{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multimodal-emotion-recognition","name":"Multimodal Emotion Recognition","slug":"multimodal-emotion-recognition","description_markdown":"This is a leaderboard for multimodal emotion recognition on the IEMOCAP dataset. The modality abbreviations are\r\nA: Acoustic\r\nT: Text\r\nV: Visual\r\n\r\nPlease include the modality in the bracket after the model name.\r\n\r\nAll models must use standard five emotion categories and are evaluated in standard leave-one-session-out (LOSO). See the papers for references.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":180,"papers_with_code":80,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multimodal-emotion-recognition-on-iemocap-4","slug":"multimodal-emotion-recognition-on-iemocap-4","dataset":"IEMOCAP-4","dataset_url":null,"rows_in_archive":11,"metrics":["Weighted F1","Accuracy","F1","Weighted Recall"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-meld","slug":"multimodal-emotion-recognition-on-meld","dataset":"MELD","dataset_url":"/dataset/meld","rows_in_archive":3,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-iemocap","slug":"multimodal-emotion-recognition-on-iemocap","dataset":"IEMOCAP","dataset_url":"/dataset/iemocap","rows_in_archive":2,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-cmu-mosei-1","slug":"multimodal-emotion-recognition-on-cmu-mosei-1","dataset":"CMU-MOSEI-Sentiment","dataset_url":null,"rows_in_archive":1,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-cmu-mosei-2","slug":"multimodal-emotion-recognition-on-cmu-mosei-2","dataset":"CMU-MOSEI-Sentiment-3","dataset_url":null,"rows_in_archive":1,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-expressive","slug":"multimodal-emotion-recognition-on-expressive","dataset":"Expressive hands and faces dataset (EHF).","dataset_url":null,"rows_in_archive":1,"metrics":["v2v error"],"first_row_in_archive_order":{"model":"SMPLify-X","paper_title":"Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning","paper_url":"/paper/multi-modal-emotion-recognition-on-iemocap","paper_date":"2018-04-16","arxiv_id":"1804.05788","code_links":[{"title":"Samarth-Tripathi/IEMOCAP-Emotion-Detection","url":"https://github.com/Samarth-Tripathi/IEMOCAP-Emotion-Detection"},{"title":"ankurbhatia24/MULTIMODAL-EMOTION-RECOGNITION","url":"https://github.com/ankurbhatia24/MULTIMODAL-EMOTION-RECOGNITION"}],"syntology":null}},{"leaderboard":"/sota/multimodal-emotion-recognition-on-meld-1","slug":"multimodal-emotion-recognition-on-meld-1","dataset":"MELD-Sentiment","dataset_url":null,"rows_in_archive":1,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper_title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","paper_url":"/paper/2407-21536","paper_date":"2024-07-31","arxiv_id":"2407.21536","code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}],"syntology":null}}],"datasets":[{"url":"/dataset/iemocap","name":"IEMOCAP","full_name":"The Interactive Emotional Dyadic Motion Capture (IEMOCAP) Database","num_papers_in_archive":749},{"url":"/dataset/meld","name":"MELD","full_name":"Multimodal EmotionLines Dataset","num_papers_in_archive":289},{"url":"/dataset/cmu-mosei","name":"CMU-MOSEI","full_name":"","num_papers_in_archive":190},{"url":"/dataset/emotic","name":"EMOTIC","full_name":"EMOTIons in Context","num_papers_in_archive":38},{"url":"/dataset/cped","name":"CPED","full_name":"Chinese Personalized and Emotional Dialogue","num_papers_in_archive":15},{"url":"/dataset/deap","name":"DEAP","full_name":"","num_papers_in_archive":11},{"url":"/dataset/resd","name":"RESD","full_name":"Russian Emotional Speech Dialogs with annotated text","num_papers_in_archive":3},{"url":"/dataset/aesi","name":"AESI","full_name":"Athens Emotional States Inventory","num_papers_in_archive":1},{"url":"/dataset/ses","name":"SES","full_name":"Spanish Emotional Speech","num_papers_in_archive":1},{"url":"/dataset/werewolf-xl","name":"Werewolf-XL","full_name":"","num_papers_in_archive":1},{"url":"/dataset/storytelling-video-dataset","name":"Video Dataset","full_name":"Storytelling Video Dataset (Russian, Emotion, Gesture, Speech)","num_papers_in_archive":0}],"subtasks":[{"url":"/task/video-emotion-detection","name":"Video Emotion Detection"}],"parent_tasks":[{"url":"/task/emotion-recognition","name":"Emotion Recognition"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":180,"of_with_code":80,"tagged_in_all":180,"counts":{"archive_papers_tagged":180,"with_a_code_link":80,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":180,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/multimodal-speech-emotion-recognition-and","slug":"multimodal-speech-emotion-recognition-and","title":"Multimodal Speech Emotion Recognition and Ambiguity Resolution","date":"2019-04-12","arxiv_id":"1904.06022","repositories_listed":5,"syntology":null},{"url":"/paper/multimodal-speech-emotion-recognition-using","slug":"multimodal-speech-emotion-recognition-using","title":"Multimodal