Neural Multimodal Cooperative Learning Toward Micro-Video Understanding

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Neural Multimodal Cooperative Learning Toward Micro-Video Understanding

By: 
Yinwei Wei; Xiang Wang; Weili Guan; Liqiang Nie; Zhouchen Lin; Baoquan Chen

The prevailing characteristics of micro-videos result in the less descriptive power of each modality. The micro-video representations, several pioneer efforts proposed, are limited in implicitly exploring the consistency between different modality information but ignore the complementarity. In this paper, we focus on how to explicitly separate the consistent features and the complementary features from the mixed information and harness their combination to improve the expressiveness of each modality. Toward this end, we present a neural multimodal cooperative learning (NMCL) model to split the consistent component and the complementary component by a novel relation-aware attention mechanism. Specifically, the computed attention score can be used to measure the correlation between the features extracted from different modalities. Then, a threshold is learned for each modality to distinguish the consistent and complementary features according to the score. Thereafter, we integrate the consistent parts to enhance the representations and supplement the complementary ones to reinforce the information in each modality. As to the problem of redundant information, which may cause overfitting and is hard to distinguish, we devise an attention network to dynamically capture the features which closely related the category and output a discriminative representation for prediction. The experimental results on a real-world micro-video dataset show that the NMCL outperforms the state-of-the-art methods. Further studies verify the effectiveness and cooperative effects brought by the attentive mechanism.

SPS on Twitter

  • is now accepting papers through Wednesday, 13 December! The conference heads to London in July and is see… https://t.co/Z1KqYXWtGY
  • The IEEE Journal of Selected Topics in Signal Processing is now accepting papers for a Special Issue on Domain Enri… https://t.co/ZX6U9oGCZe
  • New webinar alert! Join us this Tuesday, 10 December for "Toward Efficient and Flexible CNN-based Denoising in Phot… https://t.co/FiizKIEfAO

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar