{"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/5","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":5,"pages_in_order":9,"rows_per_page":100,"rows":[401,500],"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/4","next":"/task/action-detection/papers/6","papers":[{"url":null,"slug":"potloc-pseudo-label-oriented-transformer-for","title":"POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization","date":"2023-10-20","arxiv_id":"2310.13585","repositories_listed":0,"syntology":null},{"url":null,"slug":"property-aware-multi-speaker-data-simulation","title":"Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation","date":"2023-10-18","arxiv_id":"2310.12371","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-mtc-user-activity-detection-and","title":"Hierarchical MTC User Activity Detection and Channel Estimation with Unknown Spatial Covariance","date":"2023-10-16","arxiv_id":"2310.10204","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-online-speaker-diarization-with","title":"End-to-end Online Speaker Diarization with Target Speaker Tracking","date":"2023-10-12","arxiv_id":"2310.08696","repositories_listed":0,"syntology":null},{"url":null,"slug":"vsanet-real-time-speech-enhancement-based-on","title":"VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention","date":"2023-10-11","arxiv_id":"2310.07295","repositories_listed":0,"syntology":null},{"url":null,"slug":"act-net-anchor-context-action-detection-in","title":"ACT-Net: Anchor-context Action Detection in Surgery Videos","date":"2023-10-05","arxiv_id":"2310.03377","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-grammatical-compositional-model-for-video","title":"A Grammatical Compositional Model for Video Action Detection","date":"2023-10-04","arxiv_id":"2310.02887","repositories_listed":0,"syntology":null},{"url":null,"slug":"pp-met-a-real-world-personalized-prompt-based","title":"PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System","date":"2023-09-28","arxiv_id":"2309.16247","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-3-3d-learning-3d-priors-using-multi-modal","title":"M$^{3}$3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding","date":"2023-09-26","arxiv_id":"2309.15313","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-silence-on-speech-anti-spoofing","title":"The Impact of Silence on Speech Anti-Spoofing","date":"2023-09-21","arxiv_id":"2309.11827","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeletr-towrads-skeleton-based-action","title":"SkeleTR: Towrads Skeleton-based Action Recognition in the Wild","date":"2023-09-20","arxiv_id":"2309.11445","repositories_listed":0,"syntology":null},{"url":null,"slug":"joadaa-joint-online-action-detection-and","title":"JOADAA: joint online action detection and action anticipation","date":"2023-09-12","arxiv_id":"2309.06130","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-abnormal-activity-detection-on","title":"Effective Abnormal Activity Detection on Multivariate Time Series Healthcare Data","date":"2023-09-11","arxiv_id":"2309.05845","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-ear-voice-towards-milli-watt-audio","title":"In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms","date":"2023-09-05","arxiv_id":"2309.02393","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-feedback-detr-for-temporal-action","title":"Self-Feedback DETR for Temporal Action Detection","date":"2023-08-21","arxiv_id":"2308.10570","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dku-msxf-diarization-system-for-the","title":"The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023","date":"2023-08-15","arxiv_id":"2308.07595","repositories_listed":0,"syntology":null},{"url":"/paper/pat-position-aware-transformer-for-dense","slug":"pat-position-aware-transformer-for-dense","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","date":"2023-08-09","arxiv_id":"2308.05051","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-learning-based-spatio","title":"A Survey on Deep Learning-based Spatio-temporal Action Detection","date":"2023-08-03","arxiv_id":"2308.01618","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-system-for-the-detection-and","title":"An enhanced system for the detection and active cancellation of snoring signals","date":"2023-07-31","arxiv_id":"2307.16809","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-to-human-interaction-detection","title":"Human-to-Human Interaction Detection","date":"2023-07-02","arxiv_id":"2307.00464","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-microphone-automatic-speech","title":"Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features","date":"2023-06-07","arxiv_id":"2306.04268","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-neurosymbolic-integration-with","title":"Parallel Neurosymbolic Integration with Concordia","date":"2023-06-01","arxiv_id":"2306.00480","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-modal-transformer-network-for-action","title":"A Multi-Modal Transformer Network for Action Detection","date":"2023-05-31","arxiv_id":"2305.19624","repositories_listed":0,"syntology":null},{"url":null,"slug":"svvad-personal-voice-activity-detection-for","title":"SVVAD: Personal Voice Activity Detection for Speaker Verification","date":"2023-05-31","arxiv_id":"2305.19581","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-accurate-low-latency-asr-for","title":"Building Accurate Low Latency ASR for Streaming Voice Search","date":"2023-05-29","arxiv_id":"2305.18596","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-delay-detection-and-channel","title":"Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access","date":"2023-05-21","arxiv_id":"2305.12372","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-vad-low-latency-voice-activity","title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","date":"2023-05-21","arxiv_id":"2305.12450","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-asynchronous-massive-access","title":"Deep Learning for Asynchronous Massive Access with Data Frame Length Diversity","date":"2023-05-12","arxiv_id":"2305.