Speech Emotion Recognition Using Audio and Text","date":"2018-10-10","arxiv_id":"1810.04635","repositories_listed":4,"syntology":null},{"url":"/paper/mer-2023-multi-label-learning-modality","slug":"mer-2023-multi-label-learning-modality","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","date":"2023-04-18","arxiv_id":"2304.08981","repositories_listed":3,"syntology":null},{"url":"/paper/audio-text-sentiment-analysis-using-deep","slug":"audio-text-sentiment-analysis-using-deep","title":"Complementary Fusion of Multi-Features and Multi-Modalities in Sentiment Analysis","date":"2019-04-17","arxiv_id":"1904.08138","repositories_listed":3,"syntology":null},{"url":"/paper/m2se-a-multistage-multitask-instruction","slug":"m2se-a-multistage-multitask-instruction","title":"EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding","date":"2024-12-11","arxiv_id":"2412.08049","repositories_listed":2,"syntology":null},{"url":"/paper/text-and-feature-based-models-for-compound","slug":"text-and-feature-based-models-for-compound","title":"Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild","date":"2024-07-17","arxiv_id":"2407.12927","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/text-and-feature-based-models-for-compound#ran","syntology_url":"https://syntology.ai/paper/2407.12927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12927"}},"official":{"repos":["nicolas-richet/feature-vs-text-compound-emotion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/emotion-llama-multimodal-emotion-recognition","slug":"emotion-llama-multimodal-emotion-recognition","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","date":"2024-06-17","arxiv_id":"2406.11161","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/emotion-llama-multimodal-emotion-recognition#ran","syntology_url":"https://syntology.ai/paper/2406.11161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11161"}},"official":{"repos":["zebangcheng/emotion-llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mer-2024-semi-supervised-learning-noise","slug":"mer-2024-semi-supervised-learning-noise","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","date":"2024-04-26","arxiv_id":"2404.17113","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mer-2024-semi-supervised-learning-noise#ran","syntology_url":"https://syntology.ai/paper/2404.17113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17113"}},"official":{"repos":["zeroqiaoba/mertools"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cogmen-contextualized-gnn-based-multimodal","slug":"cogmen-contextualized-gnn-based-multimodal","title":"COGMEN: COntextualized GNN based Multimodal Emotion recognitioN","date":"2022-05-05","arxiv_id":"2205.02455","repositories_listed":2,"syntology":null},{"url":"/paper/emotion-recognition-in-audio-and-video-using","slug":"emotion-recognition-in-audio-and-video-using","title":"Emotion Recognition in Audio and Video Using Deep Neural Networks","date":"2020-06-15","arxiv_id":"2006.08129","repositories_listed":2,"syntology":null},{"url":"/paper/dialoguernn-an-attentive-rnn-for-emotion","slug":"dialoguernn-an-attentive-rnn-for-emotion","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","date":"2018-11-01","arxiv_id":"1811.00405","repositories_listed":2,"syntology":null},{"url":"/paper/multi-modal-emotion-recognition-on-iemocap","slug":"multi-modal-emotion-recognition-on-iemocap","title":"Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning","date":"2018-04-16","arxiv_id":"1804.05788","repositories_listed":2,"syntology":null},{"url":"/paper/context-dependent-sentiment-analysis-in-user","slug":"context-dependent-sentiment-analysis-in-user","title":"Context-Dependent Sentiment Analysis in User-Generated Videos","date":"2017-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-multimodal-emotion-recognition","slug":"end-to-end-multimodal-emotion-recognition","title":"End-to-End Multimodal Emotion Recognition using Deep Neural Networks","date":"2017-04-27","arxiv_id":"1704.08619","repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-multimodal-emotion-recognition","slug":"towards-robust-multimodal-emotion-recognition","title":"Towards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution Shifts","date":"2025-06-12","arxiv_id":"2506.10452","repositories_listed":1,"syntology":null},{"url":"/paper/tacfn-transformer-based-adaptive-cross-modal","slug":"tacfn-transformer-based-adaptive-cross-modal","title":"TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition","date":"2025-05-10","arxiv_id":"2505.06536","repositories_listed":1,"syntology":null},{"url":"/paper/feature-based-dual-visual-feature-extraction","slug":"feature-based-dual-visual-feature-extraction","title":"Feature-Based Dual Visual Feature Extraction Model for Compound Multimodal Emotion