English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multimodal Emotion Recognition in Conversation (ERC) has garnered growingattention from research communities in various fields. In this paper, wepropose a cross-modal fusion network with emotion-shift awareness (CFN-ESA) forERC. Extant approaches employ each modality equally without distinguishing theamount of emotional information, rendering it hard to adequately extractcomplementary and associative information from multimodal data. To cope withthis problem, in CFN-ESA, textual modalities are treated as the primary sourceof emotional information, while visual and acoustic modalities are taken as thesecondary sources. Besides, most multimodal ERC models ignore emotion-shiftinformation and overfocus on contextual information, leading to the failure ofemotion recognition under emotion-shift scenario. We elaborate an emotion-shiftmodule to address this challenge. CFN-ESA mainly consists of the unimodalencoder (RUME), cross-modal encoder (ACME), and emotion-shift module (LESM).RUME is applied to extract conversation-level contextual emotional cues whilepulling together the data distributions between modalities; ACME is utilized toperform multimodal interaction centered on textual modality; LESM is used tomodel emotion shift and capture related information, thereby guide the learningof the main task. Experimental results demonstrate that CFN-ESA can effectivelypromote performance for ERC and remarkably outperform the state-of-the-artmodels.

CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition