Fine-grained pose prediction, normalization, and recognition
arXiv: Computer Vision and Pattern Recognition, Volume abs/1511.07063, 2015.
Pose variation and subtle differences in appearance are key challenges to fine-grained classification. While deep networks have markedly improved general recognition, many approaches to fine-grained recognition rely on anchoring networks to parts for better accuracy. Identifying parts to find correspondence discounts pose variation so tha...More
PPT (Upload PPT)