Recognition","date":"2025-03-21","arxiv_id":"2503.17453","repositories_listed":1,"syntology":null},{"url":"/paper/r1-omni-explainable-omni-multimodal-emotion","slug":"r1-omni-explainable-omni-multimodal-emotion","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05379","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/r1-omni-explainable-omni-multimodal-emotion#ran","syntology_url":"https://syntology.ai/paper/2503.05379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05379"}},"official":null}},{"url":"/paper/latent-distribution-decoupling-a","slug":"latent-distribution-decoupling-a","title":"Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition","date":"2025-02-19","arxiv_id":"2502.13954","repositories_listed":1,"syntology":null},{"url":"/paper/milmer-a-framework-for-multiple-instance","slug":"milmer-a-framework-for-multiple-instance","title":"Milmer: a Framework for Multiple Instance Learning based Multimodal Emotion Recognition","date":"2025-02-01","arxiv_id":"2502.00547","repositories_listed":1,"syntology":null},{"url":"/paper/sdr-gnn-spectral-domain-reconstruction-graph","slug":"sdr-gnn-spectral-domain-reconstruction-graph","title":"SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition","date":"2024-11-29","arxiv_id":"2411.19822","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-hypercomplex-network-for","slug":"hierarchical-hypercomplex-network-for","title":"Hierarchical Hypercomplex Network for Multimodal Emotion Recognition","date":"2024-09-13","arxiv_id":"2409.09194","repositories_listed":1,"syntology":null},{"url":"/paper/phemonet-a-multimodal-network-for","slug":"phemonet-a-multimodal-network-for","title":"PHemoNet: A Multimodal Network for Physiological Signals","date":"2024-09-13","arxiv_id":"2410.00010","repositories_listed":1,"syntology":null},{"url":"/paper/recent-trends-of-multimodal-affective","slug":"recent-trends-of-multimodal-affective","title":"Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective","date":"2024-09-11","arxiv_id":"2409.07388","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-contrastive-learning-and-self","slug":"leveraging-contrastive-learning-and-self","title":"Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled Samples","date":"2024-08-23","arxiv_id":"2409.04447","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-contrastive-learning-and-self#ran","syntology_url":"https://syntology.ai/paper/2409.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04447"}},"official":{"repos":["wooyoohl/mer2024-semi"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sztu-cmu-at-mer2024-improving-emotion-llama","slug":"sztu-cmu-at-mer2024-improving-emotion-llama","title":"SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition","date":"2024-08-20","arxiv_id":"2408.10500","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sztu-cmu-at-mer2024-improving-emotion-llama#ran","syntology_url":"https://syntology.ai/paper/2408.10500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10500"}},"official":{"repos":["zebangcheng/emotion-llama"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-modal-fusion-by-alignment-and-label","slug":"enhancing-modal-fusion-by-alignment-and-label","title":"Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition","date":"2024-08-18","arxiv_id":"2408.09438","repositories_listed":1,"syntology":null},{"url":"/paper/multi-teacher-privileged-knowledge","slug":"multi-teacher-privileged-knowledge","title":"Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition","date":"2024-08-16","arxiv_id":"2408.09035","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21536","slug":"2407-21536","title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","date":"2024-07-31","arxiv_id":"2407.21536","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-using-audio","slug":"multimodal-emotion-recognition-using-audio","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","date":"2024-07-26","arxiv_id":"2407.18552","repositories_listed":1,"syntology":null},{"url":"/paper/multimae-der-multimodal-masked-autoencoder","slug":"multimae-der-multimodal-masked-autoencoder","title":"MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition","date":"2024-04-28","arxiv_id":"2404.18327","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-sentiment-agents-for-multimodal","slug":"cooperative-sentiment-agents-for-multimodal","title":"Cooperative Sentiment Agents for Multimodal Sentiment