{"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-recognition-in-videos/papers/8","list_of":"/task/action-recognition-in-videos","task":"Action Recognition","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":8,"pages_in_order":28,"rows_per_page":100,"rows":[701,800],"of":2759,"counts":{"archive_papers_tagged":2759,"with_a_code_link":1058,"where_syntology_ran_a_sample":275,"not_listed_spam_title":0,"listed":2759,"listed_where_code_ran":275,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":232,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":232,"listed_every_run_a_failure_of_syntologys_instrument":43,"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-recognition-in-videos","prev":"/task/action-recognition-in-videos/papers/7","next":"/task/action-recognition-in-videos/papers/9","papers":[{"url":"/paper/object-region-video-transformers-1","slug":"object-region-video-transformers-1","title":"Object-Region Video Transformers","date":"2021-10-13","arxiv_id":"2110.06915","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/object-region-video-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2110.06915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06915"}},"official":null}},{"url":"/paper/cross-modal-knowledge-distillation-for-vision","slug":"cross-modal-knowledge-distillation-for-vision","title":"Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition","date":"2021-10-08","arxiv_id":"2112.01849","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-viewpoint-outdoor-dataset-for-human","slug":"a-multi-viewpoint-outdoor-dataset-for-human","title":"A Multi-viewpoint Outdoor Dataset for Human Action Recognition","date":"2021-10-07","arxiv_id":"2110.04119","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-motion-representation-learning","slug":"unsupervised-motion-representation-learning","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","date":"2021-10-01","arxiv_id":"2110.00529","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":4,"n_ran_checked":8,"n_instrument":7,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":0,"phrase":"15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/unsupervised-motion-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2110.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00529"}},"official":{"repos":["ZiweiXU/CapsuleMotion"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":4,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/motion-aware-self-supervised-video","slug":"motion-aware-self-supervised-video","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","date":"2021-09-30","arxiv_id":"2109.15130","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-alignment-prediction-for-supervised","slug":"temporal-alignment-prediction-for-supervised","title":"Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fusion-gcn-multimodal-action-recognition","slug":"fusion-gcn-multimodal-action-recognition","title":"Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks","date":"2021-09-27","arxiv_id":"2109.12946","repositories_listed":1,"syntology":null},{"url":"/paper/improving-phenotype-prediction-using-long","slug":"improving-phenotype-prediction-using-long","title":"Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional Connectivity","date":"2021-09-07","arxiv_id":"2109.03115","repositories_listed":1,"syntology":null},{"url":"/paper/video-pose-distillation-for-few-shot-fine","slug":"video-pose-distillation-for-few-shot-fine","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","date":"2021-09-03","arxiv_id":"2109.01305","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-extreme-value-theory-for-open-set","slug":"conditional-extreme-value-theory-for-open-set","title":"Conditional Extreme Value Theory for Open Set Video Domain Adaptation","date":"2021-09-01","arxiv_id":"2109.00522","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conditional-extreme-value-theory-for-open-set#ran","syntology_url":"https://syntology.ai/paper/2109.00522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00522"}},"official":{"repos":["zhuoxiao-chen/cevt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ligar-lightweight-general-purpose-action","slug":"ligar-lightweight-general-purpose-action","title":"LIGAR: Lightweight General-purpose Action Recognition","date":"2021-08-30","arxiv_id":"2108.13153","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-fine-grained-action-recognition-via","slug":"few-shot-fine-grained-action-recognition-via","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","date":"2021-08-15","arxiv_id":"2108.06647","repositories_listed":1,"syntology":null},{"url":"/paper/learning-multi-granular-spatio-temporal-graph","slug":"learning-multi-granular-spatio-temporal-graph","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","date":"2021-08-10","arxiv_id":"2108.04536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-multi-granular-spatio-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2108.