paper-with-me

홈 › Papers

Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction

2024-07-31 · Jingyao Wu, Ting Dang, Vidhyasaharan Sethu, Eliathamby Ambikairajah

There has been a significant focus on modelling emotion ambiguity in recent years, with advancements made in representing emotions as distributions to capture ambiguity. However, there has been comparatively less effort devoted to the consideration of temporal dependencies in emotion distributions which encodes ambiguity in perceived emotions that evolve smoothly over time. Recognizing the benefits of using constrained dynamical neural ordinary differential equations (CD-NODE) to model time series as dynamic processes, we propose an ambiguity-aware dual-constrained Neural ODE approach to model the dynamics of emotion distributions on arousal and valence. In our approach, we utilize ODEs parameterised by neural networks to estimate the distribution parameters, and we integrate additional constraints to restrict the range of the system outputs to ensure the validity of predicted distributions. We evaluated our proposed system on the publicly available RECOLA dataset and observed very promising performance across a range of evaluation metrics.

📄 PDF Abstract BibTeX arXiv:2407.21344

Code (1)

JingyaoWU66/CD-NODE-gamma 공식 구현 pytorch

Tasks

Time Series

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration

2026-07-30 · Cencen Liu, Wen Yin, Dongyang Zhang, Dongmin Li 외 arxiv

All-in-one image restoration aims to handle diverse degradations within a unified framework. Existing methods commonly encode heterogeneous degradation conditions in a shared latent space, where degradation-related cues …

Image Restoration

Dual-Attention Heterogeneous GNN for Multi-robot Collaborative Area Search via Deep Reinforcement Learning

2026-01-07 · Lina Zhu, Jiyu Cheng, Yuehu Liu, Wei Zhang arxiv

In multi-robot collaborative area search, a key challenge is to dynamically balance the two objectives of exploring unknown areas and covering specific targets to be rescued. Existing methods are often constrained by hom…

Reinforcement LearningGraph Neural Network

Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning

2025-07-09 · Yang Chen, Yueqi Duan, Haowen Sun, Jiwen Lu 외 arxiv

This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignore the per-point ambiguities and less dis…

Point Cloud Segmentation3D Semantic SegmentationContrastive LearningPoint Clouds

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

2024-09-09 · Apostolos I. Rikos, Wei Jiang, Themistoklis Charalambous, Karl H. Johansson

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms…

Distributed OptimizationQuantization

Dynamic Network Adaptation at Inference

2022-04-18 · Daniel Mendoza, Caroline Trippel

Machine learning (ML) inference is a real-time workload that must comply with strict Service Level Objectives (SLOs), including latency and accuracy targets. Unfortunately, ensuring that SLOs are not violated in inferenc…

Diversity