{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":null,"description_markdown":"The **THUMOS14** (THUMOS 2014) dataset is a large-scale video dataset that includes 1,010 videos for validation and 1,574 videos for testing from 20 classes. Among all the videos, there are 220 and 212 videos with temporal annotations in validation and testing set, respectively.\r\n\r\nSource: [Learning to Localize Actions from Moments](https://arxiv.org/abs/2008.13705)\r\nImage Source: [http://crcv.ucf.edu/THUMOS14/](http://crcv.ucf.edu/THUMOS14/)","description_withheld":null,"homepage":"http://crcv.ucf.edu/THUMOS14/home.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"THUMOS challenge: Action recognition with a large number of classes","first_author":null,"url":"http://www.thumos.info/"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"},{"name":"Action Detection","url":"/task/action-detection","datasets_with_task":"/datasets/task/action-detection"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"},{"name":"Weakly Supervised Action Localization","url":"/task/weakly-supervised-action-localization","datasets_with_task":"/datasets/task/weakly-supervised-action-localization"},{"name":"Zero-Shot Action Recognition","url":"/task/zero-shot-action-recognition","datasets_with_task":"/datasets/task/zero-shot-action-recognition"},{"name":"Temporal Action Proposal Generation","url":"/task/temporal-action-proposal-generation","datasets_with_task":"/datasets/task/temporal-action-proposal-generation"},{"name":"Weakly-supervised Temporal Action Localization","url":"/task/weakly-supervised-temporal-action","datasets_with_task":"/datasets/task/weakly-supervised-temporal-action"},{"name":"Online Action Detection","url":"/task/online-action-detection","datasets_with_task":"/datasets/task/online-action-detection"},{"name":"Few Shot Temporal Action Localization","url":"/task/few-shot-temporal-action-localization","datasets_with_task":"/datasets/task/few-shot-temporal-action-localization"},{"name":"Semi-Supervised Action Detection","url":"/task/semi-supervised-action-detection","datasets_with_task":"/datasets/task/semi-supervised-action-detection"},{"name":"Zero-Shot Action Detection","url":"/task/zero-shot-action-detection","datasets_with_task":"/datasets/task/zero-shot-action-detection"}],"languages":[],"variants":["THUMOS' 14","THUMOS 2014","THUMOS’14","THUMOS'14","THUMOS14"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2/blob/master/tools/data/thumos14/README.md","frameworks":["pytorch"]}],"num_papers_in_archive":318,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset_variant":"THUMOS’14","rows":42,"metrics":["Avg mAP (0.3:0.7)","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7"],"first_row_in_archive_order":{"model":"AdaTAD (VideoMAEv2-giant)","paper":"/paper/end-to-end-temporal-action-detection-with-1b","metrics":{"Avg mAP (0.3:0.7)":"76.9","mAP IOU@0.3":"89.7","mAP IOU@0.4":"86.7","mAP IOU@0.5":"80.9","mAP IOU@0.6":"71.0","mAP IOU@0.7":"56.1"},"code_links":[{"title":"sming256/OpenTAD","url":"https://github.com/sming256/OpenTAD"},{"title":"sming256/AdaTAD","url":"https://github.com/sming256/AdaTAD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset_variant":"THUMOS 2014","rows":30,"metrics":["mAP@0.1:0.7","mAP@0.1:0.5","mAP@0.5"],"first_row_in_archive_order":{"model":"HR-Pro","paper":"/paper/hr-pro-point-supervised-temporal-action","metrics":{"mAP@0.1:0.5":"71.6","mAP@0.1:0.7":"60.3","mAP@0.5":"52.2"},"code_links":[{"title":"pipixin321/hr-pro","url":"https://github.com/pipixin321/hr-pro"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/online-action-detection-on-thumos-14","task":"Online Action Detection","dataset_variant":"THUMOS'14","rows":15,"metrics":["mAP","MFLOPs per pred"],"first_row_in_archive_order":{"model":"GateHUB(TimeSformer)","paper":"/paper/gatehub-gated-history-unit-with-background-1","metrics":{"mAP":"72.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset_variant":"THUMOS’14","rows":13,"metrics":["mAP@0.5","avg-mAP (0.1-0.5)"],"first_row_in_archive_order":{"model":"LACP","paper":"/paper/learning-action-completeness-from-points-for","metrics":{"mAP@0.5":"45.3"},"code_links":[{"title":"Pilhyeon/Learning-Action-Completeness-from-Points","url":"https://github.com/Pilhyeon/Learning-Action-Completeness-from-Points"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","task":"Weakly Supervised Action Localization","dataset_variant":"THUMOS14","rows":12,"metrics":["avg-mAP (0.3-0.7)","avg-mAP (0.1:0.7)","avg-mAP (0.1-0.5)"],"first_row_in_archive_order":{"model":"HR-Pro","paper":"/paper/hr-pro-point-supervised-temporal-action","metrics":{"avg-mAP (0.1-0.5)":"71.6","avg-mAP (0.1:0.7)":"60.3","avg-mAP (0.3-0.7)":"51.1"},"code_links":[{"title":"pipixin321/hr-pro","url":"https://github.com/pipixin321/hr-pro"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14","task":"Action