{"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/papers/2","list_of":"/task/emotion-recognition","task":"Emotion Recognition","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":21,"rows_per_page":100,"rows":[101,200],"of":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":60,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":60,"listed_every_run_a_failure_of_syntologys_instrument":9,"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"},"first_page":"/task/emotion-recognition","prev":"/task/emotion-recognition","next":"/task/emotion-recognition/papers/3","papers":[{"url":"/paper/feallm-advancing-facial-emotion-analysis-in","slug":"feallm-advancing-facial-emotion-analysis-in","title":"FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning","date":"2025-05-19","arxiv_id":"2505.13419","repositories_listed":1,"syntology":null},{"url":"/paper/jnlp-at-semeval-2025-task-11-cross-lingual","slug":"jnlp-at-semeval-2025-task-11-cross-lingual","title":"JNLP at SemEval-2025 Task 11: Cross-Lingual Multi-Label Emotion Detection Using Generative Models","date":"2025-05-19","arxiv_id":"2505.13244","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-in-eeg-emotion-recognition-state","slug":"evaluation-in-eeg-emotion-recognition-state","title":"Evaluation in EEG Emotion Recognition: State-of-the-Art Review and Unified Framework","date":"2025-05-14","arxiv_id":"2505.18175","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-qwen-training-hybrid-experts-for","slug":"emotion-qwen-training-hybrid-experts-for","title":"Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding","date":"2025-05-10","arxiv_id":"2505.06685","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/vaemo-efficient-representation-learning-for","slug":"vaemo-efficient-representation-learning-for","title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","date":"2025-05-05","arxiv_id":"2505.02331","repositories_listed":1,"syntology":null},{"url":"/paper/bersting-at-the-screams-a-benchmark-for","slug":"bersting-at-the-screams-a-benchmark-for","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","date":"2025-04-30","arxiv_id":"2505.00059","repositories_listed":1,"syntology":null},{"url":"/paper/physiosync-temporal-and-cross-modal","slug":"physiosync-temporal-and-cross-modal","title":"PhysioSync: Temporal and Cross-Modal Contrastive Learning Inspired by Physiological Synchronization for EEG-Based Emotion Recognition","date":"2025-04-24","arxiv_id":"2504.17163","repositories_listed":1,"syntology":null},{"url":"/paper/cmcrd-cross-modal-contrastive-representation","slug":"cmcrd-cross-modal-contrastive-representation","title":"CMCRD: Cross-Modal Contrastive Representation Distillation for Emotion Recognition","date":"2025-04-12","arxiv_id":"2504.09221","repositories_listed":1,"syntology":null},{"url":"/paper/mixeeg-enhancing-eeg-federated-learning-for","slug":"mixeeg-enhancing-eeg-federated-learning-for","title":"mixEEG: Enhancing EEG Federated Learning for Cross-subject EEG Classification with Tailored mixup","date":"2025-04-07","arxiv_id":"2504.07987","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-meet-contrastive","slug":"large-language-models-meet-contrastive","title":"Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages","date":"2025-03-25","arxiv_id":"2503.21806","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/maven-multi-modal-attention-for-valence","slug":"maven-multi-modal-attention-for-valence","title":"MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network","date":"2025-03-16","arxiv_id":"2503.12623","repositories_listed":1,"syntology":null},{"url":"/paper/prosody-enhanced-acoustic-pre-training-and","slug":"prosody-enhanced-acoustic-pre-training-and","title":"Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing","date":"2025-03-15","arxiv_id":"2503.12042","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-va-a-mamba-based-approach-for","slug":"mamba-va-a-mamba-based-approach-for","title":"Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space","date":"2025-03-13","arxiv_id":"2503.10104","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-of-body-motion-data","slug":"synthetic-data-generation-of-body-motion-data","title":"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition","date":"2025-03-11","arxiv_id":"2503.14513","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/a-novel-fourier-adjacency-transformer-for","slug":"a-novel-fourier-adjacency-transformer-for","title":"A novel Fourier Adjacency Transformer for advanced EEG emotion recognition","date":"2025-02-28","arxiv_id":"2503.13465","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-novel-fourier-adjacency-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2503.13465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13465"}},"official":{"repos":["YanhaoHuang23/FAT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/steering-language-model-to-stable-speech","slug":"steering-language-model-to-stable-speech","title":"Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought","date":"2025-02-25","arxiv_id":"2502.18186","repositories_listed":1,"syntology":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/mse-adapter-a-lightweight-plugin-endowing","slug":"mse-adapter-a-lightweight-plugin-endowing","title":"MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion