{"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/emotion-recognition","name":"Emotion Recognition","slug":"emotion-recognition","description_markdown":"**Emotion Recognition** is an important area of research to enable effective human-computer interaction. Human emotions can be detected using speech signal, facial expressions, body language, and electroencephalography (EEG). <span class=\"description-source\">Source: [Using Deep Autoencoders for Facial Expression Recognition ](https://arxiv.org/abs/1801.08329)</span>","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2041,"papers_with_code":614,"benchmarks":9,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"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":52,"subtasks":12,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/emotion-recognition-on-emomusic","slug":"emotion-recognition-on-emomusic","dataset":"Emomusic","dataset_url":"/dataset/emomusic","rows_in_archive":5,"metrics":["EmoA","EmoV"],"first_row_in_archive_order":{"model":"M2D-CLAP","paper_title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","paper_url":"/paper/m2d2-exploring-general-purpose-audio-language","paper_date":"2025-03-28","arxiv_id":"2503.22104","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-ravdess","slug":"emotion-recognition-on-ravdess","dataset":"RAVDESS","dataset_url":"/dataset/ravdess","rows_in_archive":5,"metrics":["Accuracy","WAR"],"first_row_in_archive_order":{"model":"LogisticRegression on posteriors of xlsr-Wav2Vec2.0&bi-LSTM+Attention","paper_title":"A proposal for Multimodal Emotion Recognition using aural transformers and Action Units on RAVDESS dataset","paper_url":"/paper/a-proposal-for-multimodal-emotion-recognition","paper_date":"2021-12-30","arxiv_id":null,"code_links":[{"title":"cristinalunaj/MMEmotionRecognition","url":"https://github.com/cristinalunaj/MMEmotionRecognition"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-emotic","slug":"emotion-recognition-on-emotic","dataset":"EMOTIC","dataset_url":"/dataset/emotic","rows_in_archive":2,"metrics":["Top-3 Accuracy (%)"],"first_row_in_archive_order":{"model":"CAGE","paper_title":"CAGE: Circumplex Affect Guided Expression Inference","paper_url":"/paper/cage-circumplex-affect-guided-expression","paper_date":"2024-04-23","arxiv_id":"2404.14975","code_links":[{"title":"wagner-niklas/cage_expression_inference","url":"https://github.com/wagner-niklas/cage_expression_inference"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-fer2013-1","slug":"emotion-recognition-on-fer2013-1","dataset":"FER2013","dataset_url":"/dataset/fer2013","rows_in_archive":1,"metrics":["5-class test accuracy"],"first_row_in_archive_order":{"model":"VGG based","paper_title":"IdentiFace : A VGG Based Multimodal Facial Biometric System","paper_url":"/paper/identiface-a-vgg-based-multimodal-facial","paper_date":"2024-01-02","arxiv_id":"2401.01227","code_links":[{"title":"MahmoudRabea13/IdentiFace","url":"https://github.com/MahmoudRabea13/IdentiFace"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-khlipkhunph","slug":"emotion-recognition-on-khlipkhunph","dataset":"คลิปคุณพ่อให้ลูกสาวยืมโทรศัพท์และความสนุกสนาน","dataset_url":null,"rows_in_archive":1,"metrics":["1'\""],"first_row_in_archive_order":{"model":"CNN","paper_title":"A Spontaneous Driver Emotion Facial Expression (DEFE) Dataset for Intelligent Vehicles","paper_url":"/paper/a-spontaneous-driver-emotion-facial","paper_date":"2020-04-26","arxiv_id":"2005.08626","code_links":[],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-masac-erc","slug":"emotion-recognition-on-masac-erc","dataset":"MaSaC_ERC","dataset_url":"/dataset/masac-erc","rows_in_archive":1,"metrics":["F1-score (Weighted)"],"first_row_in_archive_order":{"model":"MaSaC-ERC-Z","paper_title":"FeedForward at SemEval-2024 Task 10: Trigger and sentext-height enriched emotion analysis in multi-party conversations","paper_url":"/paper/feedforward-at-semeval-2024-task-10-trigger","paper_date":"2024-06-20","arxiv_id":null,"code_links":[{"title":"Zuhashaik/Multi-Party-DialoZ","url":"https://github.com/Zuhashaik/Multi-Party-DialoZ"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-mped","slug":"emotion-recognition-on-mped","dataset":"MPED","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BiHDM","paper_title":"A Novel Bi-hemispheric Discrepancy Model for EEG Emotion Recognition","paper_url":"/paper/a-novel-bi-hemispheric-discrepancy-model-for-1","paper_date":"2019-05-11","arxiv_id":"1906.01704","code_links":[],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-msp-podcast","slug":"emotion-recognition-on-msp-podcast","dataset":"MSP-Podcast","dataset_url":"/dataset/msp-podcast","rows_in_archive":1,"metrics":["Concordance correlation coefficient (CCC)"],"first_row_in_archive_order":{"model":"w2v2-L-robust-12","paper_title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","paper_url":"/paper/dawn-of-the-transformer-era-in-speech-emotion","paper_date":"2022-03-14","arxiv_id":"2203.07378","code_links":[{"title":"audeering/w2v2-how-to","url":"https://github.com/audeering/w2v2-how-to"}],"syntology":null}},{"leaderboard":"/sota/emotion-recognition-on-seed","slug":"emotion-recognition-on-seed","dataset":"SEED","dataset_url":"/dataset/seed-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"4D-aNN","paper_title":"4D Attention-based Neural Network