Analysis","date":"2024-04-19","arxiv_id":"2404.12642","repositories_listed":1,"syntology":null},{"url":"/paper/mma-dfer-multimodal-adaptation-of-unimodal","slug":"mma-dfer-multimodal-adaptation-of-unimodal","title":"MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild","date":"2024-04-13","arxiv_id":"2404.09010","repositories_listed":1,"syntology":null},{"url":"/paper/mips-at-semeval-2024-task-3-multimodal","slug":"mips-at-semeval-2024-task-3-multimodal","title":"MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models","date":"2024-03-31","arxiv_id":"2404.00511","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mips-at-semeval-2024-task-3-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.00511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00511"}},"official":{"repos":["mips-colt/mer-mce"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recursive-cross-modal-attention-for","slug":"recursive-cross-modal-attention-for","title":"Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition","date":"2024-03-20","arxiv_id":"2403.13659","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recursive-cross-modal-attention-for#ran","syntology_url":"https://syntology.ai/paper/2403.13659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13659"}},"official":{"repos":["praveena2j/rjcma"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-multimodal-transformer-for-dimensional","slug":"joint-multimodal-transformer-for-dimensional","title":"Joint Multimodal Transformer for Emotion Recognition in the Wild","date":"2024-03-15","arxiv_id":"2403.10488","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/joint-multimodal-transformer-for-dimensional#ran","syntology_url":"https://syntology.ai/paper/2403.10488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10488"}},"official":{"repos":["PoloWlg/Joint-Multimodal-Transformer-6th-ABAW"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/curriculum-learning-meets-directed-acyclic","slug":"curriculum-learning-meets-directed-acyclic","title":"Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition","date":"2024-02-27","arxiv_id":"2402.17269","repositories_listed":1,"syntology":null},{"url":"/paper/modality-collaborative-transformer-with","slug":"modality-collaborative-transformer-with","title":"Modality-Collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition","date":"2023-12-26","arxiv_id":"2312.15848","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-4v-with-emotion-a-zero-shot-benchmark-for","slug":"gpt-4v-with-emotion-a-zero-shot-benchmark-for","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","date":"2023-12-07","arxiv_id":"2312.04293","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4v-with-emotion-a-zero-shot-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2312.04293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04293"}},"official":{"repos":["zeroqiaoba/gpt4v-emotion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emotions-a-large-scale-dataset-for-emotion","slug":"emotions-a-large-scale-dataset-for-emotion","title":"Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline","date":"2023-11-29","arxiv_id":"2311.17335","repositories_listed":1,"syntology":null},{"url":"/paper/joyful-joint-modality-fusion-and-graph","slug":"joyful-joint-modality-fusion-and-graph","title":"Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition","date":"2023-11-18","arxiv_id":"2311.11009","repositories_listed":1,"syntology":null},{"url":"/paper/conversation-understanding-using-relational","slug":"conversation-understanding-using-relational","title":"Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction","date":"2023-11-08","arxiv_id":"2311.04507","repositories_listed":1,"syntology":null},{"url":"/paper/a-transformer-based-model-with-self","slug":"a-transformer-based-model-with-self","title":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","date":"2023-10-31","arxiv_id":"2310.20494","repositories_listed":1,"syntology":null},{"url":"/paper/hypercomplex-multimodal-emotion-recognition","slug":"hypercomplex-multimodal-emotion-recognition","title":"Hypercomplex Multimodal Emotion Recognition from EEG and Peripheral Physiological Signals","date":"2023-10-11","arxiv_id":"2310.07648","repositories_listed":1,"syntology":null},{"url":"/paper/learning-noise-robust-joint-representation","slug":"learning-noise-robust-joint-representation","title":"Learning Noise-Robust Joint Representation for Multimodal Emotion Recognition under Incomplete Data Scenarios","date":"2023-09-21","arxiv_id":"2311.16114","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-noise-robust-joint-representation#ran","syntology_url":"https://syntology.ai/paper/2311.16114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16114"}},"official":{"repos":["wooyoohl/noise-robust_mer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cfn-esa-a-cross-modal-fusion-network-with","slug":"cfn-esa-a-cross-modal-fusion-network-with","title":"CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition","date":"2023-07-28","arxiv_id":"2307.15432","repositories_listed":1,"syntology":null},{"url":"/paper/a-facial-expression-aware-multimodal-multi","slug":"a-facial-expression-aware-multimodal-multi","title":"A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations","date":"2023-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/decoupled-multimodal-distilling-for-emotion","slug":"decoupled-multimodal-distilling-for-emotion","title":"Decoupled Multimodal