ICCV CoViStories 2017: Difference between revisions

From Openresearch
Jump to navigation Jump to search
Omid.nn (talk | contribs)
No edit summary
Omid.nn (talk | contribs)
remove related conferences
Line 40: Line 40:


We will accept contributions as full-papers and position-papers on the above topics. Submissions are limited to 6 pages.
We will accept contributions as full-papers and position-papers on the above topics. Submissions are limited to 6 pages.
ICCV 2017  
International Conference on Computer Vision
ACML 2017  
The 9th Asian Conference on Machine Learning
ICPR 2018  
24th International Conference on Pattern Recognition
MVR3D 2017  
ICCV Workshop on Multiview Relationships in 3D Data
WWW 2018  
World Wide Web (The Web Conference)
HCI-Europe 2017  
Human Computer Interaction HCI-Europe 2017
ICMLA 2017  
16th IEEE International Conference On Machine Learning And Applications
VCIP 2017  
Visual Communications and Image Processing
WACV 2017  
IEEE Winter Conference on Applications of Computer Vision
CASCON 2017  
Conference of the Centre for Advanced Studies on Collaborative Research

Revision as of 07:11, 12 July 2017

ICCV CoViStories 2017
ICCV 2017 - CoViStories 2017 : ICCV 2017 - CoViStories: Workshop on Collaborative Visual Stories
Dates 2017/10/23 (iCal) - 2017/10/23
Homepage: http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=64989&copyownerid=100138
Location
Location: Venice, Italy
Loading map...

Important dates
Submissions: 2017/07/08
Table of Contents


The CoViStories workshop seeks contributions in the area of visual story creation, with collaborative videos, images and texts available from professional media and social-media users. The challenges in creating such visual timelines are various: alignment of videos and images through sound or timestamps, detection of video intervals of high interest, caption generation for a group of pictures, among others. Contributions in the following topics are expected:

Analysis and verification of collaborative visual content: the visual understanding of individual images or groups of related images provides strong relevance indicators with respect to the final visual story. Moreover, detecting the reliability of such visual content is critical to ensure the truth of the story. Specific topics: a. Image concept detection b. Collaborative event-episodes annotation c. Visual forensics

Temporal aspects of stories: the temporal aspects and relations extracted from visual content are key to conveying coherent, sequential storytelling. Specific topics: a. Collaborative event-episodes detection b. Temporal and semantic media alignment c. Information freshness d. Multimodal event timelines

Qualitative and perceptual aspects: are often a decisive factor in the selection of the best images and videos that can tell a story. Specific topics: a. Event summary diversity b. QoE in visual summaries c. Affect and emotion in visual summaries and caption generation

Collaborative visual summaries: the creation of visual summaries and their descriptions are the ultimate goal, building on the previous topics. Specific topics: a. Multimodal caption generation b. Collaborative media summaries c. Non-linear and multiple view summarization

User studies: we also encourage ideas about how to evaluate visual user experiences in terms of visual coherence, visual composition, story comprehensiveness and other aspects related to the creation of visual summaries from both professional and social-media content.

Applications: collective contributions of images and videos concerning a particular event can be found in many domains. Social-media applications, family photo albums, historical photo libraries, patient’s clinical history, are some of the examples.


We will accept contributions as full-papers and position-papers on the above topics. Submissions are limited to 6 pages.