for EEG Emotion Recognition","paper_url":"/paper/4d-attention-based-neural-network-for-eeg","paper_date":"2021-01-14","arxiv_id":"2101.05484","code_links":[],"syntology":null}},{"leaderboard":null,"slug":"emotion-recognition-on-mafw","dataset":"MAFW","dataset_url":"/dataset/mafw","rows_in_archive":0,"metrics":["Unweighted average recall"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/hateful-memes","name":"Hateful Memes","full_name":"Hateful Memes","num_papers_in_archive":177},{"url":"/dataset/fer2013","name":"FER2013","full_name":"Facial Expression Recognition 2013 Dataset","num_papers_in_archive":168},{"url":"/dataset/aff-wild2","name":"Aff-Wild2","full_name":"","num_papers_in_archive":142},{"url":"/dataset/aff-wild","name":"Aff-Wild","full_name":"","num_papers_in_archive":125},{"url":"/dataset/emotion","name":"CARER","full_name":"Contextualized Affect Representations for Emotion Recognition","num_papers_in_archive":123},{"url":"/dataset/seed-1","name":"SEED","full_name":"SJTU Emotion EEG Dataset","num_papers_in_archive":119},{"url":"/dataset/msp-improv","name":"MSP-IMPROV","full_name":"MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception","num_papers_in_archive":70},{"url":"/dataset/isear","name":"ISEAR","full_name":"International Survey on Emotion Antecedents and Reactions","num_papers_in_archive":55},{"url":"/dataset/hateful-memes-challenge","name":"Hateful Memes Challenge","full_name":"","num_papers_in_archive":48},{"url":"/dataset/emotionlines","name":"EmotionLines","full_name":"EmotionLines","num_papers_in_archive":44},{"url":"/dataset/expw","name":"ExpW","full_name":"Expression in-the-Wild","num_papers_in_archive":41},{"url":"/dataset/emotic","name":"EMOTIC","full_name":"EMOTIons in Context","num_papers_in_archive":38},{"url":"/dataset/emobank","name":"EmoBank","full_name":"","num_papers_in_archive":32},{"url":"/dataset/mafw","name":"MAFW","full_name":"","num_papers_in_archive":31},{"url":"/dataset/ravdess","name":"RAVDESS","full_name":"Ryerson Audio-Visual Database of Emotional Speech and Song","num_papers_in_archive":27},{"url":"/dataset/emopia","name":"EMOPIA","full_name":"A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation","num_papers_in_archive":23},{"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/video2gif","name":"Video2GIF","full_name":"","num_papers_in_archive":11},{"url":"/dataset/emowoz-1","name":"EmoWOZ","full_name":"","num_papers_in_archive":10},{"url":"/dataset/mustard-1","name":"MUStARD++","full_name":"","num_papers_in_archive":10},{"url":"/dataset/k-emocon","name":"K-EmoCon","full_name":"","num_papers_in_archive":9},{"url":"/dataset/msp-podcast","name":"MSP-Podcast","full_name":"A large naturalistic speech emotional dataset","num_papers_in_archive":9},{"url":"/dataset/send","name":"SEND","full_name":"Stanford Emotional Narratives Dataset","num_papers_in_archive":8},{"url":"/dataset/armanemo","name":"ArmanEmo","full_name":"","num_papers_in_archive":6},{"url":"/dataset/ulm-tsst","name":"Ulm-TSST","full_name":"Ulm-Trier Social Stress Dataset","num_papers_in_archive":6},{"url":"/dataset/emotional-dialogue-acts","name":"Emotional Dialogue Acts","full_name":"","num_papers_in_archive":3},{"url":"/dataset/findingemo","name":"FindingEmo","full_name":"","num_papers_in_archive":3},{"url":"/dataset/hume-vb","name":"HUME-VB","full_name":"The Hume Vocal Bursts Dataset","num_papers_in_archive":3},{"url":"/dataset/memeify","name":"Memeify","full_name":"","num_papers_in_archive":3},{"url":"/dataset/sewa-db","name":"SEWA DB","full_name":"","num_papers_in_archive":3},{"url":"/dataset/dusha","name":"Dusha","full_name":"Dusha Crowd, Dusha Podcast","num_papers_in_archive":2},{"url":"/dataset/emomusic","name":"Emomusic","full_name":"Emotion in Music Database","num_papers_in_archive":2},{"url":"/dataset/emopars","name":"EmoPars","full_name":"","num_papers_in_archive":2},{"url":"/dataset/masac-erc","name":"MaSaC_ERC","full_name":"","num_papers_in_archive":2},{"url":"/dataset/nemo-1","name":"nEMO","full_name":"","num_papers_in_archive":2},{"url":"/dataset/sentimental-liar","name":"Sentimental LIAR","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/banglaemotion","name":"BanglaEmotion","full_name":"BanglaEmotion: A Benchmark Dataset for Bangla Textual Emotion Analysis","num_papers_in_archive":1},{"url":"/dataset/berst","name":"BERSt","full_name":"Basic Emotion Random phrase Shouts","num_papers_in_archive":1},{"url":"/dataset/emofilm","name":"EmoFilm","full_name":"Emotional speech from Films","num_papers_in_archive":1},{"url":"/dataset/event-focused-emotion-corpora-for-german-and","name":"Event-focused Emotion Corpora for German and English","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mfa","name":"MFA","full_name":"Many Faces of Anger","num_papers_in_archive":1},{"url":"/dataset/modified-shemo","name":"modified_shemo","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ren-20k-dataset","name":"REN-20k Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vesus","name":"VESUS","full_name":"Varied Emotion in Syntactically Uniform Speech","num_papers_in_archive":1},{"url":"/dataset/vnemos","name":"VNEMOS","full_name":"Vietnamese Speech Emotion Dataset","num_papers_in_archive":1},{"url":"/dataset/werewolf-xl","name":"Werewolf-XL","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ym2413-mdb","name":"YM2413-MDB","full_name":"","num_papers_in_archive":1},{"url":"/dataset/affective-text","name":"Affective