posted by organizer: davidfsemedo || 7115 views || tracked by 13 users: [display]

ICCV 2017 - CoViStories 2017 : ICCV 2017 - CoViStories: Workshop on Collaborative Visual Stories

FacebookTwitterLinkedInGoogle

Link: https://sites.google.com/view/covistories/
 
When Oct 23, 2017 - Oct 23, 2017
Where Venice, Italy
Submission Deadline Jul 7, 2017
Notification Due Aug 9, 2017
Final Version Due Aug 25, 2017
Categories    computer vision   social media   machine learning   computer science
 

Call For Papers

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.

Related Resources

ICCV 2019   International Conference on Computer Vision
IUI 2019   ACM Conference on Intelligent User Interfaces
ICML 2019   36th International Conference on Machine Learning
Visual Intersections 3 2018   Visual Intersections 3 --- 11-13 of July 2018 in Durham, United Kingdom
MLDM 2019   15th International Conference on Machine Learning and Data Mining MLDM 2019
ICR 2019   4th International Conference on Interactive Collaborative Robotics
ICDMML 2019   【ACM ICPS EI SCOPUS】2019 International Conference on Data Mining and Machine Learning
LCIR 2019   The Aesthetics of Decay: Ghost Stories and Mysteries International Conference
CGVC 2018   Computer Graphics & Visual Computing
CAIP 2019   Computer Analysis of Images and Patterns