{"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/activity-detection","name":"Activity Detection","slug":"activity-detection","description_markdown":"Detecting activities in extended videos.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":380,"papers_with_code":75,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":12,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/activity-detection-on-ava-speech","slug":"activity-detection-on-ava-speech","dataset":"AVA-Speech","dataset_url":"/dataset/ava-speech","rows_in_archive":4,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"CNN-BiLSTM_best","paper_title":"A Hybrid CNN-BiLSTM Voice Activity Detector","paper_url":"/paper/a-hybrid-cnn-bilstm-voice-activity-detector","paper_date":"2021-03-05","arxiv_id":"2103.03529","code_links":[{"title":"NickWilkinson37/voxseg","url":"https://github.com/NickWilkinson37/voxseg"}],"syntology":null}}],"datasets":[{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/toyota-smarthome","name":"Toyota Smarthome Dataset","full_name":"","num_papers_in_archive":31},{"url":"/dataset/road","name":"ROAD","full_name":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","num_papers_in_archive":27},{"url":"/dataset/meva","name":"MEVA","full_name":"Multiview Extended Video with Activities","num_papers_in_archive":17},{"url":"/dataset/tsu","name":"TSU","full_name":"Toyota Smarthome Untrimmed","num_papers_in_archive":16},{"url":"/dataset/ava-speech","name":"AVA-Speech","full_name":"","num_papers_in_archive":10},{"url":"/dataset/home-action-genome","name":"Home Action Genome","full_name":"","num_papers_in_archive":9},{"url":"/dataset/iitb-corridor","name":"IITB Corridor","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mlb-youtube-dataset","name":"MLB-YouTube Dataset","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/ucla-protest-image","name":"UCLA Protest Image","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dahlia-daily-human-life-activity","name":"DAHLIA","full_name":"DAily Human Life Activity","num_papers_in_archive":0},{"url":"/dataset/infiniterep","name":"InfiniteRep","full_name":"InfiniteRep","num_papers_in_archive":0}],"subtasks":[],"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":4,"rows_per_page":100,"shown":100,"of":380,"of_with_code":75,"tagged_in_all":380,"counts":{"archive_papers_tagged":380,"with_a_code_link":75,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":380,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/moshi-a-speech-text-foundation-model-for-real","slug":"moshi-a-speech-text-foundation-model-for-real","title":"Moshi: a speech-text foundation model for real-time dialogue","date":"2024-09-17","arxiv_id":"2410.00037","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moshi-a-speech-text-foundation-model-for-real#ran","syntology_url":"https://syntology.ai/paper/2410.00037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00037"}},"official":{"repos":["kyutai-labs/moshi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-speaker-and-wide-band-simulated","slug":"multi-speaker-and-wide-band-simulated","title":"Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization","date":"2022-11-12","arxiv_id":"2211.06750","repositories_listed":3,"syntology":null},{"url":"/paper/road-the-road-event-awareness-dataset-for","slug":"road-the-road-event-awareness-dataset-for","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","date":"2021-02-23","arxiv_id":"2102.11585","repositories_listed":3,"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/road-the-road-event-awareness-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2102.11585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11585"}},"official":{"repos":["gurkirt/3D-RetinaNet","gurkirt/road-dataset"],"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/pyannoteaudio-neural-building-blocks-for","slug":"pyannoteaudio-neural-building-blocks-for","title":"pyannote.audio: neural building blocks for speaker diarization","date":"2019-11-04","arxiv_id":"1911.01255","repositories_listed":3,"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/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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/rvad-an-unsupervised-segment-based-robust","slug":"rvad-an-unsupervised-segment-based-robust","title":"rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method","date":"2019-06-09","arxiv_id":"1906.03588","repositories_listed":3,"syntology":null},{"url":"/paper/fine-grained-activity-recognition-in-baseball","slug":"fine-grained-activity-recognition-in-baseball","title":"Fine-grained Activity Recognition in Baseball Videos","date":"2018-04-09","arxiv_id":"1804.03247","repositories_listed":3,"syntology":null},{"url":"/paper/r-c3d-region-convolutional-3d-network-for","slug":"r-c3d-region-convolutional-3d-network-for","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","date":"2017-03-22","arxiv_id":"1703.07814","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/r-c3d-region-convolutional-3d-network-for#ran","syntology_url":"https://syntology.ai/paper/1703.07814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07814"}},"official":{"repos":["VisionLearningGroup/R-C3D"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/an-end-to-end-architecture-for-keyword","slug":"an-end-to-end-architecture-for-keyword","title":"An End-to-End Architecture for Keyword Spotting and Voice Activity Detection","date":"2016-11-28","arxiv_id":"1611.09405","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-activity-detection-in-untrimmed","slug":"temporal-activity-detection-in-untrimmed","title":"Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks","date":"2016-08-29","arxiv_id":"1608.08128","repositories_listed":3,"syntology":null},{"url":"/paper/ivrit-ai-a-comprehensive-dataset-of-hebrew","slug":"ivrit-ai-a-comprehensive-dataset-of-hebrew","title":"ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development","date":"2023-07-17","arxiv_id":"2307.08720","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-embedding-aware-neural-diarization","slug":"speaker-embedding-aware-neural-diarization","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","date":"2021-11-28","arxiv_id":"2111.13694","repositories_listed":2,"syntology":null},{"url":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-speaker-segmentation-for-overlap","slug":"end-to-end-speaker-segmentation-for-overlap","title":"End-to-end speaker segmentation for overlap-aware resegmentation","date":"2021-04-08","arxiv_id":"2104.04045","repositories_listed":2,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language-1","slug":"voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","date":"2020-11-25","arxiv_id":"2011.12998","repositories_listed":2,"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":3,"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/voxlingua107-a-dataset-for-spoken-language-1#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":{"repos":["alumae/torch-xvectors-wav"],"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/harvesting-ambient-rf-for-presence-detection","slug":"harvesting-ambient-rf-for-presence-detection","title":"Harvesting Ambient RF for Presence Detection Through Deep Learning","date":"2020-02-13","arxiv_id":"2002.05770","repositories_listed":2,"syntology":null},{"url":"/paper/personal-vad-speaker-conditioned-voice","slug":"personal-vad-speaker-conditioned-voice","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection","date":"2019-08-12","arxiv_id":"1908.04284","repositories_listed":2,"syntology":null},{"url":"/paper/learning-latent-super-events-to-detect","slug":"learning-latent-super-events-to-detect","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","date":"2017-12-05","arxiv_id":"1712.01938","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-diarization-with-overlapping","slug":"speaker-diarization-with-overlapping","title":"Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm","date":"2025-06-03","arxiv_id":"2506.02610","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10879","slug":"2505-10879","title":"Multi-Stage Speaker Diarization for Noisy Classrooms","date":"2025-05-16","arxiv_id":"2505.10879","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-large-language-models-for-esg","slug":"optimizing-large-language-models-for-esg","title":"Optimizing Large Language Models for ESG Activity Detection in Financial Texts","date":"2025-02-28","arxiv_id":"2502.21112","repositories_listed":1,"syntology":null},{"url":"/paper/vanpy-voice-analysis-framework","slug":"vanpy-voice-analysis-framework","title":"VANPY: Voice Analysis Framework","date":"2025-02-17","arxiv_id":"2502.17579","repositories_listed":1,"syntology":null},{"url":"/paper/when-do-they-stop-a-first-step-towards","slug":"when-do-they-stop-a-first-step-towards","title":"When do they StOP?: A First Step Towards Automatically Identifying Team Communication in the Operating Room","date":"2025-02-12","arxiv_id":"2502.08299","repositories_listed":1,"syntology":null},{"url":"/paper/pre-equalization-aided-grant-free-massive","slug":"pre-equalization-aided-grant-free-massive","title":"Pre-Equalization Aided Grant-Free Massive Access in Massive MIMO System","date":"2025-02-10","arxiv_id":"2502.06239","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-detection-and-prediction-of-namd","slug":"automatic-detection-and-prediction-of-namd","title":"Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality","date":"2025-01-24","arxiv_id":"2501.14323","repositories_listed":1,"syntology":null},{"url":"/paper/wifi-csi-based-temporal-activity-detection","slug":"wifi-csi-based-temporal-activity-detection","title":"WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network","date":"2024-12-19","arxiv_id":"2412.16233","repositories_listed":1,"syntology":null},{"url":"/paper/automating-feedback-analysis-in-surgical","slug":"automating-feedback-analysis-in-surgical","title":"Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment","date":"2024-12-01","arxiv_id":"2412.00760","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-adapting-human-robot","slug":"a-framework-for-adapting-human-robot","title":"A