2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 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 IDMMSP-7.6
Paper Title SEMI-SUPERVISED MULTIMODAL IMAGE TRANSLATION FOR MISSING MODALITY IMPUTATION
Authors Wangbin Sun, Fei Ma, Yang Li, Shao-Lun Huang, Shiguang Ni, Lin Zhang, Tsinghua University, China
SessionMMSP-7: Multimodal Perception, Integration and Multisensory Fusion
LocationGather.Town
Session Time:Friday, 11 June, 13:00 - 13:45
Presentation Time:Friday, 11 June, 13:00 - 13:45
Presentation Poster
Topic Multimedia Signal Processing: Signal Processing for Multimedia Applications
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Missing data is a common problem in multimodal and multi-view learning. It raises a critical challenge for most multimodal algorithms, which are unable to deal with incomplete datasets. Rather than discarding entries with missing modalities, this paper aims to reconstruct the complete image-based multimodal data by imputing missing modalities. We solve the imputation problem as an image translation task, which transforms images in one domain to other domains. Existing image translation techniques either can not fully utilize the information contained in partially complete entries or are limited to the bimodal situation. We propose a semi-supervised algorithm for multimodal learning with missing data, namely Cyclic Autoencoder (CycAE). Specifically, a novel cyclical structure, as well as the correlation among modalities, is integrated to leverage information from complete entries to incomplete ones. Experiments on two multimodal datasets show that our model outperforms state-of-the-art models. Downstream tasks can also benefit from the completed datasets.