@inproceedings{pan-etal-2026-state,
title = "State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition",
author = "Pan, Zhaoyan and
Li, Xiangdong and
Wu, Wenke and
Ma, Mengting and
Lou, Ye and
Zhou, Ji and
Pan, Jiatong and
Zhang, Wei",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.76/",
pages = "1663--1687",
ISBN = "979-8-89176-439-2",
abstract = "Conversational multimodal emotion recognition MER requires reliable prediction when language acoustic or visual observations are missing or unreliable. Many missing-modality methods reconstruct absent inputs yet such recovery can be non-unique in dialogue context and nonverbal cues may conflict with the target utterance. To this end we propose CoRe-KD Complete-view Reference-guided Knowledge Distillation a state-anchored conflict-regularized complete-view distillation framework for robust conversational MER. A complete-view teacher provides structured references including prediction-level references fused states and modality-specific states. Complete-view State Anchoring CSA aligns incomplete-view student predictions and states with these references while Nonverbal Conflict Exposure NCE trains on target-preserving nonverbal conflict views to reduce donor-label bias. Experiments on IEMOCAP and MELD with CMU-MOSEI as a supplementary utterance-level check show consistent gains under fixed- and random-missing protocols. Comprehensive ablation studies and further analyses support the role of CSA and the complementary effect of NCE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2026-state">
<titleInfo>
<title>State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaoyan</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangdong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenke</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengting</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiatong</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Conversational multimodal emotion recognition MER requires reliable prediction when language acoustic or visual observations are missing or unreliable. Many missing-modality methods reconstruct absent inputs yet such recovery can be non-unique in dialogue context and nonverbal cues may conflict with the target utterance. To this end we propose CoRe-KD Complete-view Reference-guided Knowledge Distillation a state-anchored conflict-regularized complete-view distillation framework for robust conversational MER. A complete-view teacher provides structured references including prediction-level references fused states and modality-specific states. Complete-view State Anchoring CSA aligns incomplete-view student predictions and states with these references while Nonverbal Conflict Exposure NCE trains on target-preserving nonverbal conflict views to reduce donor-label bias. Experiments on IEMOCAP and MELD with CMU-MOSEI as a supplementary utterance-level check show consistent gains under fixed- and random-missing protocols. Comprehensive ablation studies and further analyses support the role of CSA and the complementary effect of NCE.</abstract>
<identifier type="citekey">pan-etal-2026-state</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.76/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1663</start>
<end>1687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition
%A Pan, Zhaoyan
%A Li, Xiangdong
%A Wu, Wenke
%A Ma, Mengting
%A Lou, Ye
%A Zhou, Ji
%A Pan, Jiatong
%A Zhang, Wei
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F pan-etal-2026-state
%X Conversational multimodal emotion recognition MER requires reliable prediction when language acoustic or visual observations are missing or unreliable. Many missing-modality methods reconstruct absent inputs yet such recovery can be non-unique in dialogue context and nonverbal cues may conflict with the target utterance. To this end we propose CoRe-KD Complete-view Reference-guided Knowledge Distillation a state-anchored conflict-regularized complete-view distillation framework for robust conversational MER. A complete-view teacher provides structured references including prediction-level references fused states and modality-specific states. Complete-view State Anchoring CSA aligns incomplete-view student predictions and states with these references while Nonverbal Conflict Exposure NCE trains on target-preserving nonverbal conflict views to reduce donor-label bias. Experiments on IEMOCAP and MELD with CMU-MOSEI as a supplementary utterance-level check show consistent gains under fixed- and random-missing protocols. Comprehensive ablation studies and further analyses support the role of CSA and the complementary effect of NCE.
%U https://aclanthology.org/2026.aacl-long.76/
%P 1663-1687
Markdown (Informal)
[State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition](https://aclanthology.org/2026.aacl-long.76/) (Pan et al., AACL-IJCNLP 2026)
ACL
- Zhaoyan Pan, Xiangdong Li, Wenke Wu, Mengting Ma, Ye Lou, Ji Zhou, Jiatong Pan, and Wei Zhang. 2026. State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1663–1687, Hengqin, China. Association for Computational Linguistics.