Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space

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.

Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space

Difei Gao; Ruiping Wang; Shiguang Shan; Xilin Chen

Solving visual question answering (VQA) task requires recognizing many diverse visual concepts as the answer. These visual concepts contain rich structural semantic meanings, e.g., some concepts in VQA are highly related (e.g., red & blue), some of them are less relevant (e.g., red & standing). It is very natural for humans to efficiently learn concepts by utilizing their semantic meanings to concentrate on distinguishing relevant concepts and eliminate the disturbance of irrelevant concepts. However, previous works usually use a simple MLP to output visual concept as the answer in a flat label space that treats all labels equally, causing limitations in representing and using the semantic meanings of labels. To address this issue, we propose a novel visual recognition module named Dynamic Concept Recognizer (DCR), which is easy to be plugged in an attention-based VQA model, to utilize the semantics of the labels in answer prediction. Concretely, we introduce two key features in DCR: 1) a novel structural label space to depict the difference of semantics between concepts, where the labels in new label space are assigned to different groups according to their meanings. This type of semantic information helps decompose the visual recognizer in VQA into multiple specialized sub-recognizers to improve the capacity and efficiency of the recognizer. 2) A feature attention mechanism to capture the similarity between relevant groups of concepts, e.g., human-related group “chef, waiter” is more related to “swimming, running, etc.” than scene related group “sunny, rainy, etc.”. This type of semantic information helps sub-recognizers for relevant groups to adaptively share part of modules and to share the knowledge between relevant sub-recognizers to facilitate the learning procedure. Extensive experiments on several datasets have shown that the proposed structural label space and DCR module can efficiently learn the visual concept recognition and benefit the performance of th...

SPS on Twitter

  • On 15 September 2022, we are excited to partner with and to bring you a webinar and roundtable,… https://t.co/we14OUl2QV
  • The SPS Webinar Series continues on Monday, 22 August when Dr. Yu-Huan Wu and Dr. Shanghua Gao present “Towards Des… https://t.co/ZkHjQLLn7L
  • CALL FOR PAPERS: The IEEE/ACM Transactions on Audio, Speech, and Language Processing is now accepting submissions f… https://t.co/wkoVBKfE5j
  • DEADLINE EXTENDED: The IEEE Journal of Selected Topics in Signal Processing is now accepting submissions for a Spec… https://t.co/qoRbzFeMLL
  • Our Information Forensics and Security Webinar Series continues on Tuesday, 23 August when Dr. Anderson Rocha prese… https://t.co/q48hnIMfan

SPS Videos

Signal Processing in Home Assistants


Multimedia Forensics

Careers in Signal Processing             


Under the Radar