Framework for Adapting Human-Robot Interaction to Diverse User Groups","date":"2024-10-15","arxiv_id":"2410.11377","repositories_listed":1,"syntology":null},{"url":"/paper/inagvad-a-challenging-french-tv-and-radio","slug":"inagvad-a-challenging-french-tv-and-radio","title":"InaGVAD : a Challenging French TV and Radio Corpus Annotated for Speech Activity Detection and Speaker Gender Segmentation","date":"2024-06-06","arxiv_id":"2406.04429","repositories_listed":1,"syntology":null},{"url":"/paper/activity-detection-for-massive-connectivity","slug":"activity-detection-for-massive-connectivity","title":"Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach","date":"2024-01-30","arxiv_id":"2401.16775","repositories_listed":1,"syntology":null},{"url":"/paper/online-speaker-diarization-of-meetings-guided","slug":"online-speaker-diarization-of-meetings-guided","title":"Online speaker diarization of meetings guided by speech separation","date":"2024-01-30","arxiv_id":"2402.00067","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-emotion-recognition-with-speech","slug":"integrating-emotion-recognition-with-speech","title":"Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations","date":"2023-08-14","arxiv_id":"2308.07145","repositories_listed":1,"syntology":null},{"url":"/paper/long-term-conversation-analysis-exploring","slug":"long-term-conversation-analysis-exploring","title":"Long-term Conversation Analysis: Exploring Utility and Privacy","date":"2023-06-28","arxiv_id":"2306.16071","repositories_listed":1,"syntology":null},{"url":"/paper/funasr-a-fundamental-end-to-end-speech","slug":"funasr-a-fundamental-end-to-end-speech","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","date":"2023-05-18","arxiv_id":"2305.11013","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-noise-reduction-methods-for","slug":"evaluation-of-noise-reduction-methods-for","title":"Evaluation of Noise Reduction Methods for Sentence Recognition by Sinhala Speaking Listeners","date":"2023-03-31","arxiv_id":"2303.17829","repositories_listed":1,"syntology":null},{"url":"/paper/ts-sep-joint-diarization-and-separation","slug":"ts-sep-joint-diarization-and-separation","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","date":"2023-03-07","arxiv_id":"2303.03849","repositories_listed":1,"syntology":null},{"url":"/paper/token-turing-machines","slug":"token-turing-machines","title":"Token Turing Machines","date":"2022-11-16","arxiv_id":"2211.09119","repositories_listed":1,"syntology":null},{"url":"/paper/sg-vad-stochastic-gates-based-speech-activity","slug":"sg-vad-stochastic-gates-based-speech-activity","title":"SG-VAD: Stochastic Gates Based Speech Activity Detection","date":"2022-10-28","arxiv_id":"2210.16022","repositories_listed":1,"syntology":null},{"url":"/paper/multitask-detection-of-speaker-changes","slug":"multitask-detection-of-speaker-changes","title":"Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using wav2vec 2.0","date":"2022-10-26","arxiv_id":"2210.14755","repositories_listed":1,"syntology":null},{"url":"/paper/brouhaha-multi-task-training-for-voice","slug":"brouhaha-multi-task-training-for-voice","title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","date":"2022-10-24","arxiv_id":"2210.13248","repositories_listed":1,"syntology":null},{"url":"/paper/mm-alt-a-multimodal-automatic-lyric","slug":"mm-alt-a-multimodal-automatic-lyric","title":"MM-ALT: A Multimodal Automatic Lyric Transcription System","date":"2022-07-13","arxiv_id":"2207.06127","repositories_listed":1,"syntology":null},{"url":"/paper/a-semi-supervised-geometric-driven","slug":"a-semi-supervised-geometric-driven","title":"A semi-supervised methodology for fishing activity detection using the geometry behind the trajectory of multiple vessels","date":"2022-07-12","arxiv_id":"2207.05514","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-multi-task-deep-learning-for","slug":"adversarial-multi-task-deep-learning-for","title":"Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay","date":"2022-07-04","arxiv_id":"2207.01691","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-voice-activity-detection-by","slug":"unsupervised-voice-activity-detection-by","title":"Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering","date":"2022-06-27","arxiv_id":"2206.13420","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-speech-separation-for","slug":"leveraging-speech-separation-for","title":"Low-Latency Speech Separation Guided Diarization for Telephone