Distilling for Emotion Recognition","date":"2023-03-24","arxiv_id":"2303.13802","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/decoupled-multimodal-distilling-for-emotion#ran","syntology_url":"https://syntology.ai/paper/2303.13802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13802"}},"official":{"repos":["mdswyz/dmd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/multimodal-information-bottleneck-learning","slug":"multimodal-information-bottleneck-learning","title":"Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations","date":"2022-10-31","arxiv_id":"2210.17444","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multimodal-information-bottleneck-learning#ran","syntology_url":"https://syntology.ai/paper/2210.17444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.17444"}},"official":{"repos":["tmacmai/multimodal-information-bottleneck"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploiting-modality-invariant-feature-for","slug":"exploiting-modality-invariant-feature-for","title":"Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities","date":"2022-10-27","arxiv_id":"2210.15359","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploiting-modality-invariant-feature-for#ran","syntology_url":"https://syntology.ai/paper/2210.15359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15359"}},"official":{"repos":["zhuoyulang/if-mmin"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fv2es-a-fully-end2end-multimodal-system-for","slug":"fv2es-a-fully-end2end-multimodal-system-for","title":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","date":"2022-09-21","arxiv_id":"2209.10170","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-multimodal-emotion-recognition","slug":"interpretable-multimodal-emotion-recognition","title":"Interpretable Multimodal Emotion Recognition using Hybrid Fusion of Speech and Image Data","date":"2022-08-25","arxiv_id":"2208.11868","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-fusion-based-interpretable-multimodal","slug":"hybrid-fusion-based-interpretable-multimodal","title":"VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition","date":"2022-08-24","arxiv_id":"2208.11450","repositories_listed":1,"syntology":null},{"url":"/paper/ga2mif-graph-and-attention-based-two-stage","slug":"ga2mif-graph-and-attention-based-two-stage","title":"GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection","date":"2022-07-25","arxiv_id":"2207.11900","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-with-modality","slug":"multimodal-emotion-recognition-with-modality","title":"Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Loss","date":"2022-07-23","arxiv_id":"2207.11482","repositories_listed":1,"syntology":null},{"url":"/paper/multi-level-fusion-of-wav2vec-2-0-and-bert","slug":"multi-level-fusion-of-wav2vec-2-0-and-bert","title":"Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition","date":"2022-07-11","arxiv_id":"2207.04697","repositories_listed":1,"syntology":null},{"url":"/paper/graphcfc-a-directed-graph-based-cross-modal","slug":"graphcfc-a-directed-graph-based-cross-modal","title":"GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition","date":"2022-07-06","arxiv_id":"2207.12261","repositories_listed":1,"syntology":null},{"url":"/paper/mmer-multimodal-multi-task-learning-for","slug":"mmer-multimodal-multi-task-learning-for","title":"MMER: Multimodal Multi-task Learning for Speech Emotion Recognition","date":"2022-03-31","arxiv_id":"2203.16794","repositories_listed":1,"syntology":null},{"url":"/paper/a-joint-cross-attention-model-for-audio","slug":"a-joint-cross-attention-model-for-audio","title":"A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition","date":"2022-03-28","arxiv_id":"2203.14779","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-emotion-from-music-videos","slug":"predicting-emotion-from-music-videos","title":"Predicting emotion from music videos: exploring the relative contribution of visual and auditory information to affective responses","date":"2022-02-19","arxiv_id":"2202.10453","repositories_listed":1,"syntology":null},{"url":"/paper/group-gated-fusion-on-attention-based","slug":"group-gated-fusion-on-attention-based","title":"Group Gated Fusion on Attention-based Bidirectional Alignment for Multimodal Emotion Recognition","date":"2022-01-17","arxiv_id":"2201.06309","repositories_listed":1,"syntology":null},{"url":"/paper/a-proposal-for-multimodal-emotion-recognition","slug":"a-proposal-for-multimodal-emotion-recognition","title":"A proposal for Multimodal Emotion Recognition using aural transformers and Action Units on RAVDESS