Recognition","dataset_variant":"THUMOS’14","rows":10,"metrics":["mAP@0.5","mAP@0.1","mAP@0.2","mAP@0.3","mAP@0.4"],"first_row_in_archive_order":{"model":"BMN","paper":"/paper/bmn-boundary-matching-network-for-temporal","metrics":{"mAP@0.3":"56.0","mAP@0.4":"47.4","mAP@0.5":"38.8"},"code_links":[{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/video/models/bmn"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models/tree/develop/dygraph/bmn"},{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"PaddlePaddle/PaddleVideo","url":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/zh-CN/model_zoo/localization/bmn.md"},{"title":"Tencent/ActionDetection-DBG","url":"https://github.com/Tencent/ActionDetection-DBG"},{"title":"JJBOY/BMN-Boundary-Matching-Network","url":"https://github.com/JJBOY/BMN-Boundary-Matching-Network"},{"title":"Frostinassiky/gtad","url":"https://github.com/Frostinassiky/gtad"},{"title":"xlliu7/BMN-Boundary-Matching-Network","url":"https://github.com/xlliu7/BMN-Boundary-Matching-Network"},{"title":"handhand123/prsa-net","url":"https://github.com/handhand123/prsa-net"},{"title":"Lechatelia/action-proposal-generation","url":"https://github.com/Lechatelia/action-proposal-generation"},{"title":"2024-MindSpore-1/Code6","url":"https://github.com/2024-MindSpore-1/Code6/tree/main/BMN"},{"title":"carpedkm/G_TAD_customizing","url":"https://github.com/carpedkm/G_TAD_customizing"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/BMN"},{"title":"2023-MindSpore-1/ms-code-17","url":"https://github.com/2023-MindSpore-1/ms-code-17/tree/main/BMN"},{"title":"MindSpore-paper-code-3/code6","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/BMN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-detection-on-thumos-14","task":"Action Detection","dataset_variant":"THUMOS' 14","rows":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MAT (Ours) Trans","paper":"/paper/memory-and-anticipation-transformer-for","metrics":{"mAP":"71.6"},"code_links":[{"title":"echo0125/memory-and-anticipation-transformer","url":"https://github.com/echo0125/memory-and-anticipation-transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-temporal-action","task":"Weakly-supervised Temporal Action Localization","dataset_variant":"THUMOS’14","rows":4,"metrics":["mAP@AVG(0.1:0.9)","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7","mAP IOU@0.8","mAP IOU@0.9"],"first_row_in_archive_order":{"model":"CO2-Net","paper":"/paper/cross-modal-consensus-network-for-weakly","metrics":{"mAP IOU@0.1":"70.1","mAP IOU@0.2":"63.6","mAP IOU@0.3":"54.5","mAP IOU@0.4":"45.7","mAP IOU@0.5":"38.3","mAP IOU@0.6":"26.4","mAP IOU@0.7":"13.4","mAP IOU@0.8":"6.9","mAP IOU@0.9":"2.0","mAP@AVG(0.1:0.9)":"35.7"},"code_links":[{"title":"harlanhong/MM2021-CO2-Net","url":"https://github.com/harlanhong/MM2021-CO2-Net"},{"title":"xiaojuntang22/iccv2023-ddgnet","url":"https://github.com/xiaojuntang22/iccv2023-ddgnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-classification-on-thumos14","task":"Action Classification","dataset_variant":"THUMOS’14","rows":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"3C-Net","paper":"/paper/3c-net-category-count-and-center-loss-for","metrics":{"mAP":"86.9"},"code_links":[{"title":"naraysa/3c-net","url":"https://github.com/naraysa/3c-net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/temporal-action-proposal-generation-on-thumos","task":"Temporal Action Proposal Generation","dataset_variant":"THUMOS' 14","rows":3,"metrics":["AR@100","AR@1000","AR@200","AR@50","AR@500"],"first_row_in_archive_order":{"model":"HCH","paper":"/paper/improve-temporal-action-proposals-using","metrics":{"AR@100":"50.86","AR@1000":"67.34","AR@200":"57.56","AR@50":"64.28"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14-1","task":"Action Recognition In Videos","dataset_variant":"THUMOS’14","rows":2,"metrics":["mAP@0.1","mAP@0.2","mAP@0.3","mAP@0.4","mAP@0.5"],"first_row_in_archive_order":{"model":"Single-stream R-C3D (two-way buffer)","paper":"/paper/r-c3d-region-convolutional-3d-network-for","metrics":{"mAP@0.1":"54.5","mAP@0.2":"51.5","mAP@0.3":"44.8","mAP@0.4":"35.6","mAP@0.5":"28.9"},"code_links":[{"title":"VisionLearningGroup/R-C3D","url":"https://github.com/VisionLearningGroup/R-C3D"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/C3D"},{"title":"MindSpore-paper-code-3/code6","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/C3D"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-classification-on-thumos-14","task":"Action Classification","dataset_variant":"THUMOS'14","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"3C-Net","paper":"/paper/3c-net-category-count-and-center-loss-for","metrics":{"mAP":"86.9"},"code_links":[{"title":"naraysa/3c-net","url":"https://github.com/naraysa/3c-net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-on-thumos14","task":"Action Recognition","dataset_variant":"THUMOS14","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MSQNet","paper":"/paper/msqnet-actor-agnostic-action-recognition-with","metrics":{"Accuracy":"83.16"},"code_links":[{"title":"mondalanindya/msqnet","url":"https://github.com/mondalanindya/msqnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-temporal-action-localization-on-1","task":"Few Shot Temporal Action Localization","dataset_variant":"THUMOS14","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"FS-QAT","paper":"/paper/few-shot-temporal-action-localization-with","metrics":{"mIoU":"30.2"},"code_links":[{"title":"sauradip/fewshotQAT","url":"https://github.com/sauradip/fewshotQAT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/temporal-action-localization-on-thumos-14","task":"Temporal Action Localization","dataset_variant":"THUMOS'14","rows":1,"metrics":["mAP IOU@0.5"],"first_row_in_archive_order":{"model":"AVFusion","paper":"/paper/hear-me-out-fusional-approaches-for-audio","metrics":{"mAP IOU@0.5":"57.18"},"code_links":[{"title":"skelemoa/tal-hmo","url":"https://github.com/skelemoa/tal-hmo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/temporal-action-localization-on-thumos14-2","task":"Temporal Action Localization","dataset_variant":"THUMOS14","rows":1,"metrics":["Avg mAP (0.3:0.7)"],"first_row_in_archive_order":{"model":"BasicTAD (R50-SlowOnly)","paper":"/paper/basictad-an-astounding-rgb-only-baseline-for","metrics":{"Avg mAP (0.3:0.7)":"59.6"},"code_links":[{"title":"mcg-nju/basictad","url":"https://github.com/mcg-nju/basictad"},{"title":"cg1177/dcan","url":"https://github.com/cg1177/dcan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-localization-on-8","task":"Weakly Supervised Action Localization","dataset_variant":"THUMOS' 14","rows":1,"metrics":["avg-mAP (0.1:0.7)"],"first_row_in_archive_order":{"model":"ProCL","paper":"/paper/weakly-supervised-action-localization-via","metrics":{"avg-mAP (0.1:0.7)":"47.7"},"code_links":[{"title":"Run542968/ProCL","url":"https://github.com/Run542968/ProCL"},{"title":"fjchange/him-net","url":"https://github.com/fjchange/him-net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-action-recognition-on-thumos-14","task":"Zero-Shot Action Recognition","dataset_variant":"THUMOS' 14","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MSQNet","paper":"/paper/msqnet-actor-agnostic-action-recognition-with","metrics":{"Accuracy":"75.33"},"code_links":[{"title":"mondalanindya/msqnet","url":"https://github.com/mondalanindya/msqnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multilevel-semantic-and-adaptive-actionness","title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","date":"2024-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhancing-temporal-action-localization","title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","date":"2024-07-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-temporal-action-8","title":"Weakly supervised temporal action localization with actionness-guided false positive suppression","date":"2024-04-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/video-mamba-suite-state-space-model-as-a","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","date":"2024-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":8,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-foreground-and-background-1","title":"Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach","date":"2023-12-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-temporal-action-detection-with-1b","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","date":"2023-11-28","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/temporal-action-localization-with-enhanced","title":"Temporal Action Localization with Enhanced Instant Discriminability","date":"2023-09-11","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/hr-pro-point-supervised-temporal-action","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","date":"2023-08-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/memory-and-anticipation-transformer-for","title":"Memory-and-Anticipation Transformer for Online Action Understanding","date":"2023-08-15","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/msqnet-actor-agnostic-action-recognition-with","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","date":"2023-07-20","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/actionness-inconsistency-guided-contrastive","title":"Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization","date":"2023-06-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/proposal-based-multiple-instance-learning-for-1","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","date":"2023-05-29","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/action-sensitivity-learning-for-temporal","title":"Action Sensitivity Learning for Temporal Action Localization","date":"2023-05-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improve-temporal-action-proposals-using","title":"Improve Temporal Action Proposals using Hierarchical Context","date":"2023-04-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporalmaxer-maximize-temporal-context-with","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","date":"2023-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tridet-temporal-action-detection-with","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","date":"2023-03-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":5,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/two-stream-networks-for-weakly-supervised","title":"Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pivotal-prior-driven-supervision-for-weakly","title":"PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/miniroad-minimal-rnn-framework-for-online","title":"MiniROAD: Minimal RNN Framework for Online Action Detection","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aoe-net-entities-interactions-modeling-with","title":"AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation","date":"2022-10-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-action-detection-with-global","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","date":"2022-07-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/react-temporal-action-detection-with","title":"ReAct: Temporal Action Detection with Relational Queries","date":"2022-07-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":2,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/weakly-supervised-action-localization-via","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","date":"2022-06-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/gatehub-gated-history-unit-with-background-1","title":"GateHUB: Gated History Unit with Background Suppression for Online Action Detection","date":"2022-06-09","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/tadml-a-fast-temporal-action-detection-with","title":"TadML: