Workshop 2015 CVPR challenge

The ChaLearn Looking at People Workshop 2015, to be held next June 12th in conjunction with CVPR 2015 at room 101 of the Hynes Convention Center in Boston, Massachusetts, will be devoted to the presentation of most recent and challenging techniques from human body pose recovery, human action/interaction and cultural event recognition.

The final program is described next (pdf version original program):

09:00h Opening: Presentation of the workshop, Sergio Escalera, UB-CVC

09:15h Invited Speaker I: Tinne Tuytelaars, KU Leuven

Session chair: Sergio Escalera

10:00h Coffee Break

10:30h Session I: Challenge results presentation and award ceremony, Xavier Baró, UOC-CVC

  • ChaLearn Looking at People 2015 challenges: action spotting and cultural event recognition, Xavier Baró, Jordi Gonzàlez, Junior Fabian, Miguel Angel Bautista, Marc Oliu, Hugo J. Escalante, Isabelle Guyon, Sergio Escalera

Session chair: Sergio Escalera

10:50h Session II: Action and gesture recognition

  • Action track 1st position: Exploring Fisher Vector and Deep Networks for Action Spotting, Zhe Wang, Limin Wang, Wenbin Du, Qiao Yu
  • Applying Action Attribute Class Validation to Improve Human Activity Recognition, David Tahmoush
  • Keep it Accurate and Diverse: Enhancing Action Recognition Performance by Ensemble Learning, Mohammad Bagheri, Qigang Gao, Sergio Escalera, Albert Clapes, Kamal Nasrollahi, Michael Holte, Thomas B. Moeslund

Session chair: Xavier Baró

11:45h Invited Speaker II: Best of both worlds: human-machine collaboration for object annotation, Olga Russakovsky, Stanford

Session chair: Xavier Baró

12:30h Lunch break

13:30h Invited Speaker III: Alexandre Alahi, Stanford

Session chair: Marc Oliu

14:00h Session III: Cultural event recognition

  • 1st position: Object-Scene Convolutional Neural Networks for Event Recognition in Images, Limin Wang , Zhe Wang, Wenbin Du, Qiao Yu
  • 2nd position: Cultural Event Recognition with Visual ConvNets and Temporal Models, Amaia Salvador, Matthias Zeppelzauer, Daniel Manchon, Andrea Calafell, Xavier Giro-Nieto
  • 3rd position: Cultural Event Recognition by Subregion Classification with Convolutional Neural Network, Sungheon Park, Nojun Kwak
  • 4th position: Recognizing Cultural Events in Images: a Study of Image Categorization Models, Heeyoung Kwon, Minh Hoai, Kiwon Yun, Dimitris Samaras

Session chair: Jordi Gonzàlez

15:00h Invited Speaker IV: People in Action and Interaction, Stan Sclaroff, Univ. Boston

Session chair: Jordi Gonzàlez

15:30h Coffee Break

16:00h Session IV: Human pose and Looking at People applications

  • A Semantic Occlusion Model for Human Pose Estimation from a Single Depth Image, Umer Rafi, Juergen Gall, Bastian Leibe
  • Articulated pose estimation with tiny synthetic videos, Dennis Park, Deva Ramanan
  • A New Retexturing Method for Virtual Fitting Room Using Kinect 2 Camera, Andres Traumann, Gholamreza Anbarjafari, Sergio Escalera

Session chair: Hugo J. Escalante

16:45h Session V: Face analysis

  • Pain Recognition using Spatiotemporal Oriented Energy of Facial Muscles, Ramin Irani, Kamal Nasrollahi, Thomas B. Moeslund
  • Spatiotemporal Analysis of RGB-D-T Facial Images for Multi-Modal Pain Level Recognition, Ramin Irani, Kamal Nasrollahi, Marc Oliu, Ciprian Corneanu, Sergio Escalera, Chris Bahnsen, Dennis Lundtoft, Thomas B. Moeslund, Tanja Pedersen, Maria-Louise Klitgaa, Laura Petrini

Session chair: Hugo J. Escalante

17:15h Invited Speaker V: Actions recognition from videos: some recent results, Cordelia Schmid, INRIA Grenoble

Session chair: Miguel A. Bautista

18:00h Session VI: The COST Action iV&L Net IC1307: Challenges in Computer Vision and Natural Language, Jordi Gonzàlez, UAB-CVC

Session chair: Junior Fabian

18:30h Closing: conclusions of the workshop and upcoming events, Jordi Gonzàlez, UAB-CVC