dataset","date":"2021-12-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/shapes-of-emotions-multimodal-emotion","slug":"shapes-of-emotions-multimodal-emotion","title":"Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts","date":"2021-12-03","arxiv_id":"2112.01938","repositories_listed":1,"syntology":null},{"url":"/paper/cross-attentional-audio-visual-fusion-for-1","slug":"cross-attentional-audio-visual-fusion-for-1","title":"Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition","date":"2021-11-09","arxiv_id":"2111.05222","repositories_listed":1,"syntology":null},{"url":"/paper/a-cross-modal-fusion-network-based-on-self","slug":"a-cross-modal-fusion-network-based-on-self","title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","date":"2021-11-03","arxiv_id":"2111.02172","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-with-high","slug":"multimodal-emotion-recognition-with-high","title":"Multimodal Emotion Recognition with High-level Speech and Text Features","date":"2021-09-29","arxiv_id":"2111.10202","repositories_listed":1,"syntology":null},{"url":"/paper/combining-deep-and-unsupervised-features-for","slug":"combining-deep-and-unsupervised-features-for","title":"Combining deep and unsupervised features for multilingual speech emotion recognition","date":"2021-01-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/msaf-multimodal-split-attention-fusion","slug":"msaf-multimodal-split-attention-fusion","title":"MSAF: Multimodal Split Attention Fusion","date":"2020-12-13","arxiv_id":"2012.07175","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-with","slug":"multimodal-emotion-recognition-with","title":"Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature Fusion","date":"2020-10-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modality-transferable-emotion-embeddings-for","slug":"modality-transferable-emotion-embeddings-for","title":"Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition","date":"2020-09-21","arxiv_id":"2009.09629","repositories_listed":1,"syntology":null},{"url":"/paper/jointly-fine-tuning-bert-like-self-supervised-1","slug":"jointly-fine-tuning-bert-like-self-supervised-1","title":"Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion Recognition","date":"2020-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multilogue-net-a-context-aware-rnn-for-multi","slug":"multilogue-net-a-context-aware-rnn-for-multi","title":"Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation","date":"2020-02-19","arxiv_id":"2002.08267","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multilogue-net-a-context-aware-rnn-for-multi#ran","syntology_url":"https://syntology.ai/paper/2002.08267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08267"}},"official":{"repos":["amanshenoy/multilogue-net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/attentive-modality-hopping-mechanism-for","slug":"attentive-modality-hopping-mechanism-for","title":"Attentive Modality Hopping Mechanism for Speech Emotion Recognition","date":"2019-11-29","arxiv_id":"1912.00846","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-behavioral-markers-exploring","slug":"multimodal-behavioral-markers-exploring","title":"Multimodal Behavioral Markers Exploring Suicidal Intent in Social Media Videos","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-alignment-for-multimodal-emotion","slug":"learning-alignment-for-multimodal-emotion","title":"Learning Alignment for Multimodal Emotion Recognition from Speech","date":"2019-09-06","arxiv_id":"1909.05645","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-emotion-recognition-using-deep","slug":"multimodal-emotion-recognition-using-deep","title":"Multimodal Emotion Recognition Using Deep Canonical Correlation Analysis","date":"2019-08-13","arxiv_id":"1908.05349","repositories_listed":1,"syntology":null},{"url":"/paper/icon-interactive-conversational-memory","slug":"icon-interactive-conversational-memory","title":"ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/music-mood-detection-based-on-audio-and","slug":"music-mood-detection-based-on-audio-and","title":"Music Mood Detection Based On Audio And Lyrics With Deep Neural Net","date":"2018-09-19","arxiv_id":"1809.07276","repositories_listed":1,"syntology":null},{"url":"/paper/investigation-of-multimodal-features","slug":"investigation-of-multimodal-features","title":"Investigation of Multimodal Features, Classifiers and Fusion Methods for Emotion Recognition","date":"2018-09-13","arxiv_id":"1809.06225","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-sentiment-analysis-using","slug":"multimodal-sentiment-analysis-using","title":"Multimodal Sentiment Analysis using Hierarchical Fusion with Context Modeling","date":"2018-06-16","arxiv_id":"1806.06228","repositories_listed":1,"syntology":null},{"url":null,"slug":"a-robust-incomplete-multimodal-low-rank","title":"A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition","date":"2025-07-15","arxiv_id":"2507.11202","repositories_listed":0,"syntology":null},{"url":null,"slug":"gsdnet-revisiting-incomplete-multimodal","title":"GSDNet: Revisiting Incomplete Multimodal-Diffusion from Graph Spectrum Perspective for Conversation Emotion