Text","full_name":"","num_papers_in_archive":0},{"url":"/dataset/human-faces-with-mixed-race-various-emotions","name":"Human faces with mixed-race & various emotions","full_name":"","num_papers_in_archive":0},{"url":"/dataset/l-svd","name":"L-SVD","full_name":"Large-Scale Selfie Video Dataset (L-SVD): A Benchmark for Emotion Recognition","num_papers_in_archive":0},{"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/a-vb-culture","name":"A-VB Culture"},{"url":"/task/a-vb-high","name":"A-VB High"},{"url":"/task/a-vb-two","name":"A-VB Two"},{"url":"/task/eeg-emotion-recognition","name":"EEG Emotion Recognition"},{"url":"/task/emotion-cause-extraction","name":"Emotion Cause Extraction"},{"url":"/task/emotion-cause-pair-extraction","name":"Emotion-Cause Pair Extraction"},{"url":"/task/emotion-recognition-in-context","name":"Emotion Recognition in Context"},{"url":"/task/emotion-recognition-in-conversation","name":"Emotion Recognition in Conversation"},{"url":"/task/facial-emotion-recognition","name":"Facial Emotion Recognition"},{"url":"/task/multimodal-emotion-recognition","name":"Multimodal Emotion Recognition"},{"url":"/task/speech-emotion-recognition","name":"Speech Emotion Recognition"},{"url":"/task/video-emotion-recognition","name":"Video Emotion Recognition"}],"parent_tasks":[],"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":21,"rows_per_page":100,"shown":100,"of":2041,"of_with_code":614,"tagged_in_all":2041,"counts":{"archive_papers_tagged":2041,"with_a_code_link":614,"where_syntology_ran_a_sample":69,"not_listed_spam_title":0,"listed":2041,"listed_where_code_ran":69,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":57,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":57,"listed_every_run_a_failure_of_syntologys_instrument":12,"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/meld-a-multimodal-multi-party-dataset-for","slug":"meld-a-multimodal-multi-party-dataset-for","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","date":"2018-10-05","arxiv_id":"1810.02508","repositories_listed":8,"syntology":null},{"url":"/paper/eeg-based-emotion-recognition-using","slug":"eeg-based-emotion-recognition-using","title":"EEG-Based Emotion Recognition Using Regularized Graph Neural Networks","date":"2019-07-18","arxiv_id":"1907.07835","repositories_listed":5,"syntology":null},{"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/words-can-shift-dynamically-adjusting-word","slug":"words-can-shift-dynamically-adjusting-word","title":"Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors","date":"2018-11-23","arxiv_id":"1811.09362","repositories_listed":5,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"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 0 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","sample_list":"/paper/words-can-shift-dynamically-adjusting-word#ran","syntology_url":"https://syntology.ai/paper/1811.09362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09362"}},"official":{"repos":["victorywys/RAVEN"],"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/dialogxl-all-in-one-xlnet-for-multi-party","slug":"dialogxl-all-in-one-xlnet-for-multi-party","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","date":"2020-12-16","arxiv_id":"2012.08695","repositories_listed":4,"syntology":null},{"url":"/paper/emotion-cause-pair-extraction-a-new-task-to","slug":"emotion-cause-pair-extraction-a-new-task-to","title":"Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts","date":"2019-06-04","arxiv_id":"1906.01267","repositories_listed":4,"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/funaudiollm-voice-understanding-and","slug":"funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","arxiv_id":"2407.04051","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funaudiollm-voice-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2407.04051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04051"}},"official":{"repos":["FunAudioLLM/SenseVoice","funaudiollm/cosyvoice"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/speech-emotion-diarization-which-emotion","slug":"speech-emotion-diarization-which-emotion","title":"Speech Emotion Diarization: Which Emotion Appears When?","date":"2023-06-22","arxiv_id":"2306.12991","repositories_listed":3,"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/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ssast-self-supervised-audio-spectrogram#ran","syntology_url":"https://syntology.ai/paper/2110.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09784"}},"official":{"repos":["YuanGongND/ssast"],"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":["listed","official"]}}},{"url":"/paper/ethics-sheet-for-automatic-emotion","slug":"ethics-sheet-for-automatic-emotion","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","date":"2021-09-17","arxiv_id":"2109.08256","repositories_listed":3,"syntology":null},{"url":"/paper/ethics-sheets-for-ai-tasks","slug":"ethics-sheets-for-ai-tasks","title":"Ethics Sheets for AI Tasks","date":"2021-07-02","arxiv_id":"2107.01183","repositories_listed":3,"syntology":null},{"url":"/paper/compact-graph-architecture-for-speech-emotion","slug":"compact-graph-architecture-for-speech-emotion","title":"Compact Graph Architecture for Speech Emotion Recognition","date":"2020-08-05","arxiv_id":"2008.02063","repositories_listed":3,"syntology":null},{"url":"/paper/context-based-emotion-recognition-using","slug":"context-based-emotion-recognition-using","title":"Context Based Emotion Recognition using EMOTIC Dataset","date":"2020-03-30","arxiv_id":"2003.13401","repositories_listed":3,"syntology":null},{"url":"/paper/fau-facial-expressions-valence-and-arousal-a","slug":"fau-facial-expressions-valence-and-arousal-a","title":"Multitask Emotion Recognition with Incomplete Labels","date":"2020-02-10","arxiv_id":"2002.03557","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fau-facial-expressions-valence-and-arousal-a#ran","syntology_url":"https://syntology.ai/paper/2002.