{"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/papers/4","list_of":"/task/activity-detection","task":"Activity Detection","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":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,380],"of":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"},"first_page":"/task/activity-detection","prev":"/task/activity-detection/papers/3","next":null,"papers":[{"url":null,"slug":"towards-end-2-end-learning-for-predicting","title":"Towards end-2-end learning for predicting behavior codes from spoken utterances in psychotherapy conversations","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-jhu-multi-microphone-multi-speaker-asr","title":"The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge","date":"2020-06-14","arxiv_id":"2006.07898","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-optimization-for-massive","title":"Distributed Optimization for Massive Connectivity","date":"2020-06-10","arxiv_id":"2006.05637","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-and-posture-classification-using","title":"Speaker and Posture Classification using Instantaneous Intraspeech Breathing Features","date":"2020-05-25","arxiv_id":"2005.12230","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-radar-based-gesture-detection-and","title":"Real-Time Radar-Based Gesture Detection and Recognition Built in an Edge-Computing Platform","date":"2020-05-20","arxiv_id":"2005.10145","repositories_listed":0,"syntology":null},{"url":null,"slug":"siamese-neural-networks-for-class-activity","title":"Siamese Neural Networks for Class Activity Detection","date":"2020-05-15","arxiv_id":"2005.07549","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-voice-activity-detection-a","title":"Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario","date":"2020-05-14","arxiv_id":"2005.07272","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-network-for-noise-robust-keyword","title":"Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention","date":"2020-05-08","arxiv_id":"2005.03867","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-event-segmentation-using-attention","title":"Spatio-Temporal Event Segmentation and Localization for Wildlife Extended Videos","date":"2020-05-05","arxiv_id":"2005.02463","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five-1","title":"Semi-supervised Acoustic Modelling for Five-lingual Code-switched ASR using Automatically-segmented Soap Opera Speech","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-safe-t-corpus-a-new-resource-for","title":"The SAFE-T Corpus: A New Resource for Simulated Public Safety Communications","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-from-wearable","title":"Activity Detection from Wearable Electromyogram Sensors using Hidden Markov Model","date":"2020-04-27","arxiv_id":"2005.00107","repositories_listed":0,"syntology":null},{"url":null,"slug":"gabriella-an-online-system-for-real-time","title":"Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos","date":"2020-04-23","arxiv_id":"2004.11475","repositories_listed":0,"syntology":null},{"url":null,"slug":"group-activity-detection-from-trajectory-and","title":"Group Activity Detection from Trajectory and Video Data in Soccer","date":"2020-04-21","arxiv_id":"2004.10299","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five","title":"Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech","date":"2020-04-08","arxiv_id":"2004.06480","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporarily-aware-context-modelling-using","title":"Temporarily-Aware Context Modelling using Generative Adversarial Networks for Speech Activity Detection","date":"2020-04-02","arxiv_id":"2004.01546","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-few-shot-activity-detection-with","title":"Revisiting Few-shot Activity Detection with Class Similarity Control","date":"2020-03-31","arxiv_id":"2004.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"zstad-zero-shot-temporal-activity-detection","title":"ZSTAD: Zero-Shot Temporal Activity Detection","date":"2020-03-12","arxiv_id":"2003.05583","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossmodal-learning-for-audio-visual-speech","title":"Cross modal video representations for weakly supervised active speaker localization","date":"2020-03-09","arxiv_id":"2003.04358","repositories_listed":0,"syntology":null},{"url":null,"slug":"dihard-ii-is-still-hard-experimental-results","title":"DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team","date":"2020-02-23","arxiv_id":"2002.12761","repositories_listed":0,"syntology":null},{"url":"/paper/3d-resnet-with-ranking-loss-function-for","slug":"3d-resnet-with-ranking-loss-function-for","title":"3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos","date":"2020-02-04","arxiv_id":"2002.01132","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-automatic-speech-recognition","title":"End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection","date":"2020-02-03","arxiv_id":"2002.00551","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-activity-and-data-detection-in-massive","title":"Faster Activity and Data Detection in Massive Random Access: A Multi-armed Bandit Approach","date":"2020-01-28","arxiv_id":"2001.10237","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-point-detection-with-state-transition","title":"End-Point Detection with State Transition Model based on Chunk-Wise Classification","date":"2019-12-22","arxiv_id":"1912.10442","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-recognition-of-complex-action","title":"DASZL: Dynamic Action Signatures for Zero-shot Learning","date":"2019-12-08","arxiv_id":"1912.03613","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-reflecting-surface-for-massive","title":"Intelligent Reflecting Surface for Massive Device Connectivity: Joint Activity Detection and Channel Estimation","date":"2019-11-12","arxiv_id":"1911.12157","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-speed-submission-to-dihard-ii","title":"The Speed Submission to DIHARD II: Contributions & Lessons Learned","date":"2019-11-06","arxiv_id":"1911.02388","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bin-encoding-training-of-a-spiking-neural","title":"A Bin Encoding Training of a Spiking Neural Network-based Voice Activity Detection","date":"2019-10-28","arxiv_id":"1910.12459","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-learning-for-classroom-activity","title":"Multimodal Learning For Classroom Activity Detection","date":"2019-10-22","arxiv_id":"1910.13799","repositories_listed":0,"syntology":null},{"url":null,"slug":"spiking-neural-networks-trained-with","title":"Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection","date":"2019-10-22","arxiv_id":"1910.09993","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-adaptive-soft-voice-activity-detection","title":"Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification","date":"2019-09-26","arxiv_id":"1909.11886","repositories_listed":0,"syntology":null},{"url":"/paper/multi-timescale-trajectory-prediction-for","slug":"multi-timescale-trajectory-prediction-for","title":"Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection","date":"2019-08-12","arxiv_id":"1908.04321","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-self-supervised-learning-for-human","title":"Multi-task Self-Supervised Learning for Human Activity Detection","date":"2019-07-27","arxiv_id":"1907.11879","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-acoustic-emission-activity-detection","title":"An Acoustic Emission Activity Detection Method based on Short-Term Waveform Features: Application to Metallic Components under Uniaxial Tensile Test","date":"2019-06-26","arxiv_id":"1906.10956","repositories_listed":0,"syntology":null},{"url":null,"slug":"vireojd-mm-at-activity-detection-in-extended","title":"vireoJD-MM at Activity Detection in Extended Videos","date":"2019-06-20","arxiv_id":"1906.08547","repositories_listed":0,"syntology":null},{"url":"/paper/two-stream-region-convolutional-3d-network","slug":"two-stream-region-convolutional-3d-network","title":"Two-Stream Region Convolutional 3D Network for Temporal Activity Detection","date":"2019-06-05","arxiv_id":"1906.02182","repositories_listed":0,"syntology":null},{"url":null,"slug":"follow-the-attention-combining-partial-pose","title":"Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection","date":"2019-05-11","arxiv_id":"1905.04430","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ensemble-svm-based-approach-for-voice","title":"An Ensemble SVM-based Approach for Voice Activity Detection","date":"2019-02-05","arxiv_id":"1902.01544","repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-r-c3d-for-few-shot-temporal","title":"Similarity R-C3D for Few-shot Temporal Activity Detection","date":"2018-12-25","arxiv_id":"1812.10000","repositories_listed":0,"syntology":null},{"url":null,"slug":"tri-axial-self-attention-for-concurrent","title":"Tri-axial Self-Attention for Concurrent Activity Recognition","date":"2018-12-06","arxiv_id":"1812.02817","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-graph-approach-for-detection-of","title":"Computational Graph Approach for Detection of Composite Human Activities","date":"2018-12-05","arxiv_id":"1812.01895","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-block-based-compressed-sensing","title":"Sequence Block based Compressed Sensing Multiuser Detection for 5G","date":"2018-09-28","arxiv_id":"1809.10450","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-audiovisual-speech-activity","title":"End-to-end Audiovisual Speech Activity Detection with Bimodal Recurrent Neural Models","date":"2018-09-12","arxiv_id":"1809.04553","repositories_listed":0,"syntology":null},{"url":null,"slug":"aad-adaptive-anomaly-detection-through","title":"AAD: Adaptive Anomaly Detection through traffic surveillance videos","date":"2018-08-29","arxiv_id":"1808.10044","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-temporal-pyramid-network-a-closer","title":"Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection","date":"2018-08-07","arxiv_id":"1808.02536","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfternet-towards-2-bit-dynamic-fusion","title":"DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition","date":"2018-07-31","arxiv_id":"1808.04228","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-detection-from-a-robot-car-perspective","title":"Action Detection from a Robot-Car Perspective","date":"2018-07-30","arxiv_id":"1807.11332","repositories_listed":0,"syntology":null},{"url":null,"slug":"pm-gans-discriminative-representation","title":"PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities","date":"2018-04-17","arxiv_id":"1804.06248","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-detecting-and-separating-singing","title":"Jointly Detecting and Separating Singing Voice: A Multi-Task Approach","date":"2018-04-05","arxiv_id":"1804.01650","repositories_listed":0,"syntology":null},{"url":null,"slug":"c3po-database-and-benchmark-for-early-stage","title":"C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing","date":"2018-03-20","arxiv_id":"1803.07544","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-domain-trinicon-based-blind-source","title":"Frequency domain TRINICON-based blind source separation method with multi-source activity detection for sparsely mixed signals","date":"2018-02-25","arxiv_id":"1802.09005","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-morphing-kernel-regression-for","title":"Spatial Morphing Kernel Regression For Feature