The truth about cats and dogs
Template-based object detectors such as the deformable parts model of Felzenszwalb et al. [11] achieve state-of-the-art performance for a variety of object categories, but are still outperformed by simpler bag-of-words models for highly flexible objects such as cats and dogs. In these cases we propo...
| Autores principales: | , , , |
|---|---|
| Formato: | Conference item |
| Lenguaje: | English |
| Publicado: |
IEEE
2012
|
| _version_ | 1826316923188543488 |
|---|---|
| author | Parkhi, O Vedaldi, A Jawahar, C Zisserman, A |
| author_facet | Parkhi, O Vedaldi, A Jawahar, C Zisserman, A |
| author_sort | Parkhi, O |
| collection | OXFORD |
| description | Template-based object detectors such as the deformable parts model of Felzenszwalb et al. [11] achieve state-of-the-art performance for a variety of object categories, but are still outperformed by simpler bag-of-words models for highly flexible objects such as cats and dogs. In these cases we propose to use the template-based model to detect a distinctive part for the class, followed by detecting the rest of the object via segmentation on image specific information learnt from that part. This approach is motivated by two ob- servations: (i) many object classes contain distinctive parts that can be detected very reliably by template-based detec- tors, whilst the entire object cannot; (ii) many classes (e.g. animals) have fairly homogeneous coloring and texture that can be used to segment the object once a sample is provided in an image. We show quantitatively that our method substantially outperforms whole-body template-based detectors for these highly deformable object categories, and indeed achieves accuracy comparable to the state-of-the-art on the PASCAL VOC competition, which includes other models such as bag-of-words. © 2011 IEEE. |
| first_indexed | 2024-03-07T03:36:07Z |
| format | Conference item |
| id | oxford-uuid:bc56fd8f-c89e-4bc0-bf14-344b3c1df9d1 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:30:30Z |
| publishDate | 2012 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:bc56fd8f-c89e-4bc0-bf14-344b3c1df9d12024-12-18T16:08:32ZThe truth about cats and dogsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:bc56fd8f-c89e-4bc0-bf14-344b3c1df9d1EnglishSymplectic Elements at OxfordIEEE2012Parkhi, OVedaldi, AJawahar, CZisserman, ATemplate-based object detectors such as the deformable parts model of Felzenszwalb et al. [11] achieve state-of-the-art performance for a variety of object categories, but are still outperformed by simpler bag-of-words models for highly flexible objects such as cats and dogs. In these cases we propose to use the template-based model to detect a distinctive part for the class, followed by detecting the rest of the object via segmentation on image specific information learnt from that part. This approach is motivated by two ob- servations: (i) many object classes contain distinctive parts that can be detected very reliably by template-based detec- tors, whilst the entire object cannot; (ii) many classes (e.g. animals) have fairly homogeneous coloring and texture that can be used to segment the object once a sample is provided in an image. We show quantitatively that our method substantially outperforms whole-body template-based detectors for these highly deformable object categories, and indeed achieves accuracy comparable to the state-of-the-art on the PASCAL VOC competition, which includes other models such as bag-of-words. © 2011 IEEE. |
| spellingShingle | Parkhi, O Vedaldi, A Jawahar, C Zisserman, A The truth about cats and dogs |
| title | The truth about cats and dogs |
| title_full | The truth about cats and dogs |
| title_fullStr | The truth about cats and dogs |
| title_full_unstemmed | The truth about cats and dogs |
| title_short | The truth about cats and dogs |
| title_sort | truth about cats and dogs |
| work_keys_str_mv | AT parkhio thetruthaboutcatsanddogs AT vedaldia thetruthaboutcatsanddogs AT jawaharc thetruthaboutcatsanddogs AT zissermana thetruthaboutcatsanddogs AT parkhio truthaboutcatsanddogs AT vedaldia truthaboutcatsanddogs AT jawaharc truthaboutcatsanddogs AT zissermana truthaboutcatsanddogs |