A fast temporal action detection with Mechanics-MLP","date":"2022-06-07","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/basictad-an-astounding-rgb-only-baseline-for","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","date":"2022-05-05","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/an-empirical-study-of-end-to-end-temporal","title":"An Empirical Study of End-to-End Temporal Action Detection","date":"2022-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/asm-loc-action-aware-segment-modeling-for","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/colar-effective-and-efficient-online-action","title":"Colar: Effective and Efficient Online Action Detection by Consulting Exemplars","date":"2022-03-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","date":"2022-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/continual-transformers-redundancy-free","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","date":"2022-01-17","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/dcan-improving-temporal-action-detection-via","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","date":"2021-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-convolutional-module-for-temporal","title":"Graph Convolutional Module for Temporal Action Localization in Videos","date":"2021-12-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-action-completeness-from-points-for","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","date":"2021-08-11","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/cross-modal-consensus-network-forweakly","title":"Cross-modal Consensus Network forWeakly Supervised Temporal Action Localization","date":"2021-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-modal-consensus-network-for-weakly","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","date":"2021-07-27","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/rgb-stream-is-enough-for-temporal-action","title":"RGB Stream Is Enough for Temporal Action Detection","date":"2021-07-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/long-short-term-transformer-for-online-action","title":"Long Short-Term Transformer for Online Action Detection","date":"2021-07-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":1,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hear-me-out-fusional-approaches-for-audio","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","date":"2021-06-27","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/oadtr-online-action-detection-with","title":"OadTR: Online Action Detection with Transformers","date":"2021-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/end-to-end-temporal-action-detection-with","title":"End-to-end Temporal Action Detection with Transformer","date":"2021-06-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/action-unit-memory-network-for-weakly","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","date":"2021-04-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/acm-net-action-context-modeling-network-for","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","date":"2021-04-07","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/adaptive-mutual-supervision-for-weakly","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","date":"2021-04-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cola-weakly-supervised-temporal-action","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","date":"2021-03-30","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/acsnet-action-context-separation-network-for","title":"ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization","date":"2021-03-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/activity-graph-transformer-for-temporal","title":"Activity Graph Transformer for Temporal Action Localization","date":"2021-01-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-shot-temporal-event-localization-a","title":"Multi-shot Temporal Event Localization: a Benchmark","date":"2020-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/point-level-temporal-action-localization","title":"Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses","date":"2020-12-15","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/d2-net-weakly-supervised-action-localization","title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","date":"2020-12-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-self-stitching-graph-network-for","title":"Video Self-Stitching Graph Network for Temporal Action Localization","date":"2020-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/two-stream-consensus-network-for-weakly-1","title":"Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization","date":"2020-10-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adversarial-background-aware-loss-for-weakly","title":"Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization","date":"2020-07-13","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/background-modeling-via-uncertainty","title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","date":"2020-06-12","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/woad-weakly-supervised-online-action","title":"WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos","date":"2020-06-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-action-localization-with-2","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","date":"2020-03-31","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-action-localization-by-2","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","date":"2020-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sf-net-single-frame-supervision-for-temporal","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","date":"2020-03-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-temporal-action-1","title":"Weakly