Automated video labelling: identifying faces by corroborative evidence
We present a method for automatically labelling all faces in video archives, such as TV broadcasts, by combining multiple evidence sources and multiple modalities (visual and audio). We target the problem of ever-growing online video archives, where an effective, scalable indexing solution cannot re...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2021
|
| _version_ | 1826261662053695488 |
|---|---|
| author | Brown, A Coto, E Zisserman, A |
| author_facet | Brown, A Coto, E Zisserman, A |
| author_sort | Brown, A |
| collection | OXFORD |
| description | We present a method for automatically labelling all faces in video archives, such as TV broadcasts, by combining multiple evidence sources and multiple modalities (visual and audio). We target the problem of ever-growing online video archives, where an effective, scalable indexing solution cannot require a user to provide manual annotation or supervision. To this end, we make three key contributions: (1) We provide a novel, simple, method for determining if a person is famous or not using image-search engines. In turn this enables a face-identity model to be built reliably and robustly, and used for high precision automatic labelling; (2) We show that even for less-famous people, image-search engines can then be used for corroborative evidence to accurately label faces that are named in the scene or the speech; (3) Finally, we quantitatively demonstrate the benefits of our approach on different video domains and test settings, such as TV shows and news broadcasts. Our method works across three disparate datasets without any explicit domain adaptation, and sets new state-of-the-art results on all the public benchmarks. |
| first_indexed | 2024-03-06T19:24:53Z |
| format | Conference item |
| id | oxford-uuid:1b5c689c-65a8-445c-9c04-bd7567a20f42 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T19:24:53Z |
| publishDate | 2021 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:1b5c689c-65a8-445c-9c04-bd7567a20f422022-03-26T11:00:00ZAutomated video labelling: identifying faces by corroborative evidenceConference itemhttp://purl.org/coar/resource_type/c_5794uuid:1b5c689c-65a8-445c-9c04-bd7567a20f42EnglishSymplectic ElementsIEEE2021Brown, ACoto, EZisserman, AWe present a method for automatically labelling all faces in video archives, such as TV broadcasts, by combining multiple evidence sources and multiple modalities (visual and audio). We target the problem of ever-growing online video archives, where an effective, scalable indexing solution cannot require a user to provide manual annotation or supervision. To this end, we make three key contributions: (1) We provide a novel, simple, method for determining if a person is famous or not using image-search engines. In turn this enables a face-identity model to be built reliably and robustly, and used for high precision automatic labelling; (2) We show that even for less-famous people, image-search engines can then be used for corroborative evidence to accurately label faces that are named in the scene or the speech; (3) Finally, we quantitatively demonstrate the benefits of our approach on different video domains and test settings, such as TV shows and news broadcasts. Our method works across three disparate datasets without any explicit domain adaptation, and sets new state-of-the-art results on all the public benchmarks. |
| spellingShingle | Brown, A Coto, E Zisserman, A Automated video labelling: identifying faces by corroborative evidence |
| title | Automated video labelling: identifying faces by corroborative evidence |
| title_full | Automated video labelling: identifying faces by corroborative evidence |
| title_fullStr | Automated video labelling: identifying faces by corroborative evidence |
| title_full_unstemmed | Automated video labelling: identifying faces by corroborative evidence |
| title_short | Automated video labelling: identifying faces by corroborative evidence |
| title_sort | automated video labelling identifying faces by corroborative evidence |
| work_keys_str_mv | AT browna automatedvideolabellingidentifyingfacesbycorroborativeevidence AT cotoe automatedvideolabellingidentifyingfacesbycorroborativeevidence AT zissermana automatedvideolabellingidentifyingfacesbycorroborativeevidence |