In this paper, we design a novel Cascade Attention Guided Residue Learning GAN (CAR-GAN) to solve the challenging cross-modal audio-to-image translation task. Particularly, it employs cascaded attention guidance and a coarse-to-fine generation strategy. A novel residue learning model is also proposed to tackle the cross-modal class-label dis-match problem between audio and image modality. By introducing the residue module, generators learn to produce residue features between two stages, which pushes the output closer to its corresponding real image in a high-level semantic space. Finally, the proposed joint classification loss facilitates the model generation and keeps consistency in the label domain. Experimental results show the state-of-the-art performance on the cross-modal translation task.

Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation

**Session Chair:** prof. Samuel Rota Bulò

PS T1.1: AI and Deep Learning approaches

poster

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


Bin Duan

1

SHORT BIO

Presentations

Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES