SubmissionNumber#=%=#50
FinalPaperTitle#=%=#UWBA at SemEval-2024 Task 3: Dialogue Representation and Multimodal Fusion for Emotion Cause Analysis
ShortPaperTitle#=%=#
NumberOfPages#=%=#10
CopyrightSigned#=%=#Jiri Martinek
JobTitle#==#
Organization#==#
Abstract#==#In this paper, we present an approach for solving SemEval-2024 Task 3: The Competition of Multimodal Emotion Cause Analysis in Conversations. The task includes two subtasks that focus on emotion-cause pair extraction using text, video, and audio modalities. Our approach is composed of encoding all modalities (MFCC and Wav2Vec for audio, 3D-CNN for video, and transformer-based models for text) and combining them in an utterance-level fusion module. The model is then optimized for link and emotion prediction simultaneously. Our approach achieved 6th place in both subtasks. 
The full leaderboard can be found at https://codalab.lisn.upsaclay.fr/competitions/16141#results
Author{1}{Firstname}#=%=#Josef
Author{1}{Lastname}#=%=#Baloun
Author{1}{Email}#=%=#balounj@ntis.zcu.cz
Author{1}{Affiliation}#=%=#University of West Bohemia
Author{2}{Firstname}#=%=#Jiri
Author{2}{Lastname}#=%=#Martinek
Author{2}{Username}#=%=#jimar
Author{2}{Email}#=%=#jimar@kiv.zcu.cz
Author{2}{Affiliation}#=%=#University of West Bohemia
Author{3}{Firstname}#=%=#Ladislav
Author{3}{Lastname}#=%=#Lenc
Author{3}{Username}#=%=#llenc
Author{3}{Email}#=%=#llenc@kiv.zcu.cz
Author{3}{Affiliation}#=%=#University of West Bohemia
Author{4}{Firstname}#=%=#Pavel
Author{4}{Lastname}#=%=#Kral
Author{4}{Username}#=%=#pkral
Author{4}{Email}#=%=#pkral@kiv.zcu.cz
Author{4}{Affiliation}#=%=#University of West Bohemia, Dept. of Computer Science and Engineering
Author{5}{Firstname}#=%=#Matěj
Author{5}{Lastname}#=%=#Zeman
Author{5}{Email}#=%=#zemanm98@students.zcu.cz
Author{5}{Affiliation}#=%=#University of West Bohemia
Author{6}{Firstname}#=%=#Lukáš
Author{6}{Lastname}#=%=#Vlček
Author{6}{Email}#=%=#vlcek0@students.zcu.cz
Author{6}{Affiliation}#=%=#University of West Bohemia

==========
èéáğö