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03557"}},"official":{"repos":["wtomin/Multitask-Emotion-Recognition-with-Incomplete-Labels"],"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":["listed","official"]}}},{"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/efficient-low-rank-multimodal-fusion-with","slug":"efficient-low-rank-multimodal-fusion-with","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","date":"2018-05-31","arxiv_id":"1806.00064","repositories_listed":3,"syntology":null},{"url":"/paper/dexpression-deep-convolutional-neural-network","slug":"dexpression-deep-convolutional-neural-network","title":"DeXpression: Deep Convolutional Neural Network for Expression Recognition","date":"2015-09-17","arxiv_id":"1509.05371","repositories_listed":3,"syntology":null},{"url":"/paper/training-deep-neural-networks-on-noisy-labels","slug":"training-deep-neural-networks-on-noisy-labels","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","date":"2014-12-20","arxiv_id":"1412.6596","repositories_listed":3,"syntology":null},{"url":"/paper/exploring-remote-physiological-signal","slug":"exploring-remote-physiological-signal","title":"Exploring Remote Physiological Signal Measurement under Dynamic Lighting Conditions at Night: Dataset, Experiment, and Analysis","date":"2025-07-06","arxiv_id":"2507.04306","repositories_listed":2,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"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/why-we-feel-breaking-boundaries-in-emotional","slug":"why-we-feel-breaking-boundaries-in-emotional","title":"Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models","date":"2025-04-10","arxiv_id":"2504.07521","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/why-we-feel-breaking-boundaries-in-emotional#ran","syntology_url":"https://syntology.ai/paper/2504.07521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07521"}},"official":{"repos":["lum1104/eibench"],"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/m2d2-exploring-general-purpose-audio-language","slug":"m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/sample-correlation-for-fingerprinting-deep","slug":"sample-correlation-for-fingerprinting-deep","title":"Sample Correlation for Fingerprinting Deep Face Recognition","date":"2024-12-30","arxiv_id":"2412.20768","repositories_listed":2,"syntology":null},{"url":"/paper/prototypical-calibrating-ambiguous-samples","slug":"prototypical-calibrating-ambiguous-samples","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","date":"2024-12-19","arxiv_id":"2412.14719","repositories_listed":2,"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/libeer-a-comprehensive-benchmark-and","slug":"libeer-a-comprehensive-benchmark-and","title":"LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-based Emotion Recognition","date":"2024-10-13","arxiv_id":"2410.09767","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-emotion-bias-in-music-via-frechet","slug":"rethinking-emotion-bias-in-music-via-frechet","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","date":"2024-09-23","arxiv_id":"2409.15545","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/unveiling-hidden-factors-explainable-ai-for","slug":"unveiling-hidden-factors-explainable-ai-for","title":"Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition","date":"2024-06-01","arxiv_id":"2406.01624","repositories_listed":2,"syntology":null},{"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/gpt-as-psychologist-preliminary-evaluations","slug":"gpt-as-psychologist-preliminary-evaluations","title":"GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing","date":"2024-03-09","arxiv_id":"2403.05916","repositories_listed":2,"syntology":null},{"url":"/paper/angry-men-sad-women-large-language-models","slug":"angry-men-sad-women-large-language-models","title":"Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution","date":"2024-03-05","arxiv_id":"2403.03121","repositories_listed":2,"syntology":null},{"url":"/paper/gaussian-adaptive-attention-is-all-you-need","slug":"gaussian-adaptive-attention-is-all-you-need","title":"Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities","date":"2024-01-20","arxiv_id":"2401.11143","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 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) · 0 