Recognition","date":"2025-02-18","arxiv_id":"2502.12478","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-personalized-large-language","slug":"a-survey-of-personalized-large-language","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","date":"2025-02-17","arxiv_id":"2502.11528","repositories_listed":1,"syntology":null},{"url":"/paper/brighter-bridging-the-gap-in-human-annotated","slug":"brighter-bridging-the-gap-in-human-annotated","title":"BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages","date":"2025-02-17","arxiv_id":"2502.11926","repositories_listed":1,"syntology":null},{"url":"/paper/ramer-reconstruction-based-adversarial-model","slug":"ramer-reconstruction-based-adversarial-model","title":"RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition","date":"2025-02-09","arxiv_id":"2502.10435","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unified-music-emotion-recognition","slug":"towards-unified-music-emotion-recognition","title":"Towards Unified Music Emotion Recognition across Dimensional and Categorical Models","date":"2025-02-06","arxiv_id":"2502.03979","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/towards-unified-music-emotion-recognition#ran","syntology_url":"https://syntology.ai/paper/2502.03979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03979"}},"official":{"repos":["AMAAI-Lab/Music2Emotion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/sigwavnet-learning-multiresolution-signal","slug":"sigwavnet-learning-multiresolution-signal","title":"SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition","date":"2025-02-01","arxiv_id":"2502.00310","repositories_listed":1,"syntology":null},{"url":"/paper/osum-advancing-open-speech-understanding","slug":"osum-advancing-open-speech-understanding","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","date":"2025-01-23","arxiv_id":"2501.13306","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-by-supervised","slug":"synthetic-data-generation-by-supervised","title":"Synthetic Data Generation by Supervised Neural Gas Network for Physiological Emotion Recognition Data","date":"2025-01-19","arxiv_id":"2501.16353","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-based-feature-fusion-for","slug":"deep-learning-based-feature-fusion-for","title":"Deep Learning-Based Feature Fusion for Emotion Analysis and Suicide Risk Differentiation in Chinese Psychological Support Hotlines","date":"2025-01-15","arxiv_id":"2501.08696","repositories_listed":1,"syntology":null},{"url":"/paper/emonext-an-adapted-convnext-for-facial-1","slug":"emonext-an-adapted-convnext-for-facial-1","title":"EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition","date":"2025-01-14","arxiv_id":"2501.08199","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-deep-learning-approach-for-facial","slug":"a-novel-deep-learning-approach-for-facial","title":"A novel deep learning approach for facial emotion recognition: application to detecting emotional responses in elderly individuals with Alzheimer’s disease","date":"2024-12-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/personalized-dynamic-music-emotion","slug":"personalized-dynamic-music-emotion","title":"Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-Learning","date":"2024-12-26","arxiv_id":"2412.19200","repositories_listed":1,"syntology":null},{"url":"/paper/bridge-then-begin-anew-generating-target","slug":"bridge-then-begin-anew-generating-target","title":"Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation","date":"2024-12-18","arxiv_id":"2412.13577","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-fuzzy-oriented-multi-modal","slug":"spatio-temporal-fuzzy-oriented-multi-modal","title":"Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion Recognition","date":"2024-12-18","arxiv_id":"2412.13541","repositories_listed":1,"syntology":null},{"url":"/paper/swin-transformer-with-enhanced-dropout-and","slug":"swin-transformer-with-enhanced-dropout-and","title":"Swin Transformer with Enhanced Dropout and Layer-wise Unfreezing for Facial Expression Recognition in Mental Health Detection","date":"2024-12-02","arxiv_id":null,"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/enhanced-cross-dataset-electroencephalogram","slug":"enhanced-cross-dataset-electroencephalogram","title":"Enhanced Cross-Dataset Electroencephalogram-based Emotion Recognition using Unsupervised Domain Adaptation","date":"2024-11-19","arxiv_id":"2411.12852","repositories_listed":1,"syntology":null},{"url":"/paper/improvement-in-facial-emotion-recognition","slug":"improvement-in-facial-emotion-recognition","title":"Improvement in Facial Emotion Recognition using Synthetic Data Generated by Diffusion