Semantic Pyramids for Gender and Action Recognition

  title={Semantic Pyramids for Gender and Action Recognition},
  author={Fahad Shahbaz Khan and Joost van de Weijer and Rao Muhammad Anwer and Michael Felsberg and Carlo Gatta},
  journal={IEEE Transactions on Image Processing},
Person description is a challenging problem in computer vision. We investigated two major aspects of person description: 1) gender and 2) action recognition in still images. Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part, such as face or full-body. However, relying on a single body part is suboptimal due to significant variations in scale, viewpoint, and pose in real-world images. This paper proposes a semantic pyramid approach… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS

13 Figures & Tables



Citations per Year

Citation Velocity: 11

Averaging 11 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.