unverified","sample_list":"/paper/gaussian-adaptive-attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2401.11143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11143"}},"official":{"repos":["gioannides/gaussian-adaptive-attention"],"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/emotion2vec-self-supervised-pre-training-for","slug":"emotion2vec-self-supervised-pre-training-for","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","date":"2023-12-23","arxiv_id":"2312.15185","repositories_listed":2,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":8,"n_pointer_only":9,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emotion2vec-self-supervised-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2312.15185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15185"}},"official":{"repos":["ddlBoJack/emotion2vec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/unisa-unified-generative-framework-for-1","slug":"unisa-unified-generative-framework-for-1","title":"UniSA: Unified Generative Framework for Sentiment Analysis","date":"2023-09-04","arxiv_id":"2309.01339","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unisa-unified-generative-framework-for-1#ran","syntology_url":"https://syntology.ai/paper/2309.01339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01339"}},"official":{"repos":["dawn0815/UniSA","dawn0815/saeval-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-evaluations-of-chatgpt-and-emotion","slug":"on-the-evaluations-of-chatgpt-and-emotion","title":"Towards Interpretable Mental Health Analysis with Large Language Models","date":"2023-04-06","arxiv_id":"2304.03347","repositories_listed":2,"syntology":null},{"url":"/paper/a-persian-asr-based-ser-modification-of","slug":"a-persian-asr-based-ser-modification-of","title":"A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora","date":"2022-11-18","arxiv_id":"2211.09956","repositories_listed":2,"syntology":null},{"url":"/paper/classifying-emotions-and-engagement-in-online","slug":"classifying-emotions-and-engagement-in-online","title":"Classifying emotions and engagement in online learning based on a single facial expression recognition neural network","date":"2022-07-04","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/video-based-frame-level-facial-analysis-of","slug":"video-based-frame-level-facial-analysis-of","title":"Video-Based Frame-Level Facial Analysis of Affective Behavior on Mobile Devices Using EfficientNets","date":"2022-06-10","arxiv_id":null,"repositories_listed":2,"syntology":null},{"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/frame-level-prediction-of-facial-expressions","slug":"frame-level-prediction-of-facial-expressions","title":"Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devices","date":"2022-03-25","arxiv_id":"2203.13436","repositories_listed":2,"syntology":null},{"url":"/paper/self-attention-fusion-for-audiovisual-emotion","slug":"self-attention-fusion-for-audiovisual-emotion","title":"Self-attention fusion for audiovisual emotion recognition with incomplete data","date":"2022-01-26","arxiv_id":"2201.11095","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-attention-fusion-for-audiovisual-emotion#ran","syntology_url":"https://syntology.ai/paper/2201.11095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11095"}},"official":{"repos":["katerynaCh/multimodal-emotion-recognition"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/serab-a-multi-lingual-benchmark-for-speech","slug":"serab-a-multi-lingual-benchmark-for-speech","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","date":"2021-10-07","arxiv_id":"2110.03414","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/serab-a-multi-lingual-benchmark-for-speech#ran","syntology_url":"https://syntology.ai/paper/2110.03414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03414"}},"official":{"repos":["neclow/serab"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/federated-distillation-of-natural-language","slug":"federated-distillation-of-natural-language","title":"KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks","date":"2021-10-06","arxiv_id":"2110.02432","repositories_listed":2,"syntology":null},{"url":"/paper/hetemotionnet-two-stream-heterogeneous-graph","slug":"hetemotionnet-two-stream-heterogeneous-graph","title":"HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition","date":"2021-08-07","arxiv_id":"2108.03354","repositories_listed":2,"syntology":null},{"url":"/paper/tracing-back-music-emotion-predictions-to","slug":"tracing-back-music-emotion-predictions-to","title":"Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities","date":"2021-06-14","arxiv_id":"2106.07787","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tracing-back-music-emotion-predictions-to#ran","syntology_url":"https://syntology.ai/paper/2106.07787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07787"}},"official":{"repos":["CPJKU/audioLIME","shreyanc/model_debugging"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dialoguecrn-contextual-reasoning-networks-for","slug":"dialoguecrn-contextual-reasoning-networks-for","title":"DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations","date":"2021-06-03","arxiv_id":"2106.01978","repositories_listed":2,"syntology":null},{"url":"/paper/facial-emotion-recognition-state-of-the-art","slug":"facial-emotion-recognition-state-of-the-art","title":"Facial Emotion Recognition: State of the Art Performance on FER2013","date":"2021-05-08","arxiv_id":"2105.03588","repositories_listed":2,"syntology":null},{"url":"/paper/facial-emotion-recognition-using-transfer","slug":"facial-emotion-recognition-using-transfer","title":"Facial