Model","date":"2024-11-16","arxiv_id":"2411.10863","repositories_listed":1,"syntology":null},{"url":"/paper/pfml-self-supervised-learning-of-time-series","slug":"pfml-self-supervised-learning-of-time-series","title":"PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse","date":"2024-11-15","arxiv_id":"2411.10087","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-superb-phase-2-a-collaboratively","slug":"dynamic-superb-phase-2-a-collaboratively","title":"Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks","date":"2024-11-08","arxiv_id":"2411.05361","repositories_listed":1,"syntology":{"n":21,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":21,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dynamic-superb-phase-2-a-collaboratively#ran","syntology_url":"https://syntology.ai/paper/2411.05361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05361"}},"official":{"repos":["dynamic-superb/dynamic-superb"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/feature-distribution-adaptation-network-for","slug":"feature-distribution-adaptation-network-for","title":"Multi-modal Speech Emotion Recognition via Feature Distribution Adaptation Network","date":"2024-10-29","arxiv_id":"2410.22023","repositories_listed":1,"syntology":null},{"url":"/paper/leaving-some-facial-features-behind","slug":"leaving-some-facial-features-behind","title":"Leaving Some Facial Features Behind","date":"2024-10-29","arxiv_id":"2411.00824","repositories_listed":1,"syntology":null},{"url":"/paper/tgca-pvt-topic-guided-context-aware-pyramid","slug":"tgca-pvt-topic-guided-context-aware-pyramid","title":"TGCA-PVT: Topic-Guided Context-Aware Pyramid Vision Transformer for Sticker Emotion Recognition","date":"2024-10-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/regularized-xception-for-facial-expression","slug":"regularized-xception-for-facial-expression","title":"Regularized Xception for facial expression recognition with extra training data and step decay learning rate","date":"2024-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-llm-embeddings-for-cross-dataset","slug":"leveraging-llm-embeddings-for-cross-dataset","title":"Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction","date":"2024-10-15","arxiv_id":"2410.11522","repositories_listed":1,"syntology":null},{"url":"/paper/audio-explanation-synthesis-with-generative","slug":"audio-explanation-synthesis-with-generative","title":"Audio Explanation Synthesis with Generative Foundation Models","date":"2024-10-10","arxiv_id":"2410.07530","repositories_listed":1,"syntology":null},{"url":"/paper/context-and-system-fusion-in-post-asr-emotion","slug":"context-and-system-fusion-in-post-asr-emotion","title":"Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models","date":"2024-10-04","arxiv_id":"2410.03312","repositories_listed":1,"syntology":null},{"url":"/paper/emojiherovr-a-study-on-facial-expression","slug":"emojiherovr-a-study-on-facial-expression","title":"EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays","date":"2024-10-04","arxiv_id":"2410.03331","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-textual-and-acoustic-features","slug":"disentangling-textual-and-acoustic-features","title":"Disentangling Textual and Acoustic Features of Neural Speech Representations","date":"2024-10-03","arxiv_id":"2410.03037","repositories_listed":1,"syntology":null},{"url":"/paper/fastadasp-multitask-adapted-efficient","slug":"fastadasp-multitask-adapted-efficient","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","date":"2024-10-03","arxiv_id":"2410.03007","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastadasp-multitask-adapted-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.03007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03007"}},"official":{"repos":["yichen14/fastadasp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/do-music-generation-models-encode-music","slug":"do-music-generation-models-encode-music","title":"Do Music Generation Models Encode Music Theory?","date":"2024-10-01","arxiv_id":"2410.00872","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":0,"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/do-music-generation-models-encode-music#ran","syntology_url":"https://syntology.ai/paper/2410.00872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00872"}},"official":{"repos":["brown-palm/syntheory"],"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/uniemox-cross-modal-semantic-guided-large","slug":"uniemox-cross-modal-semantic-guided-large","title":"UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception","date":"2024-09-27","arxiv_id":"2409.18877","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-speech-emotion-recognition","slug":"cross-lingual-speech-emotion-recognition","title":"Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models","date":"2024-09-25","arxiv_id":"2409.16920","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-cognitive-state","slug":"semi-supervised-cognitive-state","title":"Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling","date":"2024-09-25","arxiv_id":"2409.16937","repositories_listed":1,"syntology":null},{"url":"/paper/online-multi-level-contrastive-representation","slug":"online-multi-level-contrastive-representation","title":"Online Multi-level Contrastive