2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSMR-3.4
Paper Title SELF-SUPERVISION BY PREDICTION FOR OBJECT DISCOVERY IN VIDEOS
Authors Beril Besbinar, Pascal Frossard, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
SessionSMR-3: Image and Video Representation
LocationArea F
Session Time:Tuesday, 21 September, 15:30 - 17:00
Presentation Time:Tuesday, 21 September, 15:30 - 17:00
Presentation Poster
Topic Image and Video Sensing, Modeling, and Representation: Image & video representation
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Despite their irresistible success, deep learning algorithms still heavily rely on annotated data, and unsupervised settings pose many challenges, such as finding the right inductive bias in diverse scenarios. In this paper, we propose an object-centric model for image sequence representation that uses the prediction task for self-supervision. By disentangling object representation and motion dynamics, our novel compositional structure explicitly handles occlusion and inpaints inferred objects and background for the composition of the predicted frame. Using auxiliary losses to promote spatially and temporally consistent object representations, we train our self-supervised framework without the help of any annotation or pretrained network. Initial experiments confirm that our new pipeline is a promising step towards object-centric video prediction.