Emotion Recognition Using Transfer Learning in the Deep CNN","date":"2021-04-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/emotion-recognition-from-speech-using-wav2vec","slug":"emotion-recognition-from-speech-using-wav2vec","title":"Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings","date":"2021-04-08","arxiv_id":"2104.03502","repositories_listed":2,"syntology":null},{"url":"/paper/tsception-capturing-temporal-dynamics-and","slug":"tsception-capturing-temporal-dynamics-and","title":"TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition","date":"2021-04-07","arxiv_id":"2104.02935","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/tsception-capturing-temporal-dynamics-and#ran","syntology_url":"https://syntology.ai/paper/2104.02935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02935"}},"official":{"repos":["yi-ding-cs/TSception"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/facial-expression-and-attributes-recognition-1","slug":"facial-expression-and-attributes-recognition-1","title":"Facial expression and attributes recognition based on multi-task learning of lightweight neural networks","date":"2021-03-31","arxiv_id":"2103.17107","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-strategies-and-datasets-for","slug":"pre-training-strategies-and-datasets-for","title":"Pre-training strategies and datasets for facial representation learning","date":"2021-03-30","arxiv_id":"2103.16554","repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-neural-network-hyperparameters","slug":"convolutional-neural-network-hyperparameters","title":"Convolutional Neural Network Hyperparameters optimization for Facial Emotion Recognition","date":"2021-03-25","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/morphset-augmenting-categorical-emotion","slug":"morphset-augmenting-categorical-emotion","title":"Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing","date":"2021-03-04","arxiv_id":"2103.02854","repositories_listed":2,"syntology":null},{"url":"/paper/seen-and-unseen-emotional-style-transfer-for","slug":"seen-and-unseen-emotional-style-transfer-for","title":"Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset","date":"2020-10-28","arxiv_id":"2010.14794","repositories_listed":2,"syntology":null},{"url":"/paper/sentimental-liar-extended-corpus-and-deep","slug":"sentimental-liar-extended-corpus-and-deep","title":"Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification","date":"2020-09-01","arxiv_id":"2009.01047","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/self-supervised-ecg-representation-learning","slug":"self-supervised-ecg-representation-learning","title":"Self-supervised ECG Representation Learning for Emotion Recognition","date":"2020-02-04","arxiv_id":"2002.03898","repositories_listed":2,"syntology":null},{"url":"/paper/emotion-recognition-from-speech","slug":"emotion-recognition-from-speech","title":"Emotion Recognition from Speech","date":"2019-12-22","arxiv_id":"1912.10458","repositories_listed":2,"syntology":null},{"url":"/paper/enriching-existing-conversational-emotion","slug":"enriching-existing-conversational-emotion","title":"EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural Annotators","date":"2019-12-02","arxiv_id":"1912.00819","repositories_listed":2,"syntology":null},{"url":"/paper/modeling-emotion-in-complex-stories-the","slug":"modeling-emotion-in-complex-stories-the","title":"Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset","date":"2019-11-22","arxiv_id":"1912.05008","repositories_listed":2,"syntology":null},{"url":"/paper/mimamo-net-integrating-micro-and-macro-motion","slug":"mimamo-net-integrating-micro-and-macro-motion","title":"MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition","date":"2019-11-21","arxiv_id":"1911.09784","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/mimamo-net-integrating-micro-and-macro-motion#ran","syntology_url":"https://syntology.ai/paper/1911.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09784"}},"official":{"repos":["wtomin/MIMAMO-Net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-learning-for-ecg-based","slug":"self-supervised-learning-for-ecg-based","title":"Self-supervised Learning for ECG-based Emotion Recognition","date":"2019-10-14","arxiv_id":"1910.07497","repositories_listed":2,"syntology":null},{"url":"/paper/student-engagement-detection-using-emotion","slug":"student-engagement-detection-using-emotion","title":"Student Engagement Detection Using Emotion Analysis, Eye Tracking and Head Movement with Machine Learning","date":"2019-09-18","arxiv_id":"1909.12913","repositories_listed":2,"syntology":null},{"url":"/paper/dialoguegcn-a-graph-convolutional-neural","slug":"dialoguegcn-a-graph-convolutional-neural","title":"DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation","date":"2019-08-30","arxiv_id":"1908.11540","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialoguegcn-a-graph-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1908.11540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.11540"}},"official":{"repos":["SenticNet/conv-emotion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/emotionx-ku-bert-max-based-contextual-emotion","slug":"emotionx-ku-bert-max-based-contextual-emotion","title":"EmotionX-KU: BERT-Max based Contextual Emotion