Interpolation","date":"2018-02-21","arxiv_id":"1802.07452","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-multi-scale-region-convolutional","title":"Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection","date":"2018-01-28","arxiv_id":"1801.09184","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-binary-neural-network-learning","title":"Recursive Binary Neural Network Learning Model with 2-bit/weight Storage Requirement","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"overcomplete-frame-thresholding-for-acoustic","title":"Overcomplete Frame Thresholding for Acoustic Scene Analysis","date":"2017-12-25","arxiv_id":"1712.09117","repositories_listed":0,"syntology":null},{"url":null,"slug":"budget-aware-activity-detection-with-a","title":"Budget-Aware Activity Detection with A Recurrent Policy Network","date":"2017-11-30","arxiv_id":"1712.00097","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-nonparametric-model-for-multimodal","title":"A Nonparametric Model for Multimodal Collaborative Activities Summarization","date":"2017-09-04","arxiv_id":"1709.01077","repositories_listed":0,"syntology":null},{"url":null,"slug":"budget-aware-deep-semantic-video-segmentation","title":"Budget-Aware Deep Semantic Video Segmentation","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"polish-read-speech-corpus-for-speech-tools","title":"Polish Read Speech Corpus for Speech Tools and Services","date":"2017-06-01","arxiv_id":"1706.00245","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-activity-detection-in-untrimmed","title":"Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search","date":"2016-07-11","arxiv_id":"1607.02815","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-temporal-activity-proposals-for","title":"Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-activity-progression-in-lstms-for","title":"Learning Activity Progression in LSTMs for Activity Detection and Early Detection","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-based-sensor-fusion-with-application","title":"Kernel-based Sensor Fusion with Application to Audio-Visual Voice Activity Detection","date":"2016-04-11","arxiv_id":"1604.02946","repositories_listed":0,"syntology":null},{"url":null,"slug":"leaving-some-stones-unturned-dynamic-feature","title":"Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video","date":"2016-04-01","arxiv_id":"1604.00427","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-supervision-for-learning-active","title":"Cross-modal Supervision for Learning Active Speaker Detection in Video","date":"2016-03-29","arxiv_id":"1603.08907","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-optical-flow-using-dense-inverse-search","title":"Fast Optical Flow using Dense Inverse Search","date":"2016-03-11","arxiv_id":"1603.03590","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-machine-learning-techniques-in","title":"Application of Machine Learning Techniques in Human Activity Recognition","date":"2015-10-19","arxiv_id":"1510.05577","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensor-vs-matrix-methods-robust-tensor","title":"Tensor vs Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations","date":"2015-10-15","arxiv_id":"1510.04747","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-anomaly-detection-via-class-imbalance","title":"Online Anomaly Detection via Class-Imbalance Learning","date":"2015-08-27","arxiv_id":"1508.06717","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-based-saliency-detection-for-videos","title":"Encoding Based Saliency Detection for Videos and Images","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"group-event-detection-with-a-varying-number","title":"Group Event Detection with a Varying Number of Group Members for Video Surveillance","date":"2015-02-28","arxiv_id":"1503.00082","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-network-based-algorithm-for-human","title":"A new network-based algorithm for human activity recognition in video","date":"2015-02-21","arxiv_id":"1502.06075","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-recent-advances-of-computer","title":"A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video","date":"2015-01-12","arxiv_id":"1501.02825","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-activity-detection-using-temporal","title":"Voice Activity Detection using Temporal Characteristics of Autocorrelation Lag and Maximum Spectral Amplitude in Sub-bands","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/gtts-ehu-systems-for-quesst-at-mediaeval-2014","slug":"gtts-ehu-systems-for-quesst-at-mediaeval-2014","title":"GTTS-EHU Systems for QUESST at MediaEval 2014","date":"2014-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rats-collection-supporting-hlt-research","title":"The RATS Collection: Supporting HLT Research with Degraded Audio Data","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"indoor-activity-detection-and-recognition-for","title":"Indoor Activity Detection and Recognition for Sport Games Analysis","date":"2014-04-25","arxiv_id":"1404.6413","repositories_listed":0,"syntology":null},{"url":null,"slug":"union-of-low-rank-subspaces-detector","title":"Union of Low-Rank Subspaces Detector","date":"2013-07-29","arxiv_id":"1307.7521","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-independent-continuous-speech-to-text","title":"Speaker Independent Continuous Speech to Text Converter for Mobile Application","date":"2013-07-19","arxiv_id":"1307.5736","repositories_listed":0,"syntology":null},{"url":"/paper/learning-spatio-temporal-structure-from-rgb-d","slug":"learning-spatio-temporal-structure-from-rgb-d","title":"Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Anticipation","date":"2013-02-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"3a507035a07256642888c9c074178375ef8adfe1be4593a8647ae70eb8e1bbcd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}