{"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/3","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":3,"pages_in_order":9,"rows_per_page":100,"rows":[201,300],"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/2","next":"/task/action-detection/papers/4","papers":[{"url":"/paper/plsm-a-parallelized-liquid-state-machine-for","slug":"plsm-a-parallelized-liquid-state-machine-for","title":"PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection","date":"2021-05-06","arxiv_id":"2105.09909","repositories_listed":1,"syntology":null},{"url":"/paper/temporally-smooth-online-action-detection","slug":"temporally-smooth-online-action-detection","title":"Temporally smooth online action detection using cycle-consistent future anticipation","date":"2021-04-16","arxiv_id":"2104.08030","repositories_listed":1,"syntology":null},{"url":"/paper/tuber-tube-transformer-for-action-detection","slug":"tuber-tube-transformer-for-action-detection","title":"TubeR: Tubelet Transformer for Video Action Detection","date":"2021-04-02","arxiv_id":"2104.00969","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tuber-tube-transformer-for-action-detection#ran","syntology_url":"https://syntology.ai/paper/2104.00969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00969"}},"official":null}},{"url":"/paper/temporal-context-aggregation-network-for","slug":"temporal-context-aggregation-network-for","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","date":"2021-03-24","arxiv_id":"2103.13141","repositories_listed":1,"syntology":null},{"url":"/paper/action-detection-using-a-neural-network","slug":"action-detection-using-a-neural-network","title":"Action detection using a neural network elucidates the genetics of mouse grooming behavior","date":"2021-03-17","arxiv_id":null,"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/modeling-multi-label-action-dependencies-for","slug":"modeling-multi-label-action-dependencies-for","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","date":"2021-03-04","arxiv_id":"2103.03027","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-multi-label-action-dependencies-for#ran","syntology_url":"https://syntology.ai/paper/2103.03027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03027"}},"official":{"repos":["ptirupat/MLAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/acdnet-an-action-detection-network-for-real","slug":"acdnet-an-action-detection-network-for-real","title":"ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation","date":"2021-02-26","arxiv_id":"2102.13493","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-multi-label-actor-action","slug":"discovering-multi-label-actor-action","title":"Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting","date":"2021-01-21","arxiv_id":"2101.08567","repositories_listed":1,"syntology":null},{"url":"/paper/pdan-pyramid-dilated-attention-network-for","slug":"pdan-pyramid-dilated-attention-network-for","title":"PDAN: Pyramid Dilated Attention Network for Action Detection","date":"2021-01-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-improving-spatiotemporal-action","slug":"towards-improving-spatiotemporal-action","title":"Towards Improving Spatiotemporal Action Recognition in Videos","date":"2020-12-15","arxiv_id":"2012.08097","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/we-don-t-need-thousand-proposals-colon-single","slug":"we-don-t-need-thousand-proposals-colon-single","title":"We don't Need Thousand Proposals$\\colon$ Single Shot Actor-Action Detection in Videos","date":"2020-11-22","arxiv_id":"2011.10927","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/online-spatiotemporal-action-detection-and","slug":"online-spatiotemporal-action-detection-and","title":"Online Spatiotemporal Action Detection and Prediction via Causal Representations","date":"2020-08-31","arxiv_id":"2008.13759","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/a-multi-task-learning-approach-for-human","slug":"a-multi-task-learning-approach-for-human","title":"A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment","date":"2020-08-07","arxiv_id":"2008.03014","repositories_listed":1,"syntology":null},{"url":"/paper/weight-excitation-built-in-attention","slug":"weight-excitation-built-in-attention","title":"Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/avid-dataset-anonymized-videos-from-diverse","slug":"avid-dataset-anonymized-videos-from-diverse","title":"AViD Dataset: Anonymized Videos from Diverse Countries","date":"2020-07-10","arxiv_id":"2007.05515","repositories_listed":1,"syntology":null},{"url":"/paper/video-representation-learning-with-visual","slug":"video-representation-learning-with-visual","title":"Video Representation Learning with Visual Tempo Consistency","date":"2020-06-28","arxiv_id":"2006.15489","repositories_listed":1,"syntology":null},{"url":"/paper/cbr-net-cascade-boundary-refinement-network","slug":"cbr-net-cascade-boundary-refinement-network","title":"CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)","date":"2020-06-13","arxiv_id":"2006.07526","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/a-benchmark-for-structured-procedural","slug":"a-benchmark-for-structured-procedural","title":"A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos","date":"2020-05-02","arxiv_id":"2005.00706","repositories_listed":1,"syntology":null},{"url":"/paper/two-stream-amtnet-for-action-detection","slug":"two-stream-amtnet-for-action-detection","title":"Two-Stream AMTnet for Action Detection","date":"2020-04-03","arxiv_id":"2004.01494","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/rethinking-online-action-detection-in","slug":"rethinking-online-action-detection-in","title":"Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol","date":"2020-03-26","arxiv_id":"2003.12041","repositories_listed":1,"syntology":null},{"url":"/paper/the-instantaneous-accuracy-a-novel-metric-for","slug":"the-instantaneous-accuracy-a-novel-metric-for","title":"The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos","date":"2020-03-22","arxiv_id":"2003.09970","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/back-to-the-future-joint-aware-temporal-deep","slug":"back-to-the-future-joint-aware-temporal-deep","title":"Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation","date":"2020-02-22","arxiv_id":"2002.11251","repositories_listed":1,"syntology":null},{"url":"/paper/human-activity-recognition-a-spatio-temporal","slug":"human-activity-recognition-a-spatio-temporal","title":"Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action