Accepted papers

Preliminary list of accepted papers is now available:

  • Paper 4: “Photo Recall: Using the Internet to Label Your Photos”, by Neeraj Kumar and Steve Seitz
  • Paper 2: “What is usual in unusual videos? Trajectory snippet histograms for discovering unusualness”, by Ahmet Iscen, Anil Armagan and Pinar Duygulu
  • Paper 6: “Streetscore – Predicting the Perceived Safety of One Million Streetscapes”, by Nikhil Naik, Jade Philipoom, Ramesh Raskar and Cesar Hidalgo
  • Paper 7: “A Stream Algebra for Computer Vision Pipelines”, by Mohamed Helala, Ken Pu and Faisal Qureshi
  • Paper 9: “Clustering Social Event Images using Kernel Canonical Correlation Analysis”, by Unaiza Ahsan

Paper submission deadline extended

In response to requests, the deadline for submitting papers to the VSM Workshop has been extended to April 13 (11:59 PM, Pacific Time).

In addition to papers, we will also accept extended abstracts (2 pages in CVPR format) of ongoing or already published work.  Authors may use this opportunity to present their work to the right audience. The deadline for submitting extended abstracts is May 11 (11:59 PM, Pacific Time).

Aims and Scope

The world-wide-web has become a large ecosystem that reaches billions of users through information processing and sharing, and most of this information resides in pixels. Web-based services like YouTube and Flickr, and social networks such as Facebook have become more and more popular, allowing people to easily upload, share and annotate massive amounts of images and videos. Vision and social media thus has recently become a very active inter-disciplinary area, involving computer vision, multimedia, machine-learning, information retrieval, and data mining.

This workshop aims to bring together leading researchers in the related fields to advocate and promote new research directions for problems involving vision and social media, such as large-scale visual content analysis, search and mining. VSM will provide an interactive platform for academic and industry researchers to disseminate their most recent results, discuss potential new directions in vision and social media, and promote new interdisciplinary collaborations. The program will consist of invited talks, panels, discussions, and reviewed paper submissions.

Topics of interest include (but are not limited to):

  • Content analysis for vision and social media
  • Efficient learning and mining algorithms for large­-scale vision and social media analysis
  • Understanding social media content and dynamics
  • Contextual models for computer vision and social media
  • Machine learning and data mining for social media
  • Indexing and retrieval for large­scale social media information
  • Tagging, semantic annotation, and object recognition on massive multimedia collections
  • Scalable and distributed machine learning and data mining methods for vision
  • Interfaces for exploring, browsing and visualizing large visual collections
  • Construction and evaluation of large‐scale visual collections
  • Crowdsourcing for vision problems Scene reconstruction and matching using large scale web images