posted by organizer: davidfsemedo || 2267 views || tracked by 6 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
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
MIWAI 2017   The 11th Multi-disciplinary International Workshop on Artificial Intelligence
HCI-Europe 2017   Human Computer Interaction HCI-Europe 2017
WACV 2017   IEEE Winter Conference on Applications of Computer Vision
VCIP 2017   Visual Communications and Image Processing
SI: IEEE Access VSB 2017   IEEE Access Special Section on Visual Surveillance and Biometrics: Practices, Challenges, and Possibilities
ICMLA 2017   16th IEEE International Conference On Machine Learning And Applications