Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
arXiv:1501.05703
Abstract
We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of 2000 individuals collected from public Flickr photo albums. With only about half of the person images containing a frontal face, the recognition task is very challenging due to the large variations in pose, clothing, camera viewpoint, image resolution and illumination. We propose the Pose Invariant PErson Recognition (PIPER) method, which accumulates the cues of poselet-level person recognizers trained by deep convolutional networks to discount for the pose variations, combined with a face recognizer and a global recognizer. Experiments on three different settings confirm that in our unconstrained setup PIPER significantly improves on the performance of DeepFace, which is one of the best face recognizers as measured on the LFW dataset.
References in corpus (4)
Cited by in corpus (11)
- Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
- Person Re-identification in the Wild
- Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective
- A Domain Based Approach to Social Relation Recognition
- Landmark Detection in Low Resolution Faces with Semi-Supervised Learning
- Natural and Effective Obfuscation by Head Inpainting
- Triplet Online Instance Matching Loss for Person Re-identification
- Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks
- Unifying Identification and Context Learning for Person Recognition
- Characteristic Regularisation for Super-Resolving Face Images
- Person Search in Videos with One Portrait Through Visual and Temporal Links