{"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/action-detection/papers/7","list_of":"/task/action-detection","task":"Action 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":7,"pages_in_order":9,"rows_per_page":100,"rows":[601,700],"of":817,"counts":{"archive_papers_tagged":817,"with_a_code_link":277,"where_syntology_ran_a_sample":53,"not_listed_spam_title":0,"listed":817,"listed_where_code_ran":53,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":46,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":46,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/action-detection","prev":"/task/action-detection/papers/6","next":"/task/action-detection/papers/8","papers":[{"url":"/paper/meva-a-large-scale-multiview-multimodal-video","slug":"meva-a-large-scale-multiview-multimodal-video","title":"MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection","date":"2020-12-02","arxiv_id":"2012.00914","repositories_listed":0,"syntology":null},{"url":null,"slug":"nudge-accelerating-overdue-pull-requests","title":"Nudge: Accelerating Overdue Pull Requests Towards Completion","date":"2020-11-25","arxiv_id":"2011.12468","repositories_listed":0,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language","slug":"voxlingua107-a-dataset-for-spoken-language","title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","date":"2020-11-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-detection-with-multi-level","title":"Temporal Action Detection with Multi-level Supervision","date":"2020-11-24","arxiv_id":"2011.11893","repositories_listed":0,"syntology":null},{"url":"/paper/privileged-knowledge-distillation-for-online","slug":"privileged-knowledge-distillation-for-online","title":"Privileged Knowledge Distillation for Online Action Detection","date":"2020-11-18","arxiv_id":"2011.09158","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-time-frequency-based-suspicious-activity","title":"A Time-Frequency based Suspicious Activity Detection for Anti-Money Laundering","date":"2020-11-17","arxiv_id":"2011.08492","repositories_listed":0,"syntology":null},{"url":null,"slug":"lap-net-adaptive-features-sampling-via","title":"LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection","date":"2020-11-16","arxiv_id":"2011.07915","repositories_listed":0,"syntology":null},{"url":null,"slug":"salad-self-assessment-learning-for-action","title":"SALAD: Self-Assessment Learning for Action Detection","date":"2020-11-13","arxiv_id":"2011.06958","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-and-modeling-using-smart","title":"Activity Detection And Modeling Using Smart Meter Data: Concept And Case Studies","date":"2020-10-26","arxiv_id":"2010.13288","repositories_listed":0,"syntology":null},{"url":null,"slug":"marblenet-deep-1d-time-channel-separable","title":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","date":"2020-10-26","arxiv_id":"2010.13886","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-multi-channel-features-for-speaker","title":"Multi-Channel Speaker Verification for Single and Multi-talker Speech","date":"2020-10-23","arxiv_id":"2010.12692","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-aided-end-to-end-multi","title":"Speech enhancement aided end-to-end multi-task learning for voice activity detection","date":"2020-10-23","arxiv_id":"2010.12484","repositories_listed":0,"syntology":null},{"url":null,"slug":"combination-of-deep-speaker-embeddings-for","title":"Combination of Deep Speaker Embeddings for Diarisation","date":"2020-10-22","arxiv_id":"2010.12025","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-huawei-speaker-diarisation-system-for-the","title":"The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker Diarisation Challenge","date":"2020-10-22","arxiv_id":"2010.11657","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-algorithm-for-device-detection","title":"An Efficient Algorithm for Device Detection and Channel Estimation in Asynchronous IoT Systems","date":"2020-10-20","arxiv_id":"2010.09979","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-two-stream-multi-feature-network-for","title":"Robust Two-Stream Multi-Feature Network for Driver Drowsiness Detection","date":"2020-10-13","arxiv_id":"2010.06235","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sound-of-silence-in-eeg-cognitive-voice","title":"The \"Sound of Silence\" in EEG -- Cognitive voice activity detection","date":"2020-10-12","arxiv_id":"2010.05497","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-deep-learning-framework-for-short","title":"A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments","date":"2020-10-06","arxiv_id":"2010.