{"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/genre-classification","name":"Genre classification","slug":"genre-classification","description_markdown":"Genre classification is the process of grouping objects together based on defined similarities such as shape, pixel, location, or intensity.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":130,"papers_with_code":51,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/genre-classification-on-book-cover-dataset","slug":"genre-classification-on-book-cover-dataset","dataset":"Book Cover Dataset","dataset_url":"/dataset/book-cover-dataset","rows_in_archive":2,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"AlexNet","paper_title":"Judging a Book By its Cover","paper_url":"/paper/judging-a-book-by-its-cover","paper_date":"2016-10-28","arxiv_id":"1610.09204","code_links":[{"title":"uchidalab/book-dataset","url":"https://github.com/uchidalab/book-dataset"},{"title":"akshaybhatia10/Book-Genre-Classification","url":"https://github.com/akshaybhatia10/Book-Genre-Classification"},{"title":"adamjeanlaurent/Book-Recommender","url":"https://github.com/adamjeanlaurent/Book-Recommender"},{"title":"SeaOfFrost/BookCoverClassifier","url":"https://github.com/SeaOfFrost/BookCoverClassifier"}],"syntology":null}},{"leaderboard":"/sota/genre-classification-on-fma","slug":"genre-classification-on-fma","dataset":"FMA","dataset_url":"/dataset/fma","rows_in_archive":1,"metrics":["CNN"],"first_row_in_archive_order":{"model":"cnn","paper_title":"Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features","paper_url":"/paper/multi-label-music-genre-classification-from","paper_date":"2017-07-16","arxiv_id":"1707.04916","code_links":[{"title":"sergiooramas/tartarus","url":"https://github.com/sergiooramas/tartarus"}],"syntology":null}}],"datasets":[{"url":"/dataset/fma","name":"FMA","full_name":"Free Music Archive","num_papers_in_archive":128},{"url":"/dataset/book-cover-dataset","name":"Book Cover Dataset","full_name":"","num_papers_in_archive":7},{"url":"/dataset/moviescope","name":"Moviescope","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mumu","name":"MuMu","full_name":"","num_papers_in_archive":4},{"url":"/dataset/ptvd","name":"PTVD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/trailers12k","name":"Trailers12k","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":130,"of_with_code":51,"tagged_in_all":130,"counts":{"archive_papers_tagged":130,"with_a_code_link":51,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":130,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/gated-multimodal-units-for-information-fusion","slug":"gated-multimodal-units-for-information-fusion","title":"Gated Multimodal Units for Information Fusion","date":"2017-02-07","arxiv_id":"1702.01992","repositories_listed":9,"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/gated-multimodal-units-for-information-fusion#ran","syntology_url":"https://syntology.ai/paper/1702.01992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.01992"}},"official":{"repos":["johnarevalo/gmu-mmimdb"],"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/judging-a-book-by-its-cover","slug":"judging-a-book-by-its-cover","title":"Judging a Book By its Cover","date":"2016-10-28","arxiv_id":"1610.09204","repositories_listed":4,"syntology":null},{"url":"/paper/pre-training-music-classification-models-via","slug":"pre-training-music-classification-models-via","title":"Pre-training Music Classification Models via Music Source Separation","date":"2023-10-24","arxiv_id":"2310.15845","repositories_listed":2,"syntology":null},{"url":"/paper/architecture-representations-for-quantum","slug":"architecture-representations-for-quantum","title":"Hierarchical quantum circuit representations for neural architecture search","date":"2022-10-26","arxiv_id":"2210.15073","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-based-edm-subgenre","slug":"deep-learning-based-edm-subgenre","title":"Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features","date":"2021-10-17","arxiv_id":"2110.08862","repositories_listed":2,"syntology":null},{"url":"/paper/musicbert-symbolic-music-understanding-with","slug":"musicbert-symbolic-music-understanding-with","title":"MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training","date":"2021-06-10","arxiv_id":"2106.05630","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/musicbert-symbolic-music-understanding-with#ran","syntology_url":"https://syntology.ai/paper/2106.05630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05630"}},"official":{"repos":["microsoft/muzic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/on-large-scale-genre-classification-in","slug":"on-large-scale-genre-classification-in","title":"On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns","date":"2019-10-21","arxiv_id":"1910.09242","repositories_listed":2,"syntology":null},{"url":"/paper/texture-selection-for-automatic-music-genre","slug":"texture-selection-for-automatic-music-genre","title":"Texture