Conversations","date":"2022-04-05","arxiv_id":"2204.02306","repositories_listed":1,"syntology":null},{"url":"/paper/gan-based-joint-activity-detection-and","slug":"gan-based-joint-activity-detection-and","title":"Gan-Based Joint Activity Detection and Channel Estimation For Grant-free Random Access","date":"2022-04-04","arxiv_id":"2204.01731","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-embedding-aware-neural-diarization-a","slug":"speaker-embedding-aware-neural-diarization-a","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","date":"2022-03-18","arxiv_id":"2203.09767","repositories_listed":1,"syntology":null},{"url":"/paper/hgcn-harmonic-gated-compensation-network-for","slug":"hgcn-harmonic-gated-compensation-network-for","title":"HGCN: Harmonic gated compensation network for speech enhancement","date":"2022-01-30","arxiv_id":"2201.12755","repositories_listed":1,"syntology":null},{"url":"/paper/nas-vad-neural-architecture-search-for-voice","slug":"nas-vad-neural-architecture-search-for-voice","title":"NAS-VAD: Neural Architecture Search for Voice Activity Detection","date":"2022-01-22","arxiv_id":"2201.09032","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-temporal-side-information-in","slug":"exploiting-temporal-side-information-in","title":"Exploiting Temporal Side Information in Massive IoT Connectivity","date":"2022-01-05","arxiv_id":"2201.01485","repositories_listed":1,"syntology":null},{"url":"/paper/x-vector-based-voice-activity-detection-for-1","slug":"x-vector-based-voice-activity-detection-for-1","title":"X-Vector based voice activity detection for multi-genre broadcast speech-to-text","date":"2021-12-09","arxiv_id":"2112.05016","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pretraining-with","slug":"self-supervised-pretraining-with","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","date":"2021-11-26","arxiv_id":"2111.13675","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-supervised-pretraining-with#ran","syntology_url":"https://syntology.ai/paper/2111.13675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13675"}},"official":{"repos":["kkahatapitiya/SSDet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/avaspeech-smad-a-strongly-labelled-speech-and","slug":"avaspeech-smad-a-strongly-labelled-speech-and","title":"AVASpeech-SMAD: A Strongly Labelled Speech and Music Activity Detection Dataset with Label Co-Occurrence","date":"2021-11-02","arxiv_id":"2111.01320","repositories_listed":1,"syntology":null},{"url":"/paper/activity-recognition-for-autism-diagnosis","slug":"activity-recognition-for-autism-diagnosis","title":"Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study","date":"2021-08-18","arxiv_id":"2108.07917","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-classroom-activity-detection","slug":"fine-grained-classroom-activity-detection","title":"Fine-Grained Classroom Activity Detection from Audio with Neural Networks","date":"2021-07-29","arxiv_id":"2107.14369","repositories_listed":1,"syntology":null},{"url":"/paper/wase-learning-when-to-attend-for-speaker","slug":"wase-learning-when-to-attend-for-speaker","title":"WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments","date":"2021-06-13","arxiv_id":"2106.07016","repositories_listed":1,"syntology":null},{"url":"/paper/learning-spectro-temporal-representations-of","slug":"learning-spectro-temporal-representations-of","title":"Learning spectro-temporal representations of complex sounds with parameterized neural networks","date":"2021-03-12","arxiv_id":"2103.07125","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-cnn-bilstm-voice-activity-detector","slug":"a-hybrid-cnn-bilstm-voice-activity-detector","title":"A Hybrid CNN-BiLSTM Voice Activity Detector","date":"2021-03-05","arxiv_id":"2103.03529","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-fine-networks-for-temporal-activity","slug":"coarse-fine-networks-for-temporal-activity","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","date":"2021-03-01","arxiv_id":"2103.01302","repositories_listed":1,"syntology":null},{"url":"/paper/av-taris-online-audio-visual-speech","slug":"av-taris-online-audio-visual-speech","title":"AV Taris: Online Audio-Visual Speech Recognition","date":"2020-12-14","arxiv_id":"2012.07467","repositories_listed":1,"syntology":null},{"url":"/paper/toyota-smarthome-untrimmed-real-world","slug":"toyota-smarthome-untrimmed-real-world","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","date":"2020-10-28","arxiv_id":"2010.14982","repositories_listed":1,"syntology":null},{"url":"/paper/respvad-voice-activity-detection-via-video","slug":"respvad-voice-activity-detection-via-video","title":"RespVAD: Voice Activity Detection via Video-Extracted Respiration Patterns","date":"2020-08-21","arxiv_id":"2008.09466","repositories_listed":1,"syntology":null},{"url":"/paper/audino-a-modern-annotation-tool-for-audio-and","slug":"audino-a-modern-annotation-tool-for-audio-and","title":"audino: A Modern