Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation

• URL: http://arxiv.org/abs/2603.11468v1
• Date: Thu, 12 Mar 2026 02:45:41 GMT
• Title: Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation
• Abstract summary: We propose a Stage-Adaptive reliability modeling framework that explicitly estimates and calibrates modality-wise confidence during multimodal integration.<n>SAGE introduces a reliability-aware fusion mechanism that dynamically rebalances audio and visual representations according to their stage-dependent informativeness.<n>Experiments on the Aff-Wild2 benchmark demonstrate that SAGE consistently improves concordance correlation coefficient scores compared with existing multimodal fusion approaches.
• Score: 11.761508894410182
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Continuous valence-arousal estimation in real-world environments is challenging due to inconsistent modality reliability and interaction-dependent variability in audio-visual signals. Existing approaches primarily focus on modeling temporal dynamics, often overlooking the fact that modality reliability can vary substantially across interaction stages. To address this issue, we propose SAGE, a Stage-Adaptive reliability modeling framework that explicitly estimates and calibrates modality-wise confidence during multimodal integration. SAGE introduces a reliability-aware fusion mechanism that dynamically rebalances audio and visual representations according to their stage-dependent informativeness, preventing unreliable signals from dominating the prediction process. By separating reliability estimation from feature representation, the proposed framework enables more stable emotion estimation under cross-modal noise, occlusion, and varying interaction conditions. Extensive experiments on the Aff-Wild2 benchmark demonstrate that SAGE consistently improves concordance correlation coefficient scores compared with existing multimodal fusion approaches, highlighting the effectiveness of reliability-driven modeling for continuous affect prediction.

Related papers

• RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty [0.5249805590164902]
  RiVaT-Fuse is a reliability-calibrated variational tensor fusion framework for image-metadata prediction.<n>It estimates a consensus latent state through a variational objective that balances image evidence, metadata evidence, structured cross-modal interaction, and stability.<n>On an image-level image-metadata prediction benchmark, RiVaT-Fuse achieves the strongest overall predictive rank among direct representation-level baselines.
  arXiv  Detail & Related papers  (2026-09-09T19:59:49Z)
• Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations [9.993152436695421]
  We argue that modality reliability is a central variable in incomplete-observation settings. Failure to model it explicitly gives rise to two related issues.<n>We propose Modality Reliability-Calibrated Framework for Multimodal Sentiment Analysis with incomplete observations.<n> MRCF contains a Reliability-Aware Branch that estimates sample-specific modality reliability from intramodal quality cues and cross-modal semantic consistency.<n>Experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS show that MRCF achieves strong performance under standard incomplete-observation protocols.
  arXiv  Detail & Related papers  (2026-08-04T13:02:48Z)
• DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models [16.097057987606714]
  We introduce textbfDecoupled textbfUpdate textbfDynamics textbf(DUD), a framework that explicitly decouples FFN and Attention contributions via noise-induced causal interventions.<n>By quantifying the independent restoration capabilities of each module, we construct a dual-stream dynamic profile that captures the model's internal fragility.
  arXiv  Detail & Related papers  (2026-08-04T10:04:33Z)
• Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model [3.294954749518474]
  Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses.<n>We introduce a Hidden Markov Model to capture sequential dependence in benchmark-constructed interaction sessions.<n>The results suggest that ignoring sequential dependence may lead to overconfident reliability estimates.
  arXiv  Detail & Related papers  (2026-07-24T23:34:40Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities [26.613566093134065]
  Multimodal Sentiment Analysis seeks to infer human emotions by integrating textual, acoustic, and visual cues.<n>Existing approaches often rely on all modalities are completeness, whereas real-world applications frequently encounter noise, hardware failures, or privacy restrictions that result in missing modalities.<n>We propose PRLF, a Progressive Representation Learning Framework designed for MSA under uncertain missing-modality conditions.
  arXiv  Detail & Related papers  (2026-03-10T02:45:02Z)
• Uncertainty-Resilient Multimodal Learning via Consistency-Guided Cross-Modal Transfer [0.0]
  This thesis explores uncertainty-resilient multimodal learning through consistency-guided cross-modal transfer.<n>The central idea is to use cross-modal semantic consistency as a basis for robust representation learning.<n>Building on this foundation, the thesis investigates strategies to enhance semantic robustness, improve data efficiency, and reduce the impact of noise and imperfect supervision.
  arXiv  Detail & Related papers  (2025-11-18T15:26:42Z)
• Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models [9.353236468990945]
  This paper addresses the limitations of large-scale language models in safety alignment and robustness.<n>It proposes a fine-tuning method that combines contrastive distillation with noise-robust training.<n>Results show that the method significantly outperforms existing baselines in knowledge transfer, robustness, and overall safety.
  arXiv  Detail & Related papers  (2025-10-31T00:54:33Z)
• MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics [72.00014675808228]
  Instability in Large Language Models evaluation process obscures true learning dynamics.<n>We introduce textbfMaP, a framework that integrates underlineMerging underlineand the underlinePass@k metric.<n>Experiments show that MaP yields significantly smoother performance curves, reduces inter-run variance, and ensures more consistent rankings.
  arXiv  Detail & Related papers  (2025-10-10T11:40:27Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation [26.580361841501514]
  Vision-language models (VLMs) excel in various multimodal tasks but frequently suffer from poor calibration.<n>This miscalibration undermines user trust, especially when models confidently provide incorrect or fabricated information.<n>We propose a novel Confidence through Semantic Perturbation (CSP) framework to improve the calibration of verbalized confidence for object-centric queries.
  arXiv  Detail & Related papers  (2025-04-21T04:01:22Z)
• ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning [26.369237406972577]
  Vision-centric semantic occupancy prediction plays a crucial role in autonomous driving. There is still few research effort to explore the reliability in predicting semantic occupancy from camera. We propose ReliOcc, a method designed to enhance the reliability of camera-based occupancy networks.
  arXiv  Detail & Related papers  (2024-09-26T16:33:16Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)
• Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions [91.63716984911278]
  We introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result. Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks.
  arXiv  Detail & Related papers  (2021-11-11T14:28:12Z)
• Trusted Multi-View Classification [76.73585034192894]
  We propose a novel multi-view classification method, termed trusted multi-view classification. It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
  arXiv  Detail & Related papers  (2021-02-03T13:30:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.