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-action-detection-in-streaming-videos","title":"Online Action Detection in Streaming Videos with Time Buffers","date":"2020-10-06","arxiv_id":"2010.03016","repositories_listed":0,"syntology":null},{"url":null,"slug":"grant-free-access-via-bilinear-inference-for","title":"Grant-Free Access via Bilinear Inference for Cell-Free MIMO with Low-Coherent Pilots","date":"2020-09-27","arxiv_id":"2009.12863","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-voice-activity-detection-with","title":"Learning Visual Voice Activity Detection with an Automatically Annotated Dataset","date":"2020-09-23","arxiv_id":"2009.11204","repositories_listed":0,"syntology":null},{"url":null,"slug":"trecvid-2019-an-evaluation-campaign-to","title":"TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & Retrieval","date":"2020-09-21","arxiv_id":"2009.09984","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multitask-loss-function-for-audio-event","title":"On Multitask Loss Function for Audio Event Detection and Localization","date":"2020-09-11","arxiv_id":"2009.05527","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-machine-type-communication-pilot","title":"Massive Machine Type Communication Pilot-Hopping Sequence Detection Architectures Based on Non-Negative Least Squares for Grant-Free Random Access","date":"2020-09-04","arxiv_id":"2009.02089","repositories_listed":0,"syntology":null},{"url":"/paper/finding-action-tubes-with-a-sparse-to-dense","slug":"finding-action-tubes-with-a-sparse-to-dense","title":"Finding Action Tubes with a Sparse-to-Dense Framework","date":"2020-08-30","arxiv_id":"2008.13196","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfad-coarse-to-fine-action-detector-for","title":"CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization","date":"2020-08-19","arxiv_id":"2008.08332","repositories_listed":0,"syntology":null},{"url":null,"slug":"segcodenet-color-coded-segmentation-masks-for","title":"SegCodeNet: Color-Coded Segmentation Masks for Activity Detection from Wearable Cameras","date":"2020-08-19","arxiv_id":"2008.08452","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlnet-an-adaptive-multiple-receptive-field","title":"MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection","date":"2020-08-13","arxiv_id":"2008.05650","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-temporal-pyramid-network-for","title":"Multi-Level Temporal Pyramid Network for Action Detection","date":"2020-08-07","arxiv_id":"2008.03270","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-sparse-signal-recovery-and-support","title":"Jointly Sparse Signal Recovery and Support Recovery via Deep Learning with Applications in MIMO-based Grant-Free Random Access","date":"2020-08-05","arxiv_id":"2008.01992","repositories_listed":0,"syntology":null},{"url":"/paper/boundary-content-graph-neural-network-for","slug":"boundary-content-graph-neural-network-for","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","date":"2020-08-04","arxiv_id":"2008.01432","repositories_listed":0,"syntology":null},{"url":null,"slug":"this-is-houston-say-again-please-the-behavox","title":"\"This is Houston. Say again, please\". The Behavox system for the Apollo-11 Fearless Steps Challenge (phase II)","date":"2020-08-04","arxiv_id":"2008.01504","repositories_listed":0,"syntology":null},{"url":"/paper/towards-efficient-coarse-to-fine-networks-for","slug":"towards-efficient-coarse-to-fine-networks-for","title":"Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-and-neural-network-based-speech","title":"Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments","date":"2020-07-28","arxiv_id":"2005.09913","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-weakly-supervised-action","title":"Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos","date":"2020-07-21","arxiv_id":"2007.10703","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-afrl-iwslt-2020-systems-work-from-home","title":"The AFRL IWSLT 2020 Systems: Work-From-Home Edition","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"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":"esad-endoscopic-surgeon-action-detection","title":"ESAD: Endoscopic Surgeon Action Detection Dataset","date":"2020-06-12","arxiv_id":"2006.07164","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":"/paper/woad-weakly-supervised-online-action","slug":"woad-weakly-supervised-online-action","title":"WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos","date":"2020-06-05","arxiv_id":"2006.03732","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":"taen-temporal-aware-embedding-network-for-few","title":"TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition","date":"2020-04-21","arxiv_id":"2004.10141","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionspotter-deep-reinforcement-learning","title":"ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos","date":"2020-04-15","arxiv_id":"2004.06971","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":"progressive-boundary-refinement-network-for","title":"Progressive Boundary Refinement Network for Temporal Action Detection","date":"2020-04-03","arxiv_id":null,"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":"spatio-temporal-action-detection-with-multi","title":"Spatio-Temporal Action Detection with Multi-Object