Research map / Label-efficient and robust learning / Recognition and long-tail

Behaviour4All: A Dependency-Aware Toolkit for in-the-wild Facial Behaviour Analysis

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Behaviour4All, a dependency-aware toolkit for joint facial valence-arousal, expression, and action unit analysis that models structured task dependencies to handle partially labelled heterogeneous datasets.

Problem

Facial behaviour analysis tasks (valence-arousal, expressions, action units) are usually handled independently or with naive multi-task learning, which ignores their structured dependencies and causes negative transfer, gradient conflicts, and poor cross-dataset generalisation, especially with heter

Approach

A dependency-aware multi-task framework that explicitly models the structured relations among VA, EXP and AU tasks, rather than naive multi-task learning, so that partially labelled heterogeneous datasets can be exploited together.

Experimental setup

Baselines: naive multi-task learning

Closest papers by meaning

• Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.87)
• EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (NeurIPS 2025 · similarity 0.85)
• PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation (AAAI 2025 · similarity 0.84)
• Lifting Scheme-Based Implicit Disentanglement of Emotion-Related Facial Dynamics in the Wild (AAAI 2025 · similarity 0.84)
• PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits (ICLR 2026 · similarity 0.83)
• Navigating Label Ambiguity for Facial Expression Recognition in the Wild (AAAI 2025 · similarity 0.83)