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-activity-detection-and-channel-3","title":"Joint Activity Detection and Channel Estimation for Clustered Massive Machine Type Communications","date":"2023-05-04","arxiv_id":"2305.02935","repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-spatio-temporal-action","slug":"end-to-end-spatio-temporal-action","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","date":"2023-04-24","arxiv_id":"2304.12160","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrsn-multi-relation-support-network-for-video","title":"MRSN: Multi-Relation Support Network for Video Action Detection","date":"2023-04-24","arxiv_id":"2304.11975","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-cell-massive-access-with","title":"Cooperative Multi-Cell Massive Access with Temporally Correlated Activity","date":"2023-04-19","arxiv_id":"2304.09727","repositories_listed":0,"syntology":null},{"url":null,"slug":"array-configuration-agnostic-personal-voice","title":"Array Configuration-Agnostic Personal Voice Activity Detection Based on Spatial Coherence","date":"2023-04-18","arxiv_id":"2304.08887","repositories_listed":0,"syntology":null},{"url":null,"slug":"attach-dataset-annotated-two-handed-assembly","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","date":"2023-04-17","arxiv_id":"2304.08210","repositories_listed":0,"syntology":null},{"url":null,"slug":"grant-free-massive-random-access-with","title":"Grant-free Massive Random Access with Retransmission: Receiver Optimization and Performance Analysis","date":"2023-04-12","arxiv_id":"2304.05648","repositories_listed":0,"syntology":null},{"url":"/paper/improve-temporal-action-proposals-using","slug":"improve-temporal-action-proposals-using","title":"Improve Temporal Action Proposals using Hierarchical Context","date":"2023-04-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"doad-decoupled-one-stage-action-detection","title":"DOAD: Decoupled One Stage Action Detection Network","date":"2023-04-01","arxiv_id":"2304.00254","repositories_listed":0,"syntology":null},{"url":null,"slug":"decomposed-cross-modal-distillation-for-rgb","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","date":"2023-03-30","arxiv_id":"2303.17285","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycleacr-cycle-modeling-of-actor-context","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","date":"2023-03-28","arxiv_id":"2303.16118","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-together-dialogue-separation-and-voice","title":"Better Together: Dialogue Separation and Voice Activity Detection for Audio Personalization in TV","date":"2023-03-23","arxiv_id":"2303.13453","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-integration-of-speech-separation","title":"End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations","date":"2023-03-21","arxiv_id":"2303.12002","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-processing-framework-to-access-large","title":"A processing framework to access large quantities of whispered speech found in ASMR","date":"2023-03-13","arxiv_id":"2303.07442","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-sub-band-network-for-deep-residual","title":"Multi-Task Sub-Band Network For Deep Residual Echo Suppression","date":"2023-03-11","arxiv_id":"2303.06404","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-transformer-based-end-to-end","title":"Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads","date":"2023-03-02","arxiv_id":"2303.01192","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-action-recognition-via-multi-label","title":"Open Set Action Recognition via Multi-Label Evidential Learning","date":"2023-02-27","arxiv_id":"2303.12698","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-frontends-that-do-not-learn","title":"Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation","date":"2023-02-20","arxiv_id":"2302.10014","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-understanding-in-computer-vision-a","title":"Context Understanding in Computer Vision: A Survey","date":"2023-02-10","arxiv_id":"2302.05011","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-policy-and-technical-aspects-of","title":"Understanding Policy and Technical Aspects of AI-Enabled Smart Video Surveillance to Address Public Safety","date":"2023-02-08","arxiv_id":"2302.04310","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-newsbridge-telecom-sudparis-voxceleb","title":"The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description","date":"2023-01-17","arxiv_id":"2301.07491","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-approaches-for-human","title":"Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation","date":"2023-01-13","arxiv_id":"2301.05575","repositories_listed":0,"syntology":null},{"url":null,"slug":"kids-kinematics-based-in-activity-detection","title":"KIDS: kinematics-based (in)activity detection and segmentation in a sleep case study","date":"2023-01-04","arxiv_id":"2301.03469","repositories_listed":0,"syntology":null},{"url":null,"slug":"ego-only-egocentric-action-detection-without","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","date":"2023-01-03","arxiv_id":"2301.01380","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-active-learning-via-deep-clustering","title":"Hybrid Active Learning via Deep Clustering for Video Action Detection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"movement-enhancement-toward-multi-scale-video","title":"Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/skeletr-towards-skeleton-based-action","slug":"skeletr-towards-skeleton-based-action","title":"SkeleTR: Towards Skeleton-based Action Recognition in the Wild","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-detection-for-grant-free-noma-in","title":"Activity Detection for Grant-Free NOMA in Massive IoT Networks","date":"2022-12-23","arxiv_id":"2301.01274","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-temporal-action-detection","title":"Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features","date":"2022-12-20","arxiv_id":"2212.10596","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-cocktail-fork-problem-for","title":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","date":"2022-12-14","arxiv_id":"2212.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-user-linking-is-easier-than-you","title":"Trajectory-User Linking Is Easier Than You Think","date":"2022-12-14","arxiv_id":"2212.07081","repositories_listed":0,"syntology":null},{"url":null,"slug":"bc-vad-a-robust-bone-conduction-voice","title":"BC-VAD: A Robust Bone Conduction Voice Activity Detection","date":"2022-12-06","arxiv_id":"2212.02996","repositories_listed":0,"syntology":null},{"url":null,"slug":"proximal-gradient-based-unfolding-for-massive","title":"Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks","date":"2022-12-04","arxiv_id":"2212.01839","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-estimation-of-clustered-user-activity","title":"Joint Estimation of Clustered User Activity and Correlated Channels with Unknown Covariance in mMTC","date":"2022-11-30","arxiv_id":"2212.00116","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-timescale-event-detection-in","title":"Multi-timescale Event Detection in Nonintrusive Load Monitoring based on MDL Principle","date":"2022-11-19","arxiv_id":"2211.10721","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-using-the-ua-speech-and-torgo-databases-to","title":"On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches","date":"2022-11-16","arxiv_id":"2211.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stream-multi-dimensional-convolutional","title":"Two-stream Multi-dimensional Convolutional Network for Real-time Violence Detection","date":"2022-11-08","arxiv_id":"2211.04255","repositories_listed":0,"syntology":null},{"url":null,"slug":"ofdm-based-massive-connectivity-for-leo","title":"OFDM-Based Massive Connectivity for LEO Satellite Internet of Things","date":"2022-10-31","arxiv_id":"2210.17355","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-short-video-speech-recognition","title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","date":"2022-10-28","arxiv_id":"2210.15876","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-voice-activity-detection-via","title":"Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction","date":"2022-10-28","arxiv_id":"2210.16127","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsup-speaker-diarization-system-for","title":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","date":"2022-10-26","arxiv_id":"2210.14653","repositories_listed":0,"syntology":null},{"url":null,"slug":"mri-multi-modal-3d-human-pose-estimation","title":"mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors","date":"2022-10-15","arxiv_id":"2210.08394","repositories_listed":0,"syntology":null},{"url":null,"slug":"intel-labs-at-ego4d-challenge-2022-a-better","title":"Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization","date":"2022-10-14","arxiv_id":"2210.07764","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-driven-ai-paradigm-for-hand-held","title":"Application-Driven AI Paradigm for Hand-Held Action Detection","date":"2022-10-13","arxiv_id":"2210.06682","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dku-dukeece-diarization-system-for-the","title":"The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022","date":"2022-10-04","arxiv_id":"2210.01677","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-acoustic-frontends-in-bird-activity","title":"Learnable Acoustic Frontends in Bird Activity Detection","date":"2022-10-03","arxiv_id":"2210.00889","repositories_listed":0,"syntology":null},{"url":null,"slug":"signed-latent-factors-for-spamming-activity","title":"Signed Latent Factors for Spamming Activity Detection","date":"2022-09-28","arxiv_id":"2209.13814","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speech-activity-and-overlap-detection","title":"Joint Speech Activity and Overlap Detection with Multi-Exit Architecture","date":"2022-09-24","arxiv_id":"2209.11906","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-kriston-ai-system-for-the-voxceleb","title":"The Kriston AI System for the VoxCeleb Speaker Recognition Challenge 2022","date":"2022-09-23","arxiv_id":"2209.11433","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-voice-activity-detection-with","title":"Cross-domain Voice Activity Detection with Self-Supervised Representations","date":"2022-09-22","arxiv_id":"2209.