A new multicultural DFER dataset GCC-FER is presented along with a culture-aware adaptation method that improves recognition performance on GCC-FER and DFEW.
Nr-dfernet: Noise-robust network for dy- namic facial expression recognition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Frame-marginal attention redistribution from confidence and inverse-entropy concentration improves video FER on ViT backbones without new parameters, with a FlashAttention-compatible approximation.
DuSE is a new dual-stream model for dynamic facial expression recognition that explicitly models cognitive priming and conceptual knowledge integration to reach state-of-the-art accuracy on in-the-wild benchmarks.
Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.
citing papers explorer
-
Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognition
A new multicultural DFER dataset GCC-FER is presented along with a culture-aware adaptation method that improves recognition performance on GCC-FER and DFEW.
-
Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding
Frame-marginal attention redistribution from confidence and inverse-entropy concentration improves video FER on ViT backbones without new parameters, with a FlashAttention-compatible approximation.
-
Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling
DuSE is a new dual-stream model for dynamic facial expression recognition that explicitly models cognitive priming and conceptual knowledge integration to reach state-of-the-art accuracy on in-the-wild benchmarks.
-
Recent Advances in Multimodal Affective Computing: An NLP Perspective
Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.
- Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets