# Towards Unified Dynamic Face Landmark Detection

arXiv: https://arxiv.org/abs/2608.10346 · HTML: https://mlsanity.com/paper/2608.10346/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks](https://mlsanity.com/paper/1711.06753/) (2017)
- [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](https://mlsanity.com/paper/1603.01249/) (2016)
- [LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood](https://mlsanity.com/paper/2004.02980/) (2020)
- [Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild](https://mlsanity.com/paper/2003.03771/) (2020)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [Structured Landmark Detection via Topology-Adapting Deep Graph Learning](https://mlsanity.com/paper/2004.08190/) (2020)
- [Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning](https://mlsanity.com/paper/2203.06541/) (2022)
- [An All-In-One Convolutional Neural Network for Face Analysis](https://mlsanity.com/paper/1611.00851/) (2016)
- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment](https://mlsanity.com/paper/2109.05721/) (2021)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation](https://mlsanity.com/paper/1908.06440/) (2019)
- [Towards Accurate Facial Landmark Detection via Cascaded Transformers](https://mlsanity.com/paper/2208.10808/) (2022)
- [Sparse to Dense Motion Transfer for Face Image Animation](https://mlsanity.com/paper/2109.00471/) (2021)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses](https://mlsanity.com/paper/2007.03221/) (2020)
- [Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking](https://mlsanity.com/paper/1906.02260/) (2019)
- [Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example](https://mlsanity.com/paper/2105.06407/) (2021)
- [FreeEnricher: Enriching Face Landmarks without Additional Cost](https://mlsanity.com/paper/2212.09525/) (2022)

## Abstract (arXiv)

Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations: (1) different network parameters need to be trained independently for each ``N-point'' benchmark dataset, and (2) a model trained on an ``N-point'' dataset reliably outputs only the N landmarks. In our work, we first conceptualize Face Part-Anchored Landmark Positions (FPALPs), wherein each landmark is treated as a progression value between zero (start) and one (end) along a face part's contour. Every landmark can be expressed in the FPALP format, irrespective of its source dataset, hence unlocking the ability to unify all ``N-point'' datasets into a single dataset. Secondly, we represent each landmark with an FPALP-based query, refine it progressively with a cross-modality decoder, and predict its coordinates based on the final representation. Our approach, called Unified Dynamic FLD, embodies these two design choices and streamlines the landmark detection pipeline by enabling (1) a single model to learn on any number of ``N-point'' datasets, and (2) yield any number of specific landmark predictions by loading the designated landmark queries at runtime. Extensive experiments on multiple benchmark datasets show that our method delivers these benefits while remaining competitive with, and in several cases outperforming existing state-of-the-art methods.