Supervised Temporal Action Localization Using Deep Metric Learning","date":"2020-01-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/g-tad-sub-graph-localization-for-temporal","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","date":"2019-11-26","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":3,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/background-suppression-network-for-weakly","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","date":"2019-11-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-temporal-action","title":"Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks","date":"2019-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-structure-mining-for-weakly","title":"Temporal Structure Mining for Weakly Supervised Action Detection","date":"2019-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-convolutional-networks-for-temporal","title":"Graph Convolutional Networks for Temporal Action Localization","date":"2019-09-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3c-net-category-count-and-center-loss-for","title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","date":"2019-08-22","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/bmn-boundary-matching-network-for-temporal","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","date":"2019-07-23","rows_on_this_dataset":2,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/two-stream-region-convolutional-3d-network","title":"Two-Stream Region Convolutional 3D Network for Temporal Activity Detection","date":"2019-06-05","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/completeness-modeling-and-context-separation","title":"Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization","date":"2019-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/marginalized-average-attentional-network-for-1","title":"Marginalized Average Attentional Network for Weakly-Supervised Learning","date":"2019-05-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decoupling-localization-and-classification-in","title":"Decoupling Localization and Classification in Single Shot Temporal Action Detection","date":"2019-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-granularity-generator-for-temporal","title":"Multi-granularity Generator for Temporal Action Proposal","date":"2018-11-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-recurrent-networks-for-online-action","title":"Temporal Recurrent Networks for Online Action Detection","date":"2018-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/autoloc-weakly-supervised-temporal-action-1","title":"AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos","date":"2018-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/w-talc-weakly-supervised-temporal-activity","title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","date":"2018-07-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bsn-boundary-sensitive-network-for-temporal","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","date":"2018-06-08","rows_on_this_dataset":3,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-the-faster-r-cnn-architecture-for","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","date":"2018-04-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-action-localization-by","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","date":"2017-12-14","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/temporal-context-network-for-activity","title":"Temporal Context Network for Activity Localization in Videos","date":"2017-08-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cascaded-boundary-regression-for-temporal","title":"Cascaded Boundary Regression for Temporal Action Detection","date":"2017-05-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-action-detection-with-structured","title":"Temporal Action Detection with Structured Segment Networks","date":"2017-04-20","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hide-and-seek-forcing-a-network-to-be","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","date":"2017-04-13","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/r-c3d-region-convolutional-3d-network-for","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","date":"2017-03-22","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/turn-tap-temporal-unit-regression-network-for","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","date":"2017-03-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/untrimmednets-for-weakly-supervised-action","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","date":"2017-03-09","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cdc-convolutional-de-convolutional-networks","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","date":"2017-03-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-action-localization-in-untrimmed","title":"Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs","date":"2016-01-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":20,"samples_harvested":133,"samples_ran":42,"samples_unverified":91,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":5,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}