Selection for Automatic Music Genre Classification","date":"2019-05-28","arxiv_id":"1905.11959","repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-neural-network-achieves-human","slug":"convolutional-neural-network-achieves-human","title":"Convolutional Neural Network Achieves Human-level Accuracy in Music Genre Classification","date":"2018-02-27","arxiv_id":"1802.09697","repositories_listed":2,"syntology":null},{"url":"/paper/music-genre-classification-with-paralleling","slug":"music-genre-classification-with-paralleling","title":"Music Genre Classification with Paralleling Recurrent Convolutional Neural Network","date":"2017-12-22","arxiv_id":"1712.08370","repositories_listed":2,"syntology":null},{"url":"/paper/controlling-out-of-domain-gaps-in-llms-for","slug":"controlling-out-of-domain-gaps-in-llms-for","title":"Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection","date":"2024-12-29","arxiv_id":"2412.20595","repositories_listed":1,"syntology":null},{"url":"/paper/music-genre-classification-using-large","slug":"music-genre-classification-using-large","title":"Music Genre Classification using Large Language Models","date":"2024-10-10","arxiv_id":"2410.08321","repositories_listed":1,"syntology":null},{"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/comparative-analysis-of-pretrained-audio","slug":"comparative-analysis-of-pretrained-audio","title":"Comparative Analysis of Pretrained Audio Representations in Music Recommender Systems","date":"2024-09-13","arxiv_id":"2409.08987","repositories_listed":1,"syntology":null},{"url":"/paper/bert-goes-off-topic-investigating-the-domain","slug":"bert-goes-off-topic-investigating-the-domain","title":"BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification","date":"2023-11-27","arxiv_id":"2311.16083","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-domain-knowledge-graph-into","slug":"incorporating-domain-knowledge-graph-into","title":"Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning","date":"2023-10-12","arxiv_id":"2310.08032","repositories_listed":1,"syntology":null},{"url":"/paper/ptvd-a-large-scale-plot-oriented-multimodal","slug":"ptvd-a-large-scale-plot-oriented-multimodal","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","date":"2023-06-26","arxiv_id":"2306.14644","repositories_listed":1,"syntology":null},{"url":"/paper/multi-source-contrastive-learning-from","slug":"multi-source-contrastive-learning-from","title":"Multi-Source Contrastive Learning from Musical Audio","date":"2023-02-14","arxiv_id":"2302.07077","repositories_listed":1,"syntology":null},{"url":"/paper/deep-architectures-for-content-moderation-and","slug":"deep-architectures-for-content-moderation-and","title":"Deep Architectures for Content Moderation and Movie Content Rating","date":"2022-12-08","arxiv_id":"2212.04533","repositories_listed":1,"syntology":null},{"url":"/paper/effective-audio-classification-network-based","slug":"effective-audio-classification-network-based","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","date":"2022-11-05","arxiv_id":"2211.02940","repositories_listed":1,"syntology":null},{"url":"/paper/integrated-parameter-efficient-tuning-for","slug":"integrated-parameter-efficient-tuning-for","title":"Integrated Parameter-Efficient Tuning for General-Purpose Audio Models","date":"2022-11-04","arxiv_id":"2211.02227","repositories_listed":1,"syntology":null},{"url":"/paper/low-resource-music-genre-classification-with","slug":"low-resource-music-genre-classification-with","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","date":"2022-11-02","arxiv_id":"2211.01317","repositories_listed":1,"syntology":null},{"url":"/paper/movieclip-visual-scene-recognition-in-movies","slug":"movieclip-visual-scene-recognition-in-movies","title":"MovieCLIP: Visual Scene Recognition in Movies","date":"2022-10-20","arxiv_id":"2210.11065","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/movieclip-visual-scene-recognition-in-movies#ran","syntology_url":"https://syntology.ai/paper/2210.