Recognition","date":"2025-06-14","arxiv_id":"2506.12325","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-mixture-of-low-rank-experts-for","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","date":"2025-05-20","arxiv_id":"2505.14143","repositories_listed":0,"syntology":null},{"url":null,"slug":"psycounassist-a-full-cycle-ai-powered","title":"PsyCounAssist: A Full-Cycle AI-Powered Psychological Counseling Assistant System","date":"2025-04-23","arxiv_id":"2504.16573","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-label-potential-for-enhanced","title":"Leveraging Label Potential for Enhanced Multimodal Emotion Recognition","date":"2025-04-07","arxiv_id":"2504.05158","repositories_listed":0,"syntology":null},{"url":null,"slug":"bemerc-behavior-aware-mllm-based-framework","title":"BeMERC: Behavior-Aware MLLM-based Framework for Multimodal Emotion Recognition in Conversation","date":"2025-03-31","arxiv_id":"2503.23990","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimodal-driven-distillation-in-multimodal","title":"Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion","date":"2025-03-31","arxiv_id":"2503.23721","repositories_listed":0,"syntology":null},{"url":null,"slug":"gatedxlstm-a-multimodal-affective-computing","title":"GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations","date":"2025-03-26","arxiv_id":"2503.20919","repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-weak-complementary-relationships-for","title":"United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space","date":"2025-03-15","arxiv_id":"2503.12261","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-emotion-recognition-and-sentiment","title":"Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts","date":"2025-03-09","arxiv_id":"2503.06805","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-approach-to-for-multimodal-emotion","title":"A Novel Approach to for Multimodal Emotion Recognition : Multimodal semantic information fusion","date":"2025-02-12","arxiv_id":"2502.08573","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-context-fusion-and-adaptive-graph","title":"Cross-modal Context Fusion and Adaptive Graph Convolutional Network for Multimodal Conversational Emotion Recognition","date":"2025-01-25","arxiv_id":"2501.15063","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotech-a-multi-modal-speech-emotion","title":"EmoTech: A Multi-modal Speech Emotion Recognition Using Multi-source Low-level Information with Hybrid Recurrent Network","date":"2025-01-22","arxiv_id":"2501.12674","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-supervised-pre-training-for-multimodal","title":"LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations","date":"2025-01-20","arxiv_id":"2501.11468","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvp-multimodal-emotion-recognition-based-on","title":"MVP: Multimodal Emotion Recognition based on Video and Physiological Signals","date":"2025-01-06","arxiv_id":"2501.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"emoe-modality-specific-enhanced-dynamic","title":"EMOE: Modality-Specific Enhanced Dynamic Emotion Experts","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multimodal-emotion-recognition","title":"Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment","date":"2024-12-30","arxiv_id":"2412.20821","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-emotion-recognition-system","title":"A Multimodal Emotion Recognition System: Integrating Facial Expressions, Body Movement, Speech, and Spoken Language","date":"2024-12-23","arxiv_id":"2412.17907","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-graph-neural-ordinary-differential","title":"Dynamic Graph Neural ODE Network for Multi-modal Emotion Recognition in Conversation","date":"2024-12-04","arxiv_id":"2412.02935","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmath-cross-modality-augmented-transformer","title":"CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation","date":"2024-11-15","arxiv_id":"2411.10060","repositories_listed":0,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/multimodal-emotion-recognition-on-meld","since_archive":"/sota/multimodal-emotion-recognition-on-meld#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multimodal-emotion-recognition-on-iemocap","since_archive":"/sota/multimodal-emotion-recognition-on-iemocap#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/task/multimodal-emotion-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/multimodal-emotion-recognition/papers/2","json":"/task/multimodal-emotion-recognition/papers/2.json","rows":80},{"order":"ran","page":1,"of":1,"url":"/task/multimodal-emotion-recognition/papers/ran/1","json":"/task/multimodal-emotion-recognition/papers/ran/1.json","rows":14}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6b21562fbc33e9674e0c15ebf6c97973d7ab0dc19f0c56e572a2911db9c0a2e3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}