| Home | << 1 >> |
|
| Record | Links | |||||
|---|---|---|---|---|---|---|
Author  |
Esteve Cervantes; Long Long Yu; Andrew Bagdanov; Marc Masana; Joost Van de Weijer |
 
|
||||
| Title | Hierarchical Part Detection with Deep Neural Networks | Type | Conference Article | |||
| Year | 2016 | Publication | 23rd IEEE International Conference on Image Processing | Abbreviated Journal | ||
| Volume | Issue | Pages | ||||
| Keywords | Object Recognition; Part Detection; Convolutional Neural Networks | |||||
| Abstract | Part detection is an important aspect of object recognition. Most approaches apply object proposals to generate hundreds of possible part bounding box candidates which are then evaluated by part classifiers. Recently several methods have investigated directly regressing to a limited set of bounding boxes from deep neural network representation. However, for object parts such methods may be unfeasible due to their relatively small size with respect to the image. We propose a hierarchical method for object and part detection. In a single network we first detect the object and then regress to part location proposals based only on the feature representation inside the object. Experiments show that our hierarchical approach outperforms a network which directly regresses the part locations. We also show that our approach obtains part detection accuracy comparable or better than state-of-the-art on the CUB-200 bird and Fashionista clothing item datasets with only a fraction of the number of part proposals. | |||||
| Address | Phoenix; Arizona; USA; September 2016 | |||||
| Corporate Author | Thesis | |||||
| Publisher | Place of Publication | Editor | ||||
| Language | Summary Language | Original Title | ||||
| Series Editor | Series Title | Abbreviated Series Title | ||||
| Series Volume | Series Issue | Edition | ||||
| ISSN | ISBN | Medium | ||||
| Area | Expedition | Conference | ICIP | |||
| Notes | LAMP; 600.106;CIC | Approved | no | |||
| Call Number | Admin @ si @ CLB2016 | Serial | 2762 | |||
| Permanent link to this record | ||||||