Gaze Embeddings for Zero-Shot Image Classification
| Authors |
|
|---|---|
| Publication date | 2017 |
| Book title | 30th IEEE Conference on Computer Vision and Pattern Recognition |
| Book subtitle | CVPR 2017 : 21-26 July 2016, Honolulu, Hawaii : proceedings |
| ISBN |
|
| ISBN (electronic) |
|
| Event | 2017 IEEE Conference on Computer Vision and Pattern Recognition |
| Pages (from-to) | 6412-6421 |
| Publisher | Piscataway, NJ: IEEE |
| Organisations |
|
| Abstract |
Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as auxiliary information, exploiting that even non-expert users have a natural ability to judge class membership. We present a data collection paradigm that involves a discrimination task to increase the information content obtained from gaze data. Our method extracts discriminative descriptors from the data and learns a compatibility function between image and gaze using three novel gaze embeddings: Gaze Histograms (GH), Gaze Features with Grid (GFG) and Gaze Features with Sequence (GFS). We introduce two new gaze-annotated datasets for fine-grained image classification and show that human gaze data is indeed class discriminative, provides a competitive alternative to expert-annotated attributes, and outperforms other baselines for zero-shot image classification.
|
| Document type | Conference contribution |
| Language | English |
| Published at | https://doi.org/10.1109/CVPR.2017.679 |
| Published at | https://arxiv.org/abs/1611.09309 |
| Downloads |
1611.09309.pd
(Accepted author manuscript)
|
| Permalink to this page | |
