mlsanityData to 14 Oct 2026

Gaze Estimation with an Ensemble of Four Architectures

arXiv 2107.01980 ↗First posted 5 Jul 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper presents a method for gaze estimation according to face images. We train several gaze estimators adopting four different network architectures, including an architecture designed for gaze estimation (i.e.,iTracker-MHSA) and three originally designed for general computer vision tasks(i.e., BoTNet, HRNet, ResNeSt). Then, we select the best six estimators and ensemble their predictions through a linear combination. The method ranks the first on the leader-board of ETH-XGaze Competition, achieving an average angular error of 3.11circ on the ETH-XGaze test set.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

14 of 27 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2017Mask R-CNNcited by 7,277
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  6. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  7. 2020ResNeSt: Split-Attention Networkscited by 445
  8. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  9. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  10. 2016Eye Tracking for Everyonecited by 155
  11. 2020ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variationcited by 141
  12. 2017MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimationcited by 118
2 more
  1. 2020A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimationcited by 66
  2. 2019Appearance-Based Gaze Estimation Using Dilated-Convolutionscited by 46

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  2. 2022Unsupervised High-Resolution Portrait Gaze Correction and Animationcited by 5
  3. 2023Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimationcited by 2
  4. 2024Merging Multiple Datasets for Improved Appearance-Based Gaze Estimationcited by 2
  5. 2025Pose-Robust Calibration Strategy for Point-of-Gaze Estimation on Mobile Phonescited by 0
  6. 2026From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanationcited by 0