Label Distribution Learning

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition
Sep 15, 2026Yiming Wang, Frederick W. B. Li, Jingyun WangAnnotator Disagreement Uncertainty Quantification
Department of Computer Science, Durham University
Multi-Label Proportion Learning for Sea-Ice Type Prediction
Sep 14, 2026Samira Alkaee Taleghan, Younghyun Koo, Andrew P. Barrett +1Label Distribution Learning Remote Sensing
University of Colorado Denver Denver, Colorado, USA · National Snow and Ice Data Center (NSIDC), CIRES, University of Colorado Boulder Boulder, Colorado, USA
Post-hoc Alignment of LLM-judges to Human Judgment Distribution
Sep 1, 2026Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1Soft-Label Learning LLM Alignment
Amazon, Barcelona, Spain · Amazon, Berlin, Germany
D3O: Dynamic Distribution Distillation for Ordinal Regression
Jul 26, 2026Chunlai Dong, Yaojun Hu, Yuyang Xu +2Label Distribution Learning Ordinal Regression
Zhejiang University Hangzhou, China
Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions
Jul 19, 2026Sosuke Suzuki, Yijin Wei, Koichiro Kamide +3Label Distribution Learning Emotion Recognition
University of Toyama · Department of Engineering · Toyama-city, Japan +6
Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition
Jun 25, 2026Zahra Omidi, John H. L. HansenAnnotator Disagreement Label Distribution Learning
Center for Robust Speech Systems, The University of Texas at Dallas, USA
SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs
Jun 3, 2026Jingyao Wu, Ashley Wang, Keane Ong +2RL for Language Models LLM Alignment
MIT Media Lab, Massachusetts Institute of Technology · National University of Singapore
Metric-Dependent Annotation Saturation for Learning from Label Distributions
May 28, 2026Guneet KohliSoft-Label Learning Annotator Disagreement
Apple
From Kellgren-Lawrence to Calcium Pyrophosphate Crystal Deposition: A Soft-Labelling Framework for Knee Osteoarthritis Assessmen
May 27, 2026Francisco Bérchez-Moreno, Riccardo Rosati, Maria Chiara Fiorentino +6Label Distribution Learning Medical Image Classification
Departamento de Ciencia de la Computación e Inteligencia Artificial, Universidad de Córdoba, Córdoba, España · Department of Political Science, Communication, and International Relations, University of Macerata, Macerata, Italy · Department of Innovative Technologies in Medicine & Dentistry, Università degli Studi "G. D’Annunzio" Chieti - Pescara, Chieti, Italy +5
Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions
May 20, 2026Mirerfan Gheibi, Gashin GhazizadehAnnotator Disagreement Label Distribution Learning
Independent Researcher.
Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
May 6, 2026Junxiang Wu, Zhiqiang Kou, Hongwei Zeng +7Federated Learning Aggregation Label Distribution Learning
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China · University of the Chinese Academy of Sciences, China +3
Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
Date pendingAndreas Spilz, Heiko Oppel, Michael MunzHuman Activity Recognition Label Distribution Learning
AI for Sensor Data Analytics Research Group, Ulm University of Applied Sciences, 89081 Ulm, Germany

Sep 15, 2026, cs.CVJ/K move · Enter open · S save

Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition

Yiming Wang, Frederick W. B. Li, Jingyun Wang

Department of Computer Science, Durham University

Annotator Disagreement Uncertainty Quantification Selective Prediction Label Distribution Learning Facial Expression Recognition

Open paper AskPDF arXiv

Dynamic facial expression recognition (DFER) benchmarks such as DFEW provide multiple annotator votes per clip, yet most models collapse them to a majority label and cannot represent human disagreement at inference time. We propose a disagreement-aware DFER framework that trains directly on the raw annotator count vector using a Dirichlet-Multinomial likelihood. Unlike mean-only soft-label objectives, the proposed likelihood provides scale-sensitive supervision for the Dirichlet concentration while preserving the predictive mean. A separate ambiguity head predicts annotation entropy for unseen clips, and a monotone Chow-style reject rule combines predicted ambiguity, vacuity, temporal instability, and input quality for selective prediction. On DFEW, the method preserves recognition accuracy while reducing ECE by 30% and AURC by 15%, and predicted ambiguity reaches a Spearman correlation of 0.52 with the annotation entropy of test clips. The calibration and selective-prediction gains transfer to FERV39k and remain under identity- and movie-disjoint DFEW splits.

Momentum

Related topics

Latest papers 12