Representation Distillation for Cross-Subject fNIRS Emotion Recognition","date":"2024-09-24","arxiv_id":"2409.16081","repositories_listed":1,"syntology":null},{"url":"/paper/revise-reason-and-recognize-llm-based-emotion","slug":"revise-reason-and-recognize-llm-based-emotion","title":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","date":"2024-09-23","arxiv_id":"2409.15551","repositories_listed":1,"syntology":null},{"url":"/paper/improving-speech-emotion-recognition-in-under","slug":"improving-speech-emotion-recognition-in-under","title":"Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection","date":"2024-09-17","arxiv_id":"2409.10985","repositories_listed":1,"syntology":null},{"url":"/paper/tbdm-net-bidirectional-dense-networks-with","slug":"tbdm-net-bidirectional-dense-networks-with","title":"TBDM-Net: Bidirectional Dense Networks with Gender Information for Speech Emotion Recognition","date":"2024-09-16","arxiv_id":"2409.10056","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-deep-learning-embeddings-for","slug":"explaining-deep-learning-embeddings-for","title":"Explaining Deep Learning Embeddings for Speech Emotion Recognition by Predicting Interpretable Acoustic Features","date":"2024-09-14","arxiv_id":"2409.09511","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-content-and-acoustic","slug":"leveraging-content-and-acoustic","title":"Leveraging Content and Acoustic Representations for Speech Emotion Recognition","date":"2024-09-09","arxiv_id":"2409.05566","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-enhanced-text-audio-video-alignment","slug":"mamba-enhanced-text-audio-video-alignment","title":"Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations","date":"2024-09-08","arxiv_id":"2409.05243","repositories_listed":1,"syntology":null},{"url":"/paper/resemotenet-bridging-accuracy-and-loss","slug":"resemotenet-bridging-accuracy-and-loss","title":"ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition","date":"2024-09-01","arxiv_id":"2409.10545","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-emotion-unveiling-the-emotion","slug":"from-text-to-emotion-unveiling-the-emotion","title":"From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs","date":"2024-08-30","arxiv_id":"2408.17026","repositories_listed":1,"syntology":null},{"url":"/paper/speechcaps-advancing-instruction-based","slug":"speechcaps-advancing-instruction-based","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","date":"2024-08-25","arxiv_id":"2408.13891","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/the-whole-is-bigger-than-the-sum-of-its-parts","slug":"the-whole-is-bigger-than-the-sum-of-its-parts","title":"The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability","date":"2024-08-21","arxiv_id":"2408.11956","repositories_listed":1,"syntology":null},{"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":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 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":3,"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/emodynamix-emotional-support-dialogue","slug":"emodynamix-emotional-support-dialogue","title":"EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics","date":"2024-08-16","arxiv_id":"2408.08782","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/ser-evals-in-domain-and-out-of-domain","slug":"ser-evals-in-domain-and-out-of-domain","title":"SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition","date":"2024-08-14","arxiv_id":"2408.07851","repositories_listed":1,"syntology":null},{"url":"/paper/hique-hierarchical-question-embedding-network","slug":"hique-hierarchical-question-embedding-network","title":"HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detection","date":"2024-08-07","arxiv_id":"2408.03648","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21315","slug":"2407-21315","title":"Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances","date":"2024-07-31","arxiv_id":"2407.21315","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/norface-improving-facial-expression-analysis","slug":"norface-improving-facial-expression-analysis","title":"Norface: Improving Facial Expression Analysis by Identity Normalization","date":"2024-07-22","arxiv_id":"2407.15617","repositories_listed":1,"syntology":null},{"url":"/paper/bsc-upc-at-emospeech-iberlef2024-attention","slug":"bsc-upc-at-emospeech-iberlef2024-attention","title":"BSC-UPC at EmoSPeech-IberLEF2024: Attention Pooling for Emotion Recognition","date":"2024-07-17","arxiv_id":"2407.12467","repositories_listed":1,"syntology":null},{"url":"/paper/mdpe-a-multimodal-deception-dataset-with","slug":"mdpe-a-multimodal-deception-dataset-with","title":"MDPE: A Multimodal Deception Dataset with Personality and Emotional Characteristics","date":"2024-07-17","arxiv_id":"2407.12274","repositories_listed":1,"syntology":null},{"url":"/paper/masive-open-ended-affective-state","slug":"masive-open-ended-affective-state","title":"MASIVE: Open-Ended Affective State Identification in English and