Interaction","date":"2020-04-01","arxiv_id":"2004.00180","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-short-term-relation-networks-for-video","title":"Long Short-Term Relation Networks for Video Action Detection","date":"2020-03-31","arxiv_id":"2003.14065","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":"comprehensive-instructional-video-analysis","title":"Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation","date":"2020-03-20","arxiv_id":"2003.09392","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-online-action-detection-framework","title":"A Novel Online Action Detection Framework from Untrimmed Video Streams","date":"2020-03-17","arxiv_id":"2003.07734","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":"srg-snippet-relatedness-based-temporal-action","title":"SRG: Snippet Relatedness-based Temporal Action Proposal Generator","date":"2019-11-26","arxiv_id":"1911.11306","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-learning-and-execution-of-collaborative","title":"Zero-Shot Imitating Collaborative Manipulation Plans from YouTube Cooking Videos","date":"2019-11-25","arxiv_id":"1911.10686","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":"191104469","title":"A Proposed Artificial intelligence Model for Real-Time Human Action Localization and Tracking","date":"2019-11-09","arxiv_id":"1911.04469","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":"afo-tad-anchor-free-one-stage-detector-for","title":"AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection","date":"2019-10-18","arxiv_id":"1910.08250","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-temporal-action-proposals-with-fewer","title":"Learning Temporal Action Proposals With Fewer Labels","date":"2019-10-03","arxiv_id":"1910.01286","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-self-attention-network-for","slug":"hierarchical-self-attention-network-for","title":"Hierarchical Self-Attention Network for Action Localization in Videos","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/temporal-structure-mining-for-weakly","slug":"temporal-structure-mining-for-weakly","title":"Temporal Structure Mining for Weakly Supervised Action Detection","date":"2019-10-01","arxiv_id":null,"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":null,"slug":"computer-aided-automated-detection-of-gene","title":"Computer-Aided Automated Detection of Gene-Controlled Social Actions of Drosophila","date":"2019-09-11","arxiv_id":"1909.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stream-single-shot-spatial-temporal","title":"Multi-Stream Single Shot Spatial-Temporal Action Detection","date":"2019-08-22","arxiv_id":"1908.08178","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":"adversarial-seeded-sequence-growing-for","title":"Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization","date":"2019-08-07","arxiv_id":"1908.02422","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":"a-novel-approach-for-robust-multi-human","title":"A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks","date":"2019-07-25","arxiv_id":"1907.11272","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-filtering-for-multi-person","title":"Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures","date":"2019-07-21","arxiv_id":"1907.12919","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-deep-neural-network-applied-to","title":"An end-to-end (deep) neural network applied to raw EEG, fNIRs and body motion data for data fusion and BCI classification task without any pre-/post-processing","date":"2019-07-17","arxiv_id":"1907.09523","repositories_listed":0,"syntology":null},{"url":null,"slug":"deformable-tube-network-for-action-detection","title":"Deformable Tube Network for Action Detection in Videos","date":"2019-07-03","arxiv_id":"1907.01847","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":null,"slug":"improving-temporal-action-proposal-generation","title":"Accelerating temporal action proposal generation via high performance computing","date":"2019-06-15","arxiv_id":"1906.06496","repositories_listed":0,"syntology":null},{"url":"/paper/learning-spatio-temporal-representation-with-3","slug":"learning-spatio-temporal-representation-with-3","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","date":"2019-06-13","arxiv_id":"1906.05571","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":"language-driven-temporal-activity","title":"Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/tacnet-transition-aware-context-network-for-1","slug":"tacnet-transition-aware-context-network-for-1","title":"TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection","date":"2019-05-31","arxiv_id":"1905.13417","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-action-localization-by-progressive-1","title":"Improving Action Localization by Progressive Cross-stream Cooperation","date":"2019-05-28","arxiv_id":"1905.11575","repositories_listed":0,"syntology":null}],"record_sha256":"f4ec90981bc1254eb6582715a17dab23ed560b3662e07c683da27057e3b981c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}