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"gist-aiter-system-for-the-diarization-task-of","title":"GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge","date":"2022-09-21","arxiv_id":"2209.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-accelerator-and-neural-network-co","title":"Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices","date":"2022-09-08","arxiv_id":"2209.03807","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-action-detection-under-large","title":"Spatio-Temporal Action Detection Under Large Motion","date":"2022-09-06","arxiv_id":"2209.02250","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-circular-window-based-cascade-transformer","title":"A Circular Window-based Cascade Transformer for Online Action Detection","date":"2022-08-30","arxiv_id":"2208.14209","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-voice-activity-detection-with-1","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","date":"2022-08-27","arxiv_id":"2208.13085","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-weakly-supervised-temporal-action","title":"Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream","date":"2022-08-25","arxiv_id":"2208.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-on-action-recognition-for-accident","title":"Review on Action Recognition for Accident Detection in Smart City Transportation Systems","date":"2022-08-20","arxiv_id":"2208.09588","repositories_listed":0,"syntology":null},{"url":null,"slug":"bodily-behaviors-in-social-interaction-novel","title":"Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation","date":"2022-07-26","arxiv_id":"2207.12817","repositories_listed":0,"syntology":null},{"url":null,"slug":"textbf-p-2-a-a-dataset-and-benchmark-for","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","date":"2022-07-26","arxiv_id":"2207.12730","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-spatio-temporal-pyramid","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","date":"2022-07-21","arxiv_id":"2207.10448","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-target-speaker-voice-activity","title":"Online Target Speaker Voice Activity Detection for Speaker Diarization","date":"2022-07-13","arxiv_id":"2207.05920","repositories_listed":0,"syntology":null},{"url":"/paper/fine-grained-activities-of-people-worldwide","slug":"fine-grained-activities-of-people-worldwide","title":"Fine-grained Activities of People Worldwide","date":"2022-07-11","arxiv_id":"2207.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"tandem-multitask-training-of-speaker","title":"Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription","date":"2022-07-08","arxiv_id":"2207.03852","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-aiot-enabled-autonomous-dementia","title":"An AIoT-enabled Autonomous Dementia Monitoring System","date":"2022-07-02","arxiv_id":"2207.00804","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-stage-action-detection-transformer","title":"One-stage Action Detection Transformer","date":"2022-06-21","arxiv_id":"2206.10080","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-end-to-end-neural-network-for","title":"Multi-channel end-to-end neural network for speech enhancement, source localization, and voice activity detection","date":"2022-06-20","arxiv_id":"2206.09728","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-proposal-network-for-temporal","title":"Context-aware Proposal Network for Temporal Action Detection","date":"2022-06-18","arxiv_id":"2206.09082","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-speech-extraction-for-multiple","title":"Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios","date":"2022-06-17","arxiv_id":"2206.08525","repositories_listed":0,"syntology":null},{"url":null,"slug":"ris-assisted-device-activity-detection-with","title":"RIS Assisted Device Activity Detection with Statistical Channel State Information","date":"2022-06-14","arxiv_id":"2206.06805","repositories_listed":0,"syntology":null},{"url":"/paper/gatehub-gated-history-unit-with-background-1","slug":"gatehub-gated-history-unit-with-background-1","title":"GateHUB: Gated History Unit with Background Suppression for Online Action Detection","date":"2022-06-09","arxiv_id":"2206.04668","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-aided-active-user-detection-with-a-user","title":"Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems","date":"2022-05-22","arxiv_id":"2205.10780","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-boosting-algorithm-for-positive-unlabeled","title":"A Boosting Algorithm for Positive-Unlabeled Learning","date":"2022-05-19","arxiv_id":"2205.09485","repositories_listed":0,"syntology":null}],"record_sha256":"622e5a9d47bd1e76144b0abd29420992a877513a98bb82bdf3557a570f4f9ee2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}