MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild
Yiming Lin, Shiyang Cheng, Jie Shen, Maja Pantic

TL;DR
MobiFace introduces a comprehensive dataset of mobile face tracking videos captured in real-world conditions, providing a new benchmark to develop and evaluate mobile face tracking algorithms.
Contribution
This work presents the first dedicated dataset for mobile face tracking, including extensive annotations and evaluation tools, addressing a significant gap in existing benchmarks.
Findings
Existing trackers perform poorly on mobile face tracking.
Fine-tuning deep trackers on MobiFace improves performance.
Mobile face tracking remains a challenging problem.
Abstract
Face tracking serves as the crucial initial step in mobile applications trying to analyse target faces over time in mobile settings. However, this problem has received little attention, mainly due to the scarcity of dedicated face tracking benchmarks. In this work, we introduce MobiFace, the first dataset for single face tracking in mobile situations. It consists of 80 unedited live-streaming mobile videos captured by 70 different smartphone users in fully unconstrained environments. Over bounding boxes are manually labelled. The videos are carefully selected to cover typical smartphone usage. The videos are also annotated with 14 attributes, including 6 newly proposed attributes and 8 commonly seen in object tracking. 36 state-of-the-art trackers, including facial landmark trackers, generic object trackers and trackers that we have fine-tuned or improved, are evaluated. The…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · Video Surveillance and Tracking Methods · Visual Attention and Saliency Detection
