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 IDMLR-APPL-IVSMR-1.3
Paper Title SPARSE AND STRUCTURED VISUAL ATTENTION
Authors Pedro Henrique Martins, Instituto de Telecomunicações, Portugal; Vlad Niculae, IvI, University of Amsterdam, Netherlands; Zita Marinho, Institute of Systems and Robotics / Priberam Labs, Portugal; André F. T. Martins, Instituto de Telecomunicações / Unbabel, Portugal
SessionMLR-APPL-IVSMR-1: Machine learning for image and video sensing, modeling and representation 1
LocationArea C
Session Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Poster
Topic Applications of Machine Learning: Machine learning for image & video sensing, modeling, and representation
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their adjacency structure and of their relevance to the text. In this paper, to better link the image structure with the text, we replace the traditional softmax attention mechanism with two alternative sparsity-promoting transformations: sparsemax, which is able to select only the relevant regions (assigning zero weight to the rest), and a newly proposed Total-Variation Sparse Attention (TVmax), which further encourages the joint selection of adjacent spatial locations. Experiments in VQA show gains in accuracy as well as higher similarity to human attention, which suggests better interpretability.