Spanish","date":"2024-07-16","arxiv_id":"2407.12196","repositories_listed":1,"syntology":null},{"url":"/paper/listen-and-speak-fairly-a-study-on-semantic","slug":"listen-and-speak-fairly-a-study-on-semantic","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","date":"2024-07-09","arxiv_id":"2407.06957","repositories_listed":1,"syntology":null},{"url":"/paper/meeg-and-at-dgnn-advancing-eeg-emotion","slug":"meeg-and-at-dgnn-advancing-eeg-emotion","title":"MEEG and AT-DGNN: Improving EEG Emotion Recognition with Music Introducing and Graph-based Learning","date":"2024-07-08","arxiv_id":"2407.05550","repositories_listed":1,"syntology":null},{"url":"/paper/mmad-multi-label-micro-action-detection-in","slug":"mmad-multi-label-micro-action-detection-in","title":"MMAD: Multi-label Micro-Action Detection in Videos","date":"2024-07-07","arxiv_id":"2407.05311","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-prompt-learning-with-missing","slug":"multimodal-prompt-learning-with-missing","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","date":"2024-07-07","arxiv_id":"2407.05374","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multimodal-prompt-learning-with-missing#ran","syntology_url":"https://syntology.ai/paper/2407.05374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05374"}},"official":{"repos":["zrguo/MPLMM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/bioserc-integrating-biography-speakers","slug":"bioserc-integrating-biography-speakers","title":"BiosERC: Integrating Biography Speakers Supported by LLMs for ERC Tasks","date":"2024-07-05","arxiv_id":"2407.04279","repositories_listed":1,"syntology":null},{"url":"/paper/are-you-sure-analysing-uncertainty","slug":"are-you-sure-analysing-uncertainty","title":"Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition","date":"2024-07-01","arxiv_id":"2407.01143","repositories_listed":1,"syntology":null},{"url":"/paper/emt-a-novel-transformer-for-generalized-cross","slug":"emt-a-novel-transformer-for-generalized-cross","title":"EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition","date":"2024-06-26","arxiv_id":"2406.18345","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":1,"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/emt-a-novel-transformer-for-generalized-cross#ran","syntology_url":"https://syntology.ai/paper/2406.18345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18345"}},"official":{"repos":["yi-ding-cs/emt"],"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/feature-fusion-based-on-mutual-cross","slug":"feature-fusion-based-on-mutual-cross","title":"Feature Fusion Based on Mutual-Cross-Attention Mechanism for EEG Emotion Recognition","date":"2024-06-20","arxiv_id":"2406.14014","repositories_listed":1,"syntology":null},{"url":"/paper/feedforward-at-semeval-2024-task-10-trigger","slug":"feedforward-at-semeval-2024-task-10-trigger","title":"FeedForward at SemEval-2024 Task 10: Trigger and sentext-height enriched emotion analysis in multi-party conversations","date":"2024-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/odyssey-2024-speech-emotion-recognition","slug":"odyssey-2024-speech-emotion-recognition","title":"Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results","date":"2024-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/are-we-there-yet-a-brief-survey-of-music","slug":"are-we-there-yet-a-brief-survey-of-music","title":"Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges","date":"2024-06-13","arxiv_id":"2406.08809","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-multilingual-unseen-speaker-emotion","slug":"exploring-multilingual-unseen-speaker-emotion","title":"Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning","date":"2024-06-13","arxiv_id":"2406.08931","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-with-asr","slug":"speech-emotion-recognition-with-asr","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","date":"2024-06-12","arxiv_id":"2406.08353","repositories_listed":1,"syntology":null},{"url":"/paper/emobox-multilingual-multi-corpus-speech","slug":"emobox-multilingual-multi-corpus-speech","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","date":"2024-06-11","arxiv_id":"2406.07162","repositories_listed":1,"syntology":null},{"url":"/paper/exhubert-enhancing-hubert-through-block","slug":"exhubert-enhancing-hubert-through-block","title":"ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets","date":"2024-06-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enrolment-based-personalisation-for-improving","slug":"enrolment-based-personalisation-for-improving","title":"Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition","date":"2024-06-10","arxiv_id":"2406.06665","repositories_listed":1,"syntology":null},{"url":"/paper/interspeech-2009-emotion-challenge-revisited","slug":"interspeech-2009-emotion-challenge-revisited","title":"INTERSPEECH 2009 Emotion Challenge Revisited: Benchmarking 15 Years of Progress in Speech Emotion Recognition","date":"2024-06-10","arxiv_id":"2406.06401","repositories_listed":1,"syntology":null}],"record_sha256":"8aac954bb5ce1ffd19a73b7fb339565a7513ce3a24f0a7a78730dc7c1a9838d1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}