Synergy between face alignment and tracking via Discriminative Global Consensus Optimization
An open question in facial landmark localization in video is whether one should perform tracking or tracking-by-detection (i.e. face alignment). Tracking produces fittings of high accuracy but is prone to drifting. Tracking-by-detection is drift-free but results in low accuracy fittings. To provide...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2017
|
| Online Access: | https://eprints.nottingham.ac.uk/44755/ |
| _version_ | 1848796991050481664 |
|---|---|
| author | Khan, Muhammad Haris McDonagh, John Tzimiropoulos, Georgios |
| author_facet | Khan, Muhammad Haris McDonagh, John Tzimiropoulos, Georgios |
| author_sort | Khan, Muhammad Haris |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | An open question in facial landmark localization in video is whether one should perform tracking or tracking-by-detection (i.e. face alignment). Tracking produces fittings of high accuracy but is prone to drifting. Tracking-by-detection is drift-free but results in low accuracy fittings. To provide a solution to this problem, we describe the very first, to the best of our knowledge, synergistic approach between detection (face alignment) and tracking which completely eliminates drifting from face tracking, and does not merely perform tracking-by-detection. Our first main contribution is to show that one can achieve this synergy between detection and tracking using a principled optimization framework based on the theory of Global Variable Consensus Optimization using ADMM; Our second contribution is to show how the proposed analytic framework can be integrated within state-of-the-art discriminative methods for face alignment and tracking based on cascaded regression and deeply learned features. Overall, we call our method Discriminative Global Consensus Model (DGCM). Our third contribution is to show that DGCM achieves large performance improvement over the currently best performing face tracking methods on the most challenging category of the 300-VW dataset. |
| first_indexed | 2025-11-14T19:56:46Z |
| format | Conference or Workshop Item |
| id | nottingham-44755 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:56:46Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-447552020-05-04T19:14:22Z https://eprints.nottingham.ac.uk/44755/ Synergy between face alignment and tracking via Discriminative Global Consensus Optimization Khan, Muhammad Haris McDonagh, John Tzimiropoulos, Georgios An open question in facial landmark localization in video is whether one should perform tracking or tracking-by-detection (i.e. face alignment). Tracking produces fittings of high accuracy but is prone to drifting. Tracking-by-detection is drift-free but results in low accuracy fittings. To provide a solution to this problem, we describe the very first, to the best of our knowledge, synergistic approach between detection (face alignment) and tracking which completely eliminates drifting from face tracking, and does not merely perform tracking-by-detection. Our first main contribution is to show that one can achieve this synergy between detection and tracking using a principled optimization framework based on the theory of Global Variable Consensus Optimization using ADMM; Our second contribution is to show how the proposed analytic framework can be integrated within state-of-the-art discriminative methods for face alignment and tracking based on cascaded regression and deeply learned features. Overall, we call our method Discriminative Global Consensus Model (DGCM). Our third contribution is to show that DGCM achieves large performance improvement over the currently best performing face tracking methods on the most challenging category of the 300-VW dataset. 2017-10-26 Conference or Workshop Item PeerReviewed Khan, Muhammad Haris, McDonagh, John and Tzimiropoulos, Georgios (2017) Synergy between face alignment and tracking via Discriminative Global Consensus Optimization. In: International Conference on Computer Vision (ICCV17), 22-29 Oct 2017, Venice, Italy. http://ieeexplore.ieee.org/document/8237671/ |
| spellingShingle | Khan, Muhammad Haris McDonagh, John Tzimiropoulos, Georgios Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title | Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title_full | Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title_fullStr | Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title_full_unstemmed | Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title_short | Synergy between face alignment and tracking via Discriminative Global Consensus Optimization |
| title_sort | synergy between face alignment and tracking via discriminative global consensus optimization |
| url | https://eprints.nottingham.ac.uk/44755/ https://eprints.nottingham.ac.uk/44755/ |