International Workshop on Large Scale Visual Recognition and Retrieval

6/28/2014, Columbus, Ohio, CVPR 2014


    • Workshop program is up!
    • Submission deadline is now extended to April 18, 2014.


  • 9:00-9:05 opening remarks
  • 9:05-9:40 invited talk: Alexei Efros (UC Berkeley). Towards a Visual Memex.
  • 9:40-10:15 invited talk: Vittorio Ferrari (University of Edinburgh). Video as Training Data for Object Class Detectors.
  • 10:15-10:45 coffee break
  • 10:45-11:20 invited talk: Trevor Darrell and Yangqing Jia (UC Berkeley). Towards Large-Scale Semantic Representations.
  • 11:20-12:00 spotlights & posters
  • 12:00-14:15 lunch & posters
  • 14:15-14:50 invited talk: Tamara Berg (UNC Chapel Hill). Learning from Descriptive Text.
  • 14:50-15:25 invited talk: Noah Snavely (Cornell University). The Distributed Camera.
  • 15:25-15:55 coffee break
  • 15:55-16:30 invited talk: Drago Anguelov (Google). Large-Scale Image Understanding.
  • 16:30-17:05 Invited talk: Yann LeCun (Facebook AI Research & New York University). Toward a Universal Perception System.


  1. Inferring Analogous Attributes: Large-Scale Transfer of Category-Specific Attribute Classifiers. Chao-Yeh Chen, University of Texas at Austin; Kristen Grauman, University of Texas at Austin
  2. Analysis of Randomized Max-Margin Compositions for Visual Recognition. Angela Eigenstetter, IWR; Björn Ommer,
  3. Ensemble of Exemplar SVM - Convex Relaxation of Latent SVM. Aravindh Mahendran, Carnegie Mellon University; Martial Hebert, Carnegie Mellon University; Stephen Smith, Carnegie Mellon University
  4. Learning to Count Buildings in Diverse Aerial Scenes. Jiangye Yuan, Oak Ridge National Laboratory; Anil Cheriyadat,
  5. Large-Scale Object Detection with FLAIR. Koen Van de Sande, University of Amsterdam / Euvision Technologies; Cees Snoek, University of Amsterdam; Arnold Smeulders, University of Amsterdam / CWI
  6. Propose and Re-rank Semantic Segmentation via Deep Image Classification. Xiao Lin, Virginia Tech; Michael Cogswell, Virginia Tech; Devi Parikh, Virginia Tech; Dhruv Batra, Virginia Tech
  7. Audio-Visual Identity Grounding for Enabling Cross Media Search. Kevin Brady, MIT Lincoln Laboratory
  8. Real-World Computer Vision Applications Are Open, So Should Your Recognition. Lalit Jain, University of Colorado; Walter Scheirer, Harward; Terrance Boult, University of Colorado Colorado Springs
  9. Learning from Label Proportions: Algorithm, Theory, and Applications. Felix Yu, Columbia University
  10. COSTA: Co-Occurrence Statistics for Zero-Shot Classification. Thomas Mensink, University of Amsterdam; Efstratios Gavves, University of Amsterdam; Cees Snoek, University of Amsterdam
  11. Exemplar Codes: An Accurate and Efficient Mid-Level Representation for Big Vision Problems. Ethan Rudd, UCCS; Michael Wilber, ; Terrance Boult, University of Colorado Colorado Springs
  12. Learning Fine-grained Image Similarity with Deep Ranking. Jiang Wang, Northwestern University; Yang Song, Google; Thomas Leung, ; Chuck Rosenberg, ; Jingbin Wang, Google; James Philbin, Google; Bo Chen, Caltech; Ying Wu,
  13. Predicting USA President Election with Online Photos. Quanzeng You, University of Rochester; Liangliang Cao, IBM; Junhuan Zhu, University of Rochester; Michele Merler, IBM Research; Jiebo Luo, University of Rochester; John Smith, IBM Research
  14. Privacy Protection for Large Scale Naturalistic Driving Videos. Sujitha Martin, University of California, San ; Ashish Tawari, UCSD; Mohan Trivedi, UCSD
  15. SUN3D: A Database of Big Spaces Reconstructed using SfM and Object Labels. Jianxiong Xiao, ; Andrew Owens, MIT; Antonio Torralba, Massachusetts Institute of Technology
  16. PanoContext: A Whole-room 3D Context Model for Panoramic Scene Understanding. Yinda Zhang, Princeton University; Shuran Song, Princeton University; Jianxiong Xiao, Princeton University ; Ping Tan, Princeton University
  17. Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines. Shuran Song, Princeton University; Jianxiong Xiao, Princeton University
  18. Sliding Shapes for 3D Object Detection in RGB-D Images. Shuran Song, Princeton University; Jianxiong Xiao, Princeton University; Thomas Funkhouser, Princeton University

Call for Submissions

Submission site: https://cmt.research.microsoft.com/BV2014/

Big data has been revolutionizing computer vision research. The increasing availability of massive visual datasets creates unprecedented opportunities for researchers to tackle fundamental computer vision challenges: recognizing everything in the visual world, indexing and organizing the sea of visual information, and extracting knowledge and discovering patterns from big visual data. Achieving these goals calls for bold innovations on many fronts: data collection, learning, inference, representations, indexing, and systems infrastructure.

The goal of this workshop is providing a venue for researchers interested in large-scale vision to present new work, exchange ideas, and connect with each other. The workshop will feature invited talks from leading researchers as well as a poster session that fosters in depth discussion.

We invite submissions of extended abstracts related to the following topics in the context of big data and large-scale vision:

  • Indexing algorithms and data structures
  • Weakly supervised or unsupervised learning
  • Metric learning
  • Visual models and feature representations
  • Transfer learning and domain adaptation
  • Systems and infrastructure
  • Visual data mining and knowledge discovery
  • Dataset issues (e.g. dataset collection and dataset biases
  • Efficient learning and inference techniques
  • Optimization techniques

The abstracts should be no more than 2 pages in CVPR 2014 format. Accepted abstracts will be presented as posters. The workshop is not intended as a venue for publication and no proceedings will be produced. All submissions will undergo double-blind reviews. In the case of previous published work, the review will be single-blind.

Important Dates

  • Submission deadline (extended): April 18, 2014.
  • Decision notification: May 17, 2014.
  • Camera ready deadline: June 6, 2014.
  • Workshop date: June 28, 2012.

Program Committee

  • Serge Belongie, UCSD
  • Lubomir Bourdev, Facebook
  • Shih-Fu Chang, Columbia University
  • Trevor Darrell, UC Berkeley
  • Kristen Grauman, UT Austin
  • Brian Kulis, Ohio State University
  • Christoph Lampert, IST Austria
  • Honglak Lee, University of Michigan
  • Jia Li, Yahoo Research
  • Ce Liu, Microsoft Research
  • Florent Perronnin, XRCE
  • Marc'Aurelio Ranzato, Facebook
  • Fei Sha, USC
  • Lorenzo Torresani, Dartmouth College
  • Xiaoyu Wang, NEC
  • Jianxiong Xiao, Princeton University
  • Jianchao Yang, Adobe
  • Kai Yu, Baidu

Program Chairs

  • Jia Deng, University of Michigan
  • Alex Berg, UNC Chapel Hill
  • Yuanqing Lin, NEC Labs America
  • Jason Corso, SUNY Buffalo


  • Samy Bengio, Google
  • Fei-Fei Li, Stanford University

Past Workshops