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04536"}},"official":{"repos":["tailin1009/dualhead-network"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autovideo-an-automated-video-action","slug":"autovideo-an-automated-video-action","title":"AutoVideo: An Automated Video Action Recognition System","date":"2021-08-09","arxiv_id":"2108.04212","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-object-affordance-detection-in-the","slug":"one-shot-object-affordance-detection-in-the","title":"One-Shot Object Affordance Detection in the Wild","date":"2021-08-08","arxiv_id":"2108.03658","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-contrastive-3d-action-representation","slug":"skeleton-contrastive-3d-action-representation","title":"Skeleton-Contrastive 3D Action Representation Learning","date":"2021-08-08","arxiv_id":"2108.03656","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/skeleton-contrastive-3d-action-representation#ran","syntology_url":"https://syntology.ai/paper/2108.03656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03656"}},"official":{"repos":["fmthoker/skeleton-contrast"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/temporal-action-localization-using-gated","slug":"temporal-action-localization-using-gated","title":"Temporal Action Localization Using Gated Recurrent Units","date":"2021-08-07","arxiv_id":"2108.03375","repositories_listed":1,"syntology":null},{"url":"/paper/elaborative-rehearsal-for-zero-shot-action","slug":"elaborative-rehearsal-for-zero-shot-action","title":"Elaborative Rehearsal for Zero-shot Action Recognition","date":"2021-08-05","arxiv_id":"2108.02833","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/elaborative-rehearsal-for-zero-shot-action#ran","syntology_url":"https://syntology.ai/paper/2108.02833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02833"}},"official":{"repos":["DeLightCMU/ElaborativeRehearsal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-nonlocal-blocks-for-neural-networks","slug":"unifying-nonlocal-blocks-for-neural-networks","title":"Unifying Nonlocal Blocks for Neural Networks","date":"2021-08-05","arxiv_id":"2108.02451","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-nonlocal-blocks-for-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2108.02451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02451"}},"official":{"repos":["zh460045050/SNL_ICCV2021"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-based-fall-detection-using-human-poses","slug":"video-based-fall-detection-using-human-poses","title":"Video Based Fall Detection Using Human Poses","date":"2021-07-29","arxiv_id":"2107.14633","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-split-for-evaluating-true-zero-shot","slug":"a-new-split-for-evaluating-true-zero-shot","title":"A New Split for Evaluating True Zero-Shot Action Recognition","date":"2021-07-27","arxiv_id":"2107.13029","repositories_listed":1,"syntology":null},{"url":"/paper/tinyaction-challenge-recognizing-real-world","slug":"tinyaction-challenge-recognizing-real-world","title":"TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos","date":"2021-07-24","arxiv_id":"2107.11494","repositories_listed":1,"syntology":null},{"url":"/paper/ean-event-adaptive-network-for-enhanced","slug":"ean-event-adaptive-network-for-enhanced","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","date":"2021-07-22","arxiv_id":"2107.10771","repositories_listed":1,"syntology":null},{"url":"/paper/unik-a-unified-framework-for-real-world","slug":"unik-a-unified-framework-for-real-world","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","date":"2021-07-19","arxiv_id":"2107.08580","repositories_listed":1,"syntology":null},{"url":"/paper/lsfb-cont-and-lsfb-isol-two-new-datasets-for","slug":"lsfb-cont-and-lsfb-isol-two-new-datasets-for","title":"LSFB-CONT and LSFB-ISOL: Two New Datasets for Vision-Based Sign Language Recognition","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-video-transformer-for-violence","slug":"data-efficient-video-transformer-for-violence","title":"Data Efficient Video Transformer for Violence Detection","date":"2021-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/group-activity-recognition-using-joint","slug":"group-activity-recognition-using-joint","title":"Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping","date":"2021-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/star-sparse-transformer-based-action","slug":"star-sparse-transformer-based-action","title":"STAR: Sparse Transformer-based Action Recognition","date":"2021-07-15","arxiv_id":"2107.07089","repositories_listed":1,"syntology":null},{"url":"/paper/ttan-two-stage-temporal-alignment-network-for","slug":"ttan-two-stage-temporal-alignment-network-for","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","date":"2021-07-10","arxiv_id":"2107.04782","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-for-multi-center-imaging","slug":"federated-learning-for-multi-center-imaging","title":"Federated Learning for Multi-Center Imaging Diagnostics: A Study in Cardiovascular Disease","date":"2021-07-07","arxiv_id":"2107.03901","repositories_listed":1,"syntology":null},{"url":"/paper/attention-bottlenecks-for-multimodal-fusion","slug":"attention-bottlenecks-for-multimodal-fusion","title":"Attention