Classifier","date":"2019-06-27","arxiv_id":"1906.11565","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-based-emotion-recognition","slug":"deep-learning-based-emotion-recognition","title":"Deep Learning based Emotion Recognition System Using Speech Features and Transcriptions","date":"2019-06-11","arxiv_id":"1906.05681","repositories_listed":2,"syntology":null},{"url":"/paper/recovering-remote-photoplethysmograph-signal","slug":"recovering-remote-photoplethysmograph-signal","title":"Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks","date":"2019-05-07","arxiv_id":"1905.02419","repositories_listed":2,"syntology":null},{"url":"/paper/190410788","slug":"190410788","title":"Speech Emotion Recognition Using Multi-hop Attention Mechanism","date":"2019-04-23","arxiv_id":"1904.10788","repositories_listed":2,"syntology":null},{"url":"/paper/a-compact-embedding-for-facial-expression","slug":"a-compact-embedding-for-facial-expression","title":"A Compact Embedding for Facial Expression Similarity","date":"2018-11-27","arxiv_id":"1811.11283","repositories_listed":2,"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/a-compact-embedding-for-facial-expression#ran","syntology_url":"https://syntology.ai/paper/1811.11283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11283"}},"official":null}},{"url":"/paper/hide-and-seek-a-data-augmentation-technique","slug":"hide-and-seek-a-data-augmentation-technique","title":"Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond","date":"2018-11-06","arxiv_id":"1811.02545","repositories_listed":2,"syntology":null},{"url":"/paper/where-is-your-evidence-improving-fact","slug":"where-is-your-evidence-improving-fact","title":"Where is Your Evidence: Improving Fact-checking by Justification Modeling","date":"2018-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/classifying-and-visualizing-emotions-with","slug":"classifying-and-visualizing-emotions-with","title":"Classifying and Visualizing Emotions with Emotional DAN","date":"2018-10-23","arxiv_id":"1810.10529","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-utterance-level-affect-analysis","slug":"multimodal-utterance-level-affect-analysis","title":"Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features","date":"2018-05-02","arxiv_id":"1805.00625","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/multi-attention-recurrent-network-for-human","slug":"multi-attention-recurrent-network-for-human","title":"Multi-attention Recurrent Network for Human Communication Comprehension","date":"2018-02-03","arxiv_id":"1802.00923","repositories_listed":2,"syntology":null},{"url":"/paper/emotxt-a-toolkit-for-emotion-recognition-from","slug":"emotxt-a-toolkit-for-emotion-recognition-from","title":"EmoTxt: A Toolkit for Emotion Recognition from Text","date":"2017-08-13","arxiv_id":"1708.03892","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/dager-deep-age-gender-and-emotion-recognition","slug":"dager-deep-age-gender-and-emotion-recognition","title":"DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network","date":"2017-02-14","arxiv_id":"1702.04280","repositories_listed":2,"syntology":null},{"url":"/paper/building-a-large-scale-dataset-for-image","slug":"building-a-large-scale-dataset-for-image","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","date":"2016-05-09","arxiv_id":"1605.02677","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 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) · 0 unverified","sample_list":"/paper/building-a-large-scale-dataset-for-image#ran","syntology_url":"https://syntology.ai/paper/1605.02677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02677"}},"official":null}},{"url":"/paper/long-short-distance-graph-neural-networks-and","slug":"long-short-distance-graph-neural-networks-and","title":"Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation","date":"2025-07-21","arxiv_id":"2507.15205","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-parameter-memory-temporary-lora","slug":"dynamic-parameter-memory-temporary-lora","title":"Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation","date":"2025-07-11","arxiv_id":"2507.09076","repositories_listed":1,"syntology":null},{"url":"/paper/infant-cry-emotion-recognition-using-improved","slug":"infant-cry-emotion-recognition-using-improved","title":"Infant Cry Emotion Recognition Using Improved ECAPA-TDNN with Multiscale Feature Fusion and Attention Enhancement","date":"2025-06-23","arxiv_id":"2506.18402","repositories_listed":1,"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/medusa-a-multimodal-deep-fusion-multi-stage","slug":"medusa-a-multimodal-deep-fusion-multi-stage","title":"MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions","date":"2025-06-11","arxiv_id":"2506.09556","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08717","slug":"2506-08717","title":"Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition","date":"2025-06-10","arxiv_id":"2506.08717","repositories_listed":1,"syntology":null},{"url":"/paper/comumdr-code-mixed-multi-modal-multi-domain","slug":"comumdr-code-mixed-multi-modal-multi-domain","title":"CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations","date":"2025-06-10","arxiv_id":"2506.08504","repositories_listed":1,"syntology":null},{"url":"/paper/efficientfer-efficientnetv2-based-deep","slug":"efficientfer-efficientnetv2-based-deep","title":"EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition","date":"2025-06-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/melt-towards-automated-multimodal-emotion","slug":"melt-towards-automated-multimodal-emotion","title":"MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge","date":"2025-05-30","arxiv_id":"2505.24493","repositories_listed":1,"syntology":null},{"url":"/paper/what-about-emotions-guiding-fine-grained","slug":"what-about-emotions-guiding-fine-grained","title":"What