Detection","date":"2020-02-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-study-on-temporal-modeling","slug":"a-comprehensive-study-on-temporal-modeling","title":"A Comprehensive Study on Temporal Modeling for Online Action Detection","date":"2020-01-21","arxiv_id":"2001.07501","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/why-cant-i-dance-in-the-mall-learning-to-1","slug":"why-cant-i-dance-in-the-mall-learning-to-1","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","date":"2019-12-11","arxiv_id":"1912.05534","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/why-cant-i-dance-in-the-mall-learning-to-1#ran","syntology_url":"https://syntology.ai/paper/1912.05534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05534"}},"official":{"repos":["vt-vl-lab/SDN"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/comprehensive-soccer-video-understanding","slug":"comprehensive-soccer-video-understanding","title":"SoccerDB: A Large-Scale Database for Comprehensive Video Understanding","date":"2019-12-10","arxiv_id":"1912.04465","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-discriminate-information-for","slug":"learning-to-discriminate-information-for","title":"Learning to Discriminate Information for Online Action Detection","date":"2019-12-10","arxiv_id":"1912.04461","repositories_listed":1,"syntology":null},{"url":"/paper/stage-spatio-temporal-attention-on-graph","slug":"stage-spatio-temporal-attention-on-graph","title":"Video action detection by learning graph-based spatio-temporal interactions","date":"2019-12-09","arxiv_id":"1912.04316","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/identifying-visible-actions-in-lifestyle","slug":"identifying-visible-actions-in-lifestyle","title":"Identifying Visible Actions in Lifestyle Vlogs","date":"2019-06-10","arxiv_id":"1906.04236","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/identifying-visible-actions-in-lifestyle#ran","syntology_url":"https://syntology.ai/paper/1906.04236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04236"}},"official":{"repos":["MichiganNLP/vlog_action_recognition"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/simple-yet-efficient-real-time-pose-based","slug":"simple-yet-efficient-real-time-pose-based","title":"Simple yet efficient real-time pose-based action recognition","date":"2019-04-19","arxiv_id":"1904.09140","repositories_listed":1,"syntology":null},{"url":"/paper/step-spatio-temporal-progressive-learning-for","slug":"step-spatio-temporal-progressive-learning-for","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","date":"2019-04-19","arxiv_id":"1904.09288","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-localization-and-classification-in","slug":"decoupling-localization-and-classification-in","title":"Decoupling Localization and Classification in Single Shot Temporal Action Detection","date":"2019-04-16","arxiv_id":"1904.07442","repositories_listed":1,"syntology":null},{"url":"/paper/dance-with-flow-two-in-one-stream-action","slug":"dance-with-flow-two-in-one-stream-action","title":"Dance with Flow: Two-in-One Stream Action Detection","date":"2019-04-01","arxiv_id":"1904.00696","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-action-detection-and-emotion","slug":"emotion-action-detection-and-emotion","title":"Emotion Action Detection and Emotion Inference: the Task and Dataset","date":"2019-03-16","arxiv_id":"1903.06901","repositories_listed":1,"syntology":null},{"url":"/paper/towards-segmenting-everything-that-moves","slug":"towards-segmenting-everything-that-moves","title":"Towards Segmenting Anything That Moves","date":"2019-02-11","arxiv_id":"1902.03715","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/temporal-recurrent-networks-for-online-action","slug":"temporal-recurrent-networks-for-online-action","title":"Temporal Recurrent Networks for Online Action Detection","date":"2018-11-18","arxiv_id":"1811.07391","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/temporal-recurrent-networks-for-online-action#ran","syntology_url":"https://syntology.ai/paper/1811.07391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07391"}},"official":{"repos":["xumingze0308/TRN.pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-centric-relation-network","slug":"actor-centric-relation-network","title":"Actor-Centric Relation Network","date":"2018-07-28","arxiv_id":"1807.10982","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/a-flexible-model-for-training-action","slug":"a-flexible-model-for-training-action","title":"A flexible model for training action localization with varying levels of supervision","date":"2018-06-29","arxiv_id":"1806.11328","repositories_listed":1,"syntology":null},{"url":"/paper/modality-distillation-with-multiple-stream","slug":"modality-distillation-with-multiple-stream","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","date":"2018-06-19","arxiv_id":"1806.07110","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-visual-instrument-playing","slug":"weakly-supervised-visual-instrument-playing","title":"Weakly-supervised Visual Instrument-playing Action Detection in Videos","date":"2018-05-05","arxiv_id":"1805.02031","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-anonymize-faces-for-privacy","slug":"learning-to-anonymize-faces-for-privacy","title":"Learning to Anonymize Faces for Privacy Preserving Action Detection","date":"2018-03-30","arxiv_id":"1803.11556","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-anonymize-faces-for-privacy#ran","syntology_url":"https://syntology.ai/paper/1803.11556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11556"}},"official":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/structured-label-inference-for-visual","slug":"structured-label-inference-for-visual","title":"Structured