Annotation Tool for Audio and Speech","date":"2020-06-09","arxiv_id":"2006.05236","repositories_listed":1,"syntology":null},{"url":"/paper/dual-attention-in-time-and-frequency-domain","slug":"dual-attention-in-time-and-frequency-domain","title":"Dual Attention in Time and Frequency Domain for Voice Activity Detection","date":"2020-03-27","arxiv_id":"2003.12266","repositories_listed":1,"syntology":null},{"url":"/paper/argus-efficient-activity-detection-system-for","slug":"argus-efficient-activity-detection-system-for","title":"Argus: Efficient Activity Detection System for Extended Video Analysis","date":"2020-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/personalized-activity-recognition-with-deep","slug":"personalized-activity-recognition-with-deep","title":"Personalized Activity Recognition with Deep Triplet Embeddings","date":"2020-01-15","arxiv_id":"2001.05517","repositories_listed":1,"syntology":null},{"url":"/paper/the-second-dihard-diarization-challenge","slug":"the-second-dihard-diarization-challenge","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","date":"2019-06-18","arxiv_id":"1906.07839","repositories_listed":1,"syntology":null},{"url":"/paper/structure-aware-convolutional-neural-networks","slug":"structure-aware-convolutional-neural-networks","title":"Structure-Aware Convolutional Neural Networks","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/s3d-single-shot-multi-span-detector-via-fully","slug":"s3d-single-shot-multi-span-detector-via-fully","title":"S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks","date":"2018-07-21","arxiv_id":"1807.08069","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-gaussian-mixture-layer-for-videos","slug":"temporal-gaussian-mixture-layer-for-videos","title":"Temporal Gaussian Mixture Layer for Videos","date":"2018-03-16","arxiv_id":"1803.06316","repositories_listed":1,"syntology":null},{"url":"/paper/a-convolutional-neural-network-smartphone-app","slug":"a-convolutional-neural-network-smartphone-app","title":"A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection","date":"2018-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/protest-activity-detection-and-perceived","slug":"protest-activity-detection-and-perceived","title":"Protest Activity Detection and Perceived Violence Estimation from Social Media Images","date":"2017-09-18","arxiv_id":"1709.06204","repositories_listed":1,"syntology":null},{"url":"/paper/a-pursuit-of-temporal-accuracy-in-general","slug":"a-pursuit-of-temporal-accuracy-in-general","title":"A Pursuit of Temporal Accuracy in General Activity Detection","date":"2017-03-08","arxiv_id":"1703.02716","repositories_listed":1,"syntology":null},{"url":"/paper/untrimmed-video-classification-for-activity","slug":"untrimmed-video-classification-for-activity","title":"Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge","date":"2016-07-07","arxiv_id":"1607.01979","repositories_listed":1,"syntology":null},{"url":"/paper/activitynet-a-large-scale-video-benchmark-for","slug":"activitynet-a-large-scale-video-benchmark-for","title":"ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding","date":"2015-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unstructured-human-activity-detection-from","slug":"unstructured-human-activity-detection-from","title":"Unstructured Human Activity Detection from RGBD Images","date":"2012-06-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"cbf-afa-chunk-based-multi-ssl-fusion-for","title":"CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment","date":"2025-06-25","arxiv_id":"2506.20243","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-activity-detection-for-cell-free","title":"Distributed Activity Detection for Cell-Free Hybrid Near-Far Field Communications","date":"2025-06-17","arxiv_id":"2506.14254","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-is-not-always-the-answer-optimizing","title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","date":"2025-06-02","arxiv_id":"2506.01365","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-detection-and-channel-5","title":"Joint Activity Detection and Channel Estimation for Massive Connectivity: Where Message Passing Meets Score-Based Generative Priors","date":"2025-05-31","arxiv_id":"2506.00581","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-overlapping-speech-detection-a","title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","date":"2025-05-29","arxiv_id":"2505.23207","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-activity-detection-for-massive-random","title":"Robust Activity Detection for Massive Random Access","date":"2025-05-21","arxiv_id":"2505.15555","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-endpoint-detection-in-end-to-end","title":"Improving endpoint detection in end-to-end streaming ASR for conversational