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11065"}},"official":{"repos":["usc-sail/mica-MovieCLIP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/trailers12k-evaluating-transfer-learning-for","slug":"trailers12k-evaluating-transfer-learning-for","title":"Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification","date":"2022-10-14","arxiv_id":"2210.07983","repositories_listed":1,"syntology":null},{"url":"/paper/matt-a-multiple-instance-attention-mechanism","slug":"matt-a-multiple-instance-attention-mechanism","title":"MATT: A Multiple-instance Attention Mechanism for Long-tail Music Genre Classification","date":"2022-09-09","arxiv_id":"2209.04109","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-on-broadcast-networks-for-music-genre","slug":"a-study-on-broadcast-networks-for-music-genre","title":"A Study on Broadcast Networks for Music Genre Classification","date":"2022-08-25","arxiv_id":"2208.12086","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-audio-language-learning-for-music","slug":"contrastive-audio-language-learning-for-music","title":"Contrastive Audio-Language Learning for Music","date":"2022-08-25","arxiv_id":"2208.12208","repositories_listed":1,"syntology":null},{"url":"/paper/grown-up-a-graph-representation-of-a-webpage","slug":"grown-up-a-graph-representation-of-a-webpage","title":"GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training","date":"2022-08-03","arxiv_id":"2208.02252","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-calibration-for-deep-audio","slug":"uncertainty-calibration-for-deep-audio","title":"Uncertainty Calibration for Deep Audio Classifiers","date":"2022-06-27","arxiv_id":"2206.13071","repositories_listed":1,"syntology":null},{"url":"/paper/ems-efficient-and-effective-massively","slug":"ems-efficient-and-effective-massively","title":"EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning","date":"2022-05-31","arxiv_id":"2205.15744","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-musical-form-recognition","slug":"deep-learning-for-musical-form-recognition","title":"Deep Learning for Musical Form: Recognition and Analysis","date":"2022-04-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/effectively-leveraging-multi-modal-features","slug":"effectively-leveraging-multi-modal-features","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","date":"2022-03-24","arxiv_id":"2203.13281","repositories_listed":1,"syntology":null},{"url":"/paper/s3t-self-supervised-pre-training-with-swin","slug":"s3t-self-supervised-pre-training-with-swin","title":"S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification","date":"2022-02-21","arxiv_id":"2202.10139","repositories_listed":1,"syntology":null},{"url":"/paper/towards-tokenized-human-dynamics","slug":"towards-tokenized-human-dynamics","title":"Towards Tokenized Human Dynamics Representation","date":"2021-11-22","arxiv_id":"2111.11433","repositories_listed":1,"syntology":null},{"url":"/paper/ms-sincresnet-joint-learning-of-1d-and-2d","slug":"ms-sincresnet-joint-learning-of-1d-and-2d","title":"MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification","date":"2021-09-18","arxiv_id":"2109.08910","repositories_listed":1,"syntology":null},{"url":"/paper/dadagp-a-dataset-of-tokenized-guitarpro-songs","slug":"dadagp-a-dataset-of-tokenized-guitarpro-songs","title":"DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models","date":"2021-07-30","arxiv_id":"2107.14653","repositories_listed":1,"syntology":null},{"url":"/paper/codified-audio-language-modeling-learns","slug":"codified-audio-language-modeling-learns","title":"Codified audio language modeling learns useful representations for music information retrieval","date":"2021-07-12","arxiv_id":"2107.05677","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codified-audio-language-modeling-learns#ran","syntology_url":"https://syntology.ai/paper/2107.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05677"}},"official":{"repos":["p-lambda/jukemir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-weighted-fusion-of-transformers","slug":"multimodal-weighted-fusion-of-transformers","title":"Multimodal Weighted Fusion of Transformers for Movie Genre Classification","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enriched-music-representations-with-multiple","slug":"enriched-music-representations-with-multiple","title":"Enriched Music Representations with Multiple Cross-modal Contrastive Learning","date":"2021-04-01","arxiv_id":"2104.00437","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/enriched-music-representations-with-multiple#ran","syntology_url":"https://syntology.ai/paper/2104.00437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00437"}},"official":{"repos":["andrebola/contrastive-mir-learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/indicnlpsuite-monolingual-corpora-evaluation","slug":"indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/know-thy-corpus-robust-methods-for-digital","slug":"know-thy-corpus-robust-methods-for-digital","title":"Know