paper-with-me

홈 › Papers

Evaluating and Correcting Human Annotation Bias in Dynamic Micro-Expression Recognition

2026-03-05 · Feng Liu, Bingyu Nan, Xuezhong Qian, Xiaolan Fu arxiv

Existing manual labeling of micro-expressions is subject to errors in accuracy, especially in cross-cultural scenarios where deviation in labeling of key frames is more prominent. To address this issue, this paper presents a novel Global Anti-Monotonic Differential Selection Strategy (GAMDSS) architecture for enhancing the effectiveness of spatio-temporal modeling of micro-expressions through keyframe re-selection. Specifically, the method identifies Onset and Apex frames, which are characterized by significant micro-expression variation, from complete micro-expression action sequences via a dynamic frame reselection mechanism. It then uses these to determine Offset frames and construct a rich spatio-temporal dynamic representation. A two-branch structure with shared parameters is then used to efficiently extract spatio-temporal features. Extensive experiments are conducted on seven widely recognized micro-expression datasets. The results demonstrate that GAMDSS effectively reduces subjective errors caused by human factors in multicultural datasets such as SAMM and 4DME. Furthermore, quantitative analyses confirm that offset-frame annotations in multicultural datasets are more uncertain, providing theoretical justification for standardizing micro-expression annotations. These findings directly support our argument for reconsidering the validity and generalizability of dataset annotation paradigms. Notably, this design can be integrated into existing models without increasing the number of parameters, offering a new approach to enhancing micro-expression recognition performance. The source code is available on GitHub[https://github.com/Cross-Innovation-Lab/GAMDSS].

📄 PDF Abstract BibTeX arXiv:2603.04766

Code (0)

등록된 구현이 없습니다.

Tasks

Micro-Expression Recognition

Similar Papers 제목 키워드 기반

PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation

2026-01-26 · Abhishek Divekar, Anirban Majumder arxiv

Evaluating the quality of search, ranking and RAG systems traditionally requires a significant number of human relevance annotations. In recent times, several deployed systems have explored the usage of Large Language Mo…

Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models

2019-12-02 · Shruti Bhargava, David Forsyth

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the wo…

Gender ClassificationImage Captioning

Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench

2026-04-17 · Bhaskar Gurram arxiv

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task be…

Generating Labels for Regression of Subjective Constructs using Triplet Embeddings

2019-04-02 · Karel Mundnich, Brandon M. Booth, Benjamin Girault, Shrikanth Narayanan

Human annotations serve an important role in computational models where the target constructs under study are hidden, such as dimensions of affect. This is especially relevant in machine learning, where subjective labels…

regressionTriplet

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation

2021-11-07 · Shanyan Guan, Jingwei Xu, Michelle Z. He, Yunbo Wang 외

We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affected by the distribution shift represented …

3D Absolute Human Pose Estimation3D Human Pose EstimationBilevel Optimization