamental paradigm in image classification, object detection, semantic segmentation or tracking.

A key ingredient of such a success has been the availability of visual data with annotations, both for training and testing, and well-established protocols for evaluating the results.

However, most of the time, annotating visual information is a tiresome human activity prone to errors. This represents a limitation for addressing new tasks and/or operating in new domains. In order to scale to such situations, it is worth finding mechanisms to reuse the available annotations or the models learned from them.

This aim challenges machine learning theory since its more traditional corpus corresponds to situations where there are sufficient labeled data of each task, and the training data distribution matches the test distribution.

Therefore, transferring and adapting source knowledge (in the form of annotated data or learned models) to perform new tasks and/or operating in new domains has recently emerged as a challenge to develop computer vision methods that are reliable across domains and tasks.

Accordingly, TASK-CV aims to bring together research in transfer learning and domain adaptation for computer vision as a workshop hosted by the ICCV 2015. We invite the submission of research contributions such as:

- TL/DA learning methods for challenging paradigms like unsupervised, and incremental or online learning.
- TL/DA focusing on specific visual features, models or learning algorithms.
- TL/DA jointly applied with other learning paradigms such as reinforcement learning.
- TL/DA in the era of convolutional neural networks (CNNs), adaptation effects of fine-tuning, regularization techniques, transfer of architectures and weights, etc.
- TL/DA focusing on specific computer vision tasks (e.g., image classification, object detection, semantic segmentation, recognition, retrieval, tracking, etc.) and applications (biomedical, robotics, multimedia, autonomous driving, etc.).
- Comparative studies of different TL/DA methods.
- Working frameworks with appropriate CV-oriented datasets and evaluation protocols to assess TL/DA methods.
- Transferring part representations between categories.
- Transferring tasks to new domains.
- Solving domain shift due to sensor differences (e.g., low-vs-high resolution, power spectrum sensitivity) and compression schemes.
- Datasets and protocols for evaluating TL/DA methods. This is not a closed list; thus, we welcome other interesting and relevant research for TASK-CV.


____________
SUBMISSION
____________

Authors should take into account the following:
- The submission site is https://cmt.research.microsoft.com/TASK2015/.
- The contributions will consist in Extended Abstracts (EA) of 4 pages. Thus, they can be summary papers presented in the main conference or just ongoing work that will be eventually submitted or not to another conference. In any case, we will encourage the accepted EA to submit a longer version to the journal special issue that we will organize.
- The format of the papers is the same as the ICCV main conference.
- Submissions will be rejected without review if they: contain more than 4 pages (excluding references) or violate the double-blind policy.
- Manuscript templates can be found at the main conference website: http://pamitc.org/iccv15/author_guidelines.php
- The accepted papers will be linked in the TASK-CV webpage.

_____________________
BEST PAPER
_____________________

The TASK-CV will award the best student paper of the workshop, voted by the program committee. More details will be provided in the workshop web page.

_________
Contact
_________

David Vazquez (dvazquez@cvc.uab.es)
Antonio M. Lopez (antonio@cvc.uab.es)

Related Resources

OSAD 2022   Open Source Automation Days
ICDM 2022   22nd IEEE International Conference on Data Mining
CCVPR 2022   2022 5th International Joint Conference on Computer Vision and Pattern Recognition (CCVPR 2022)
MLDM 2023   18th International Conference on Machine Learning and Data Mining
CV-CMEM 2022   ICIAP 2021 - Special Session on Computer Vision for Coastal and Marine Environment Monitoring
ICMLA 2022   IEEE International conference on Machine Learning and Applications
3rd Food Chemistry Conference 2023   3rd Food Chemistry Conference: Shaping a healthy and sustainable food chain through knowledge
FAIML 2022   2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2022)
ADMA 2022   18th International Conference on Advanced Data Mining and Applications
IOP, EI, Scopus-PRECE 2022   2022 International Conference on Power, Renewable Energy and Control Engineering (PRECE 2022)-EI Compendex