thy corpus! Robust methods for digital curation of Web corpora","date":"2020-03-13","arxiv_id":"2003.06389","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-for-music-genre-multifaceted","slug":"machine-learning-for-music-genre-multifaceted","title":"Machine learning for music genre: multifaceted review and experimentation with audioset","date":"2019-11-28","arxiv_id":"1911.12618","repositories_listed":1,"syntology":null},{"url":"/paper/recognizing-musical-entities-in-user","slug":"recognizing-musical-entities-in-user","title":"Recognizing Musical Entities in User-generated Content","date":"2019-04-01","arxiv_id":"1904.00648","repositories_listed":1,"syntology":null},{"url":"/paper/bottom-up-broadcast-neural-network-for-music","slug":"bottom-up-broadcast-neural-network-for-music","title":"Bottom-up Broadcast Neural Network For Music Genre Classification","date":"2019-01-24","arxiv_id":"1901.08928","repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-a-transparency-driven-environment","slug":"utilizing-a-transparency-driven-environment","title":"Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History","date":"2018-10-01","arxiv_id":"1810.00968","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-of-artist-group-factors-to","slug":"transfer-learning-of-artist-group-factors-to","title":"Transfer Learning of Artist Group Factors to Musical Genre Classification","date":"2018-05-05","arxiv_id":"1805.02043","repositories_listed":1,"syntology":null},{"url":"/paper/music-genre-classification-using-masked","slug":"music-genre-classification-using-masked","title":"Music Genre Classification using Masked Conditional Neural Networks","date":"2018-02-18","arxiv_id":"1802.06432","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-music-genre-classification-from","slug":"multi-label-music-genre-classification-from","title":"Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features","date":"2017-07-16","arxiv_id":"1707.04916","repositories_listed":1,"syntology":null},{"url":"/paper/lyrics-based-music-genre-classification-using","slug":"lyrics-based-music-genre-classification-using","title":"Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network","date":"2017-07-15","arxiv_id":"1707.04678","repositories_listed":1,"syntology":null},{"url":"/paper/column-networks-for-collective-classification","slug":"column-networks-for-collective-classification","title":"Column Networks for Collective Classification","date":"2016-09-15","arxiv_id":"1609.04508","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-deep-convolutional-neural-networks","slug":"explaining-deep-convolutional-neural-networks","title":"Explaining Deep Convolutional Neural Networks on Music Classification","date":"2016-07-08","arxiv_id":"1607.02444","repositories_listed":1,"syntology":null},{"url":null,"slug":"cmi-bench-a-comprehensive-benchmark-for","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","date":"2025-06-14","arxiv_id":"2506.12285","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-ornaments-in-vocal-indian-art","title":"Recognizing Ornaments in Vocal Indian Art Music with Active Annotation","date":"2025-05-07","arxiv_id":"2505.04419","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-data-resilient-multi-modal","title":"An Adaptive Data-Resilient Multi-Modal Framework for Hierarchical Multi-Label Book Genre Identification","date":"2025-05-05","arxiv_id":"2505.03839","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-you-sure-enhancing-multimodal-pretraining","title":"Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimation","date":"2025-04-18","arxiv_id":"2504.13465","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-rock-music-classification","title":"Progressive Rock Music Classification","date":"2025-04-15","arxiv_id":"2504.10821","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-movie-production-years-through","title":"Predicting Movie Production Years through Facial Recognition of Actors with Machine Learning","date":"2025-04-01","arxiv_id":"2504.01047","repositories_listed":0,"syntology":null},{"url":null,"slug":"ban-neuroanatomical-aligning-in-auditory","title":"BAN: Neuroanatomical Aligning in Auditory Recognition between Artificial Neural Network and Human Cortex","date":"2025-02-21","arxiv_id":"2502.15503","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-independent-deterministic","title":"EVolutionary Independent DEtermiNistiC Explanation","date":"2025-01-20","arxiv_id":"2501.16357","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-label-cross-lingual-automatic-music","title":"Multi-label