CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yin, Li, Jia, Hu, Jinpeng, Hu, Zhenzhen, Hong, Richang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915500734283776
author Chen, Yin
Li, Jia
Hu, Jinpeng
Hu, Zhenzhen
Hong, Richang
author_facet Chen, Yin
Li, Jia
Hu, Jinpeng
Hu, Zhenzhen
Hong, Richang
contents Audiovisual emotion recognition (AVER) in the wild is still hindered by pose variation, occlusion, and background noise. Prevailing methods primarily rely on large-scale domain-specific pre-training, which is costly and often mismatched to real-world affective data. To address this, we present CLAIP-Emo, a modular framework that reframes in-the-wild AVER as a parameter-efficient adaptation of language-supervised foundation models (CLIP/CLAP). Specifically, it (i) preserves language-supervised priors by freezing CLIP/CLAP backbones and performing emotion-oriented adaptation via LoRA (updating \ensuremath{\le}4.0\% of the total parameters), (ii) allocates temporal modeling asymmetrically, employing a lightweight Transformer for visual dynamics while applying mean pooling for audio prosody, and (iii) applies a simple fusion head for prediction. On DFEW and MAFW, CLAIP-Emo (ViT-L/14) achieves 80.14\% and 61.18\% weighted average recall with only 8M training parameters, setting a new state of the art. Our findings suggest that parameter-efficient adaptation of language-supervised foundation models provides a scalable alternative to domain-specific pre-training for real-world AVER. The code and models will be available at \href{https://github.com/MSA-LMC/CLAIP-Emo}{https://github.com/MSA-LMC/CLAIP-Emo}.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14527
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition
Chen, Yin
Li, Jia
Hu, Jinpeng
Hu, Zhenzhen
Hong, Richang
Multimedia
Sound
Audiovisual emotion recognition (AVER) in the wild is still hindered by pose variation, occlusion, and background noise. Prevailing methods primarily rely on large-scale domain-specific pre-training, which is costly and often mismatched to real-world affective data. To address this, we present CLAIP-Emo, a modular framework that reframes in-the-wild AVER as a parameter-efficient adaptation of language-supervised foundation models (CLIP/CLAP). Specifically, it (i) preserves language-supervised priors by freezing CLIP/CLAP backbones and performing emotion-oriented adaptation via LoRA (updating \ensuremath{\le}4.0\% of the total parameters), (ii) allocates temporal modeling asymmetrically, employing a lightweight Transformer for visual dynamics while applying mean pooling for audio prosody, and (iii) applies a simple fusion head for prediction. On DFEW and MAFW, CLAIP-Emo (ViT-L/14) achieves 80.14\% and 61.18\% weighted average recall with only 8M training parameters, setting a new state of the art. Our findings suggest that parameter-efficient adaptation of language-supervised foundation models provides a scalable alternative to domain-specific pre-training for real-world AVER. The code and models will be available at \href{https://github.com/MSA-LMC/CLAIP-Emo}{https://github.com/MSA-LMC/CLAIP-Emo}.
title CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition
topic Multimedia
Sound
url https://arxiv.org/abs/2509.14527