posted by organizer: davidfsemedo || 4628 views || tracked by 10 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 2017   International Conference on Computer Vision
ICPR 2018   24th International Conference on Pattern Recognition
ECCV 2018   European Conference on Computer Vision
MVR3D 2017   ICCV Workshop on Multiview Relationships in 3D Data
NAACL HLT 2018   The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
CogSIMA 2018   2018 IEEE Conference on Cognitive and Computational Aspects of Situation Management
MLDM 2018   14th International Conference on Machine Learning and Data Mining MLDM 2018
ESIDA 2018   ESIDA 2018 : 2nd ACM IUI Workshop on Exploratory Search and Interactive Data Analytics
CASCON 2017   Conference of the Centre for Advanced Studies on Collaborative Research
ICAISC 2018   International Conference on Artificial Intelligence and Soft Computing