Cross-lingual automatic music genre classification from lyrics with Sentence BERT","date":"2025-01-07","arxiv_id":"2501.03769","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-genre-classification-ensemble-learning","title":"Music Genre Classification: Ensemble Learning with Subcomponents-level Attention","date":"2024-12-20","arxiv_id":"2412.15602","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-spectrogram-sequence","title":"Attention-guided Spectrogram Sequence Modeling with CNNs for Music Genre Classification","date":"2024-11-18","arxiv_id":"2411.14474","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-processing-using-pattern-recognition","title":"Audio Processing using Pattern Recognition for Music Genre Classification","date":"2024-10-19","arxiv_id":"2410.14990","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-movie-genres-through-cross","title":"Unraveling Movie Genres through Cross-Attention Fusion of Bi-Modal Synergy of Poster","date":"2024-10-12","arxiv_id":"2410.19764","repositories_listed":0,"syntology":null},{"url":null,"slug":"movie-trailer-genre-classification-using","title":"Movie Trailer Genre Classification Using Multimodal Pretrained Features","date":"2024-10-11","arxiv_id":"2410.19760","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-perceptual-metrics-on-music","title":"The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification","date":"2024-09-25","arxiv_id":"2409.17069","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-sub-genre-classification-for","title":"Benchmarking Sub-Genre Classification For Mainstage Dance Music","date":"2024-09-10","arxiv_id":"2409.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-genre-and-success-classification","title":"Exploring Genre and Success Classification through Song Lyrics using DistilBERT: A Fun NLP Venture","date":"2024-07-28","arxiv_id":"2407.21068","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-music-genre-classification-through","title":"Enhancing Music Genre Classification through Multi-Algorithm Analysis and User-Friendly Visualization","date":"2024-05-27","arxiv_id":"2405.17413","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-genre-classification-training-an-ai","title":"Music Genre Classification: Training an AI model","date":"2024-05-23","arxiv_id":"2405.15096","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-genre-classification-a-comparative","title":"Music Genre Classification: A Comparative Analysis of CNN and XGBoost Approaches with Mel-frequency cepstral coefficients and Mel Spectrograms","date":"2024-01-09","arxiv_id":"2401.04737","repositories_listed":0,"syntology":null},{"url":null,"slug":"panel-transitions-for-genre-analysis-in","title":"Panel Transitions for Genre Analysis in Visual Narratives","date":"2023-12-14","arxiv_id":"2312.08720","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-recipe-genre-classification","title":"Towards Automated Recipe Genre Classification using Semi-Supervised Learning","date":"2023-10-24","arxiv_id":"2310.15693","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-music-genre-classification","title":"Exploring Music Genre Classification: Algorithm Analysis and Deployment Architecture","date":"2023-09-09","arxiv_id":"2309.04861","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-contrastive-learning-in-music-video","title":"Towards Contrastive Learning in Music Video Domain","date":"2023-09-01","arxiv_id":"2309.00347","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-genre-classification-with-resnet-and-bi","title":"Music Genre Classification with ResNet and Bi-GRU Using Visual Spectrograms","date":"2023-07-20","arxiv_id":"2307.10773","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-influence-in-multimodal-machine","title":"Modality Influence in Multimodal Machine Learning","date":"2023-06-10","arxiv_id":"2306.06476","repositories_listed":0,"syntology":null},{"url":null,"slug":"assorted-archetypal-and-annotated-two-million","title":"Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning","date":"2023-03-27","arxiv_id":"2303.16778","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtr-ctrl-instrument-and-genre-conditioning","title":"GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformers","date":"2023-02-10","arxiv_id":"2302.05393","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolution-channel-separation-and-frequency","title":"Convolution channel separation and frequency sub-bands aggregation for music genre classification","date":"2022-11-03","arxiv_id":"2211.01599","repositories_listed":0,"syntology":null},{"url":null,"slug":"cem-mil-podcasts-a-spoken-portuguese-document","title":"Cem Mil Podcasts: A Spoken Portuguese Document Corpus For Multi-modal, Multi-lingual and Multi-Dialect Information Access Research","date":"2022-09-23","arxiv_id":"2209.