About Emotions? Guiding Fine-Grained Emotion Extraction from Mobile App Reviews","date":"2025-05-29","arxiv_id":"2505.23452","repositories_listed":1,"syntology":null},{"url":"/paper/emosphere-ser-enhancing-speech-emotion","slug":"emosphere-ser-enhancing-speech-emotion","title":"EmoSphere-SER: Enhancing Speech Emotion Recognition Through Spherical Representation with Auxiliary Classification","date":"2025-05-26","arxiv_id":"2505.19693","repositories_listed":1,"syntology":null},{"url":"/paper/improving-speech-emotion-recognition-through-1","slug":"improving-speech-emotion-recognition-through-1","title":"Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model","date":"2025-05-26","arxiv_id":"2505.20007","repositories_listed":1,"syntology":null},{"url":"/paper/abhinaya-a-system-for-speech-emotion","slug":"abhinaya-a-system-for-speech-emotion","title":"ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge","date":"2025-05-23","arxiv_id":"2505.18217","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-distillation-of-emotion-knowledge","slug":"contrastive-distillation-of-emotion-knowledge","title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition","date":"2025-05-23","arxiv_id":"2505.18040","repositories_listed":1,"syntology":null}],"syntology_records":21,"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":4,"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/emotion-recognition-on-ravdess","since_archive":"/sota/emotion-recognition-on-ravdess#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/emotion-recognition-on-seed","since_archive":"/sota/emotion-recognition-on-seed#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":69,"papers_where_code_ran_first_page":"/task/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":21,"url":"/task/emotion-recognition/papers/2","json":"/task/emotion-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":21,"url":"/task/emotion-recognition/papers/3","json":"/task/emotion-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":21,"url":"/task/emotion-recognition/papers/4","json":"/task/emotion-recognition/papers/4.json","rows":100},{"order":"archive","page":5,"of":21,"url":"/task/emotion-recognition/papers/5","json":"/task/emotion-recognition/papers/5.json","rows":100},{"order":"archive","page":6,"of":21,"url":"/task/emotion-recognition/papers/6","json":"/task/emotion-recognition/papers/6.json","rows":100},{"order":"archive","page":7,"of":21,"url":"/task/emotion-recognition/papers/7","json":"/task/emotion-recognition/papers/7.json","rows":100},{"order":"archive","page":8,"of":21,"url":"/task/emotion-recognition/papers/8","json":"/task/emotion-recognition/papers/8.json","rows":100},{"order":"archive","page":9,"of":21,"url":"/task/emotion-recognition/papers/9","json":"/task/emotion-recognition/papers/9.json","rows":100},{"order":"archive","page":10,"of":21,"url":"/task/emotion-recognition/papers/10","json":"/task/emotion-recognition/papers/10.json","rows":100},{"order":"archive","page":11,"of":21,"url":"/task/emotion-recognition/papers/11","json":"/task/emotion-recognition/papers/11.json","rows":100},{"order":"archive","page":12,"of":21,"url":"/task/emotion-recognition/papers/12","json":"/task/emotion-recognition/papers/12.json","rows":100},{"order":"archive","page":13,"of":21,"url":"/task/emotion-recognition/papers/13","json":"/task/emotion-recognition/papers/13.json","rows":100},{"order":"archive","page":14,"of":21,"url":"/task/emotion-recognition/papers/14","json":"/task/emotion-recognition/papers/14.json","rows":100},{"order":"archive","page":15,"of":21,"url":"/task/emotion-recognition/papers/15","json":"/task/emotion-recognition/papers/15.json","rows":100},{"order":"archive","page":16,"of":21,"url":"/task/emotion-recognition/papers/16","json":"/task/emotion-recognition/papers/16.json","rows":100},{"order":"archive","page":17,"of":21,"url":"/task/emotion-recognition/papers/17","json":"/task/emotion-recognition/papers/17.json","rows":100},{"order":"archive","page":18,"of":21,"url":"/task/emotion-recognition/papers/18","json":"/task/emotion-recognition/papers/18.json","rows":100},{"order":"archive","page":19,"of":21,"url":"/task/emotion-recognition/papers/19","json":"/task/emotion-recognition/papers/19.json","rows":100},{"order":"archive","page":20,"of":21,"url":"/task/emotion-recognition/papers/20","json":"/task/emotion-recognition/papers/20.json","rows":100},{"order":"archive","page":21,"of":21,"url":"/task/emotion-recognition/papers/21","json":"/task/emotion-recognition/papers/21.json","rows":41},{"order":"ran","page":1,"of":1,"url":"/task/emotion-recognition/papers/ran/1","json":"/task/emotion-recognition/papers/ran/1.json","rows":69}],"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":"821b22f2ff3a85e654014d0f892905b266cb43cfbf73dcf579f067bd7826e3f9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}