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 IDARS-8.4
Paper Title PUNet: Temporal Action Proposal Generation with Positive Unlabeled Learning using Key Frame Annotations
Authors Noor ul Sehr Zia, Osman Semih Kayhan, Jan C. van Gemert, Delft University of Technology, Netherlands
SessionARS-8: Image and Video Mid-Level Analysis
LocationArea I
Session Time:Monday, 20 September, 13:30 - 15:00
Presentation Time:Monday, 20 September, 13:30 - 15:00
Presentation Poster
Topic Image and Video Analysis, Synthesis, and Retrieval: Image & Video Mid-Level Analysis
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Popular approaches to classifying action segments in long, realistic, untrimmed videos start with high quality action proposals. Current action proposal methods based on deep learning are trained on labeled video segments. Obtaining annotated segments for untrimmed videos is time consuming, expensive and error-prone as annotated temporal action boundaries are imprecise, subjective and inconsistent. By embracing this uncertainty we explore to significantly speed up temporal annotations by using just a single key frame label for each action instance instead of the inherently imprecise start and end frames. To tackle the class imbalance by using only a single frame, we evaluate an extremely simple Positive-Unlabeled algorithm (PU-learning). We demonstrate on THUMOS'14 and ActivityNet that using a single key frame label give good results while being significantly faster to annotate. In addition, we show that our simple method, PUNet, is data-efficient which further reduces the need for expensive annotations.