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-recognition-for-music-genre","title":"Open Set Recognition For Music Genre Classification","date":"2022-09-15","arxiv_id":"2209.07548","repositories_listed":0,"syntology":null},{"url":null,"slug":"gafx-a-general-audio-feature-extractor","title":"GAFX: A General Audio Feature eXtractor","date":"2022-07-19","arxiv_id":"2207.09145","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-scattering-transform-network-with","title":"The Scattering Transform Network with Generalized Morse Wavelets and Its Application to Music Genre Classification","date":"2022-06-16","arxiv_id":"2206.07857","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-confidence-of-predictions-of","title":"Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task","date":"2022-06-15","arxiv_id":"2206.07427","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-confidence-of-predictions-of-1","title":"Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"when-does-clip-generalize-better-than","title":"When does CLIP generalize better than unimodal models? When judging human-centric concepts","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-deep-music-generation-methods","title":"Evaluating Deep Music Generation Methods Using Data Augmentation","date":"2021-12-31","arxiv_id":"2201.00052","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonnegative-opls-for-supervised-design-of","title":"Nonnegative OPLS for Supervised Design of Filter Banks: Application to Image and Audio Feature Extraction","date":"2021-12-22","arxiv_id":"2112.12280","repositories_listed":0,"syntology":null},{"url":null,"slug":"violence-detection-in-videos","title":"Violence Detection in Videos","date":"2021-09-18","arxiv_id":"2109.08941","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilevel-profiling-of-situation-and","title":"Multilevel profiling of situation and dialogue-based deep networks for movie genre classification using movie trailers","date":"2021-09-14","arxiv_id":"2109.06488","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-classes-through-word-attribution","title":"Explaining Classes through Word Attribution","date":"2021-08-31","arxiv_id":"2108.13653","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-for-structure-based-news-genre","title":"A Joint Model for Structure-based News Genre Classification with Application to Text Summarization","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-audio-segments-in-call","title":"Classification of Audio Segments in Call Center Recordings using Convolutional Recurrent Neural Networks","date":"2021-06-04","arxiv_id":"2106.02422","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-content-analysis","title":"Audio Content Analysis","date":"2021-01-01","arxiv_id":"2101.00132","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-movie-genre-classification-with","title":"Rethinking movie genre classification with fine-grained semantic clustering","date":"2020-12-04","arxiv_id":"2012.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-multimodal-music-genre-classifier","title":"A Novel Multimodal Music Genre Classifier using Hierarchical Attention and Convolutional Neural Network","date":"2020-11-24","arxiv_id":"2011.11970","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-video-game-genre","title":"Deep learning for video game genre classification","date":"2020-11-21","arxiv_id":"2011.12143","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multi-modal-networks-for-book-genre","title":"Deep multi-modal networks for book genre classification based on its cover","date":"2020-11-15","arxiv_id":"2011.07658","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-traffic-analysis-based-iot-device","title":"Network Traffic Analysis based IoT Device Identification","date":"2020-09-10","arxiv_id":"2009.04682","repositories_listed":0,"syntology":null}],"syntology_records":6,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/genre-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/genre-classification/papers/2","json":"/task/genre-classification/papers/2.json","rows":30},{"order":"ran","page":1,"of":1,"url":"/task/genre-classification/papers/ran/1","json":"/task/genre-classification/papers/ran/1.json","rows":6}],"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":"b3203b9c45c2faaf2a6dc782abfb484d1a440980e96303118661dfee030e69cf","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}