Label Inference for Visual Understanding","date":"2018-02-18","arxiv_id":"1802.06459","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/graph-distillation-for-action-detection-with","slug":"graph-distillation-for-action-detection-with","title":"Graph Distillation for Action Detection with Privileged Modalities","date":"2017-11-30","arxiv_id":"1712.00108","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-action-detection-in-video","slug":"real-time-action-detection-in-video","title":"Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN","date":"2017-10-10","arxiv_id":"1710.03383","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/sst-single-stream-temporal-action-proposals","slug":"sst-single-stream-temporal-action-proposals","title":"SST: Single-Stream Temporal Action Proposals","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-self-adaptive-proposal-model-for-temporal","slug":"a-self-adaptive-proposal-model-for-temporal","title":"A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning","date":"2017-06-22","arxiv_id":"1706.07251","repositories_listed":1,"syntology":null},{"url":"/paper/action-sets-weakly-supervised-action","slug":"action-sets-weakly-supervised-action","title":"Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints","date":"2017-06-02","arxiv_id":"1706.00699","repositories_listed":1,"syntology":null},{"url":"/paper/am-i-done-predicting-action-progress-in","slug":"am-i-done-predicting-action-progress-in","title":"Am I Done? Predicting Action Progress in Videos","date":"2017-05-04","arxiv_id":"1705.01781","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-based-action-recognition-with-2","slug":"skeleton-based-action-recognition-with-2","title":"Skeleton-based Action Recognition with Convolutional Neural Networks","date":"2017-04-25","arxiv_id":"1704.07595","repositories_listed":1,"syntology":null},{"url":"/paper/incremental-tube-construction-for-human","slug":"incremental-tube-construction-for-human","title":"Incremental Tube Construction for Human Action Detection","date":"2017-04-05","arxiv_id":"1704.01358","repositories_listed":1,"syntology":null},{"url":"/paper/tube-convolutional-neural-network-t-cnn-for","slug":"tube-convolutional-neural-network-t-cnn-for","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","date":"2017-03-30","arxiv_id":"1703.10664","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/temporal-tessellation-a-unified-approach-for","slug":"temporal-tessellation-a-unified-approach-for","title":"Temporal Tessellation: A Unified Approach for Video Analysis","date":"2016-12-21","arxiv_id":"1612.06950","repositories_listed":1,"syntology":null},{"url":"/paper/review-of-action-recognition-and-detection","slug":"review-of-action-recognition-and-detection","title":"Review of Action Recognition and Detection Methods","date":"2016-10-21","arxiv_id":"1610.06906","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/temporal-action-detection-using-a-statistical","slug":"temporal-action-detection-using-a-statistical","title":"Temporal Action Detection Using a Statistical Language Model","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/online-human-action-detection-using-joint","slug":"online-human-action-detection-using-joint","title":"Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks","date":"2016-04-19","arxiv_id":"1604.05633","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-learning-of-action-detection-from","slug":"end-to-end-learning-of-action-detection-from","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","date":"2015-11-22","arxiv_id":"1511.06984","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/finding-action-tubes","slug":"finding-action-tubes","title":"Finding Action Tubes","date":"2014-11-21","arxiv_id":"1411.6031","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":"/paper/multihuman-testbench-benchmarking-image","slug":"multihuman-testbench-benchmarking-image","title":"MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans","date":"2025-06-25","arxiv_id":"2506.20879","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multihuman-testbench-benchmarking-image#ran","syntology_url":"https://syntology.ai/paper/2506.20879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20879"}},"official":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":"beyond-pixels-leveraging-the-language-of","title":"Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos","date":"2025-05-14","arxiv_id":"2505.09455","repositories_listed":0,"syntology":null},{"url":null,"slug":"sensing-framework-design-and-performance","title":"Sensing Framework Design and Performance Optimization with Action Detection for ISCC","date":"2025-05-05","arxiv_id":"2505.02554","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-md-grounded-video-language-pre","title":"Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection","date":"2025-04-20","arxiv_id":"2504.14553","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":"fddet-frequency-decoupling-for-boundary","title":"FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection","date":"2025-04-01","arxiv_id":"2504.00647","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-detection-model-compression","title":"Temporal Action Detection Model Compression by Progressive Block Drop","date":"2025-03-21","arxiv_id":"2503.16916","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":"act360-an-efficient-360-degree-action","title":"ACT360: An Efficient 360-Degree Action Detection and Summarization Framework for Mission-Critical Training and Debriefing","date":"2025-03-17","arxiv_id":"2503.12852","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":"game-state-and-spatio-temporal-action","title":"Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks","date":"2025-02-21","arxiv_id":"2502.15462","repositories_listed":0,"syntology":null}],"record_sha256":"97a8583f84fc2c41adfd11be74a26e26402fec17838f7d73e092aa5b85b66cdc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}