speech","date":"2025-05-19","arxiv_id":"2505.17070","repositories_listed":0,"syntology":null},{"url":null,"slug":"micronas-an-automated-framework-for","title":"MicroNAS: An Automated Framework for Developing a Fall Detection System","date":"2025-04-10","arxiv_id":"2504.07397","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-mle-and-mape-based-device-activity","title":"Fast MLE and MAPE-Based Device Activity Detection for Grant-Free Access via PSCA and PSCA-Net","date":"2025-03-19","arxiv_id":"2503.15259","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-for-secure-and-efficient","title":"Federated Learning for Secure and Efficient Device Activity Detection in mMTC Networks","date":"2025-03-14","arxiv_id":"2503.13513","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-learning-for-grant-free-activity","title":"Lightweight Learning for Grant-Free Activity Detection in Cell-Free Massive MIMO Networks","date":"2025-03-14","arxiv_id":"2503.11305","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-learning-based-sparse-recovery-for","title":"Robust Learning-Based Sparse Recovery for Device Activity Detection in Grant-Free Random Access Cell-Free Massive MIMO: Enhancing Resilience to Impairments","date":"2025-03-13","arxiv_id":"2503.10280","repositories_listed":0,"syntology":null},{"url":null,"slug":"caddi-an-in-class-activity-detection-dataset","title":"CADDI: An in-Class Activity Detection Dataset using IMU data from low-cost sensors","date":"2025-03-04","arxiv_id":"2503.02853","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-experts-augmented-deep-unfolding","title":"Mixture of Experts-augmented Deep Unfolding for Activity Detection in IRS-aided Systems","date":"2025-02-27","arxiv_id":"2502.20183","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-ecc-vulnerabilities-lstm-networks","title":"Unveiling ECC Vulnerabilities: LSTM Networks for Operation Recognition in Side-Channel Attacks","date":"2025-02-24","arxiv_id":"2502.17330","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexduo-a-pluggable-system-for-enabling-full","title":"FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems","date":"2025-02-19","arxiv_id":"2502.13472","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-enhanced-dialogue-management-for-full","title":"LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems","date":"2025-02-19","arxiv_id":"2502.14145","repositories_listed":0,"syntology":null},{"url":null,"slug":"dt4ecg-a-dual-task-learning-framework-for-ecg","title":"DT4ECG: A Dual-Task Learning Framework for ECG-Based Human Identity Recognition and Human Activity Detection","date":"2025-02-16","arxiv_id":"2502.11023","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-power-of-complex-valued","title":"Unveiling the Power of Complex-Valued Transformers in Wireless Communications","date":"2025-02-16","arxiv_id":"2502.11151","repositories_listed":0,"syntology":null},{"url":null,"slug":"microphone-array-geometry-independent-multi","title":"Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge","date":"2025-02-14","arxiv_id":"2502.09859","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-speaker-embedding-free-target","title":"Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection","date":"2025-01-07","arxiv_id":"2501.03612","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-robust-target-speaker-voice-activity","title":"Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining","date":"2025-01-06","arxiv_id":"2501.03184","repositories_listed":0,"syntology":null},{"url":null,"slug":"fotheidil-an-automatic-transcription-system","title":"Fotheidil: an Automatic Transcription System for the Irish Language","date":"2024-12-31","arxiv_id":"2501.00509","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-deep-learning-4","title":"Comparative Analysis of Deep Learning Approaches for Harmful Brain Activity Detection Using EEG","date":"2024-12-10","arxiv_id":"2412.07878","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-random-access-in-massive-mimo","title":"Asynchronous Random Access in Massive MIMO Systems Facilitated by the Delay-Angle Domain","date":"2024-12-06","arxiv_id":"2412.04841","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":5,"papers_where_code_ran_first_page":"/task/activity-detection/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":4,"url":"/task/activity-detection/papers/2","json":"/task/activity-detection/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/activity-detection/papers/3","json":"/task/activity-detection/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/activity-detection/papers/4","json":"/task/activity-detection/papers/4.json","rows":80},{"order":"ran","page":1,"of":1,"url":"/task/activity-detection/papers/ran/1","json":"/task/activity-detection/papers/ran/1.json","rows":5}],"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":"3c075d39c7f1bedb2fbfc6976925777c8450b86e48e2785c7e57bbb93588c0d1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}