posted by organizer: davidfsemedo || 8364 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

NCAD 2020   IEEE VTC Workshop: Network-assisted Collaborative Automated Driving
FAIML 2020-Ei Compendex & Scopus 2020   2020 2nd International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2020)
CollaborateCom 2020   (Virtual) 16th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing
AVC 2020   Advances in Vision Computing: An International Journal
ISVC 2020   ISVC 2020: 15th International Symposium on Visual Computing
AICA 2020   O'Reilly AI Conference San Jose
ICPR-IETBiom-VSaaS 2021   25th ICPR Special Issue on Real-Time Visual Surveillance as-a-Service (VSaaS) for Smart Security Solutions in IET Biometrics
MLMI--ACM, Ei, Scopus 2020   ACM--2020 The 3rd International Conference on Machine Learning and Machine Intelligence (MLMI 2020)--Ei Compendex, Scopus
EL 2020   14th International Conference on e-Learning 2020
NLAI 2020   International Conference on NLP & Artificial Intelligence Techniques