Bottlenecks for Multimodal Fusion","date":"2021-06-30","arxiv_id":"2107.00135","repositories_listed":1,"syntology":null},{"url":"/paper/hear-me-out-fusional-approaches-for-audio","slug":"hear-me-out-fusional-approaches-for-audio","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","date":"2021-06-27","arxiv_id":"2106.14118","repositories_listed":1,"syntology":null},{"url":"/paper/an-image-classifier-can-suffice-video","slug":"an-image-classifier-can-suffice-video","title":"Can An Image Classifier Suffice For Action Recognition?","date":"2021-06-26","arxiv_id":"2106.14104","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-image-classifier-can-suffice-video#ran","syntology_url":"https://syntology.ai/paper/2106.14104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14104"}},"official":{"repos":["ibm/sifar-pytorch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-based-behavioral-recognition-of","slug":"vision-based-behavioral-recognition-of","title":"Vision-based Behavioral Recognition of Novelty Preference in Pigs","date":"2021-06-23","arxiv_id":"2106.12181","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-of-deep-spatiotemporal","slug":"transfer-learning-of-deep-spatiotemporal","title":"Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures","date":"2021-06-22","arxiv_id":"2106.12014","repositories_listed":1,"syntology":null},{"url":"/paper/vimpac-video-pre-training-via-masked-token","slug":"vimpac-video-pre-training-via-masked-token","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","date":"2021-06-21","arxiv_id":"2106.11250","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":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vimpac-video-pre-training-via-masked-token#ran","syntology_url":"https://syntology.ai/paper/2106.11250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11250"}},"official":{"repos":["airsplay/vimpac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/point-4d-transformer-networks-for-spatio","slug":"point-4d-transformer-networks-for-spatio","title":"Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","repositories_listed":1,"syntology":null},{"url":"/paper/babel-bodies-action-and-behavior-with-english","slug":"babel-bodies-action-and-behavior-with-english","title":"BABEL: Bodies, Action and Behavior with English Labels","date":"2021-06-17","arxiv_id":"2106.09696","repositories_listed":1,"syntology":null},{"url":"/paper/modist-motion-distillation-for-self","slug":"modist-motion-distillation-for-self","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","date":"2021-06-17","arxiv_id":"2106.09703","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":3,"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/modist-motion-distillation-for-self#ran","syntology_url":"https://syntology.ai/paper/2106.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09703"}},"official":{"repos":["amazon-science/self-supervised-maclr"],"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/movi-a-large-multi-purpose-human-motion-and","slug":"movi-a-large-multi-purpose-human-motion-and","title":"MoVi: A large multi-purpose human motion and video dataset","date":"2021-06-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/isolated-sign-recognition-from-rgb-video","slug":"isolated-sign-recognition-from-rgb-video","title":"Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention","date":"2021-06-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}},"official":{"repos":["1adrianb/video-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-training-stronger-video-vision","slug":"towards-training-stronger-video-vision","title":"Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition","date":"2021-06-09","arxiv_id":"2106.05058","repositories_listed":1,"syntology":null},{"url":"/paper/technical-report-temporal-aggregate","slug":"technical-report-temporal-aggregate","title":"Technical Report: Temporal Aggregate Representations","date":"2021-06-06","arxiv_id":"2106.03152","repositories_listed":1,"syntology":null},{"url":"/paper/ct-net-channel-tensorization-network-for-1","slug":"ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","date":"2021-06-03","arxiv_id":"2106.01603","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":2,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ct-net-channel-tensorization-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}},"official":{"repos":["Andy1621/CT-Net"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-power-of-log-sum-exp-sequential-density","slug":"the-power-of-log-sum-exp-sequential-density","title":"The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization","date":"2021-05-28","arxiv_id":"2105.13636","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/the-power-of-log-sum-exp-sequential-density#ran","syntology_url":"https://syntology.ai/paper/2105.13636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13636"}},"official":{"repos":["TaikiMiyagawa/MSPRT-TANDEM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dsanet-dynamic-segment-aggregation-network","slug":"dsanet-dynamic-segment-aggregation-network","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","date":"2021-05-25","arxiv_id":"2105.12085","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dsanet-dynamic-segment-aggregation-network#ran","syntology_url":"https://syntology.ai/paper/2105.12085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12085"}},"official":{"repos":["whwu95/DSANet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sharing-pain-using-domain-transfer-between","slug":"sharing-pain-using-domain-transfer-between","title":"Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses","date":"2021-05-21","arxiv_id":"2105.10313","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-fusion-via-teacher-student-network","slug":"multimodal-fusion-via-teacher-student-network","title":"Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition","date":"2021-05-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vpn-rethinking-video-pose-embeddings-for","slug":"vpn-rethinking-video-pose-embeddings-for","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","date":"2021-05-17","arxiv_id":"2105.08141","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vpn-rethinking-video-pose-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/2105.08141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08141"}},"official":{"repos":["srijandas07/vpnplusplus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mutualnet-adaptive-convnet-via-mutual","slug":"mutualnet-adaptive-convnet-via-mutual","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","date":"2021-05-14","arxiv_id":"2105.07085","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mutualnet-adaptive-convnet-via-mutual#ran","syntology_url":"https://syntology.ai/paper/2105.07085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.07085"}},"official":{"repos":["taoyang1122/MutualNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/home-action-genome-cooperative-compositional","slug":"home-action-genome-cooperative-compositional","title":"Home Action Genome: Cooperative Compositional Action Understanding","date":"2021-05-11","arxiv_id":"2105.05226","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/home-action-genome-cooperative-compositional#ran","syntology_url":"https://syntology.ai/paper/2105.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05226"}},"official":{"repos":["nishantrai18/homage"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-visual-representation-learning-1","slug":"unsupervised-visual-representation-learning-1","title":"Unsupervised Visual Representation Learning by Tracking Patches in Video","date":"2021-05-06","arxiv_id":"2105.02545","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-third-order-features-in-skeleton","slug":"leveraging-third-order-features-in-skeleton","title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","date":"2021-05-04","arxiv_id":"2105.01563","repositories_listed":1,"syntology":null},{"url":"/paper/cocon-cooperative-contrastive-learning","slug":"cocon-cooperative-contrastive-learning","title":"CoCon: Cooperative-Contrastive Learning","date":"2021-04-30","arxiv_id":"2104.14764","repositories_listed":1,"syntology":null},{"url":"/paper/3d-human-action-representation-learning-via","slug":"3d-human-action-representation-learning-via","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","date":"2021-04-29","arxiv_id":"2104.14466","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-human-action-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2104.14466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14466"}},"official":{"repos":["LinguoLi/CrosSCLR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/hierarchical-growing-grid-networks-for","slug":"hierarchical-growing-grid-networks-for","title":"Hierarchical growing grid networks for skeleton based action recognition","date":"2021-04-22","arxiv_id":"2104.11165","repositories_listed":1,"syntology":null},{"url":"/paper/mgsampler-an-explainable-sampling-strategy","slug":"mgsampler-an-explainable-sampling-strategy","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","date":"2021-04-20","arxiv_id":"2104.09952","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mgsampler-an-explainable-sampling-strategy#ran","syntology_url":"https://syntology.ai/paper/2104.09952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09952"}},"official":{"repos":["mcg-nju/mgsampler"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/higher-order-recurrent-space-time-transformer","slug":"higher-order-recurrent-space-time-transformer","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","date":"2021-04-17","arxiv_id":"2104.08665","repositories_listed":1,"syntology":null},{"url":"/paper/first-and-second-order-dynamics-in-a","slug":"first-and-second-order-dynamics-in-a","title":"First and Second Order Dynamics in a Hierarchical SOM system for Action Recognition","date":"2021-04-13","arxiv_id":"2104.06059","repositories_listed":1,"syntology":null},{"url":"/paper/online-recognition-of-actions-involving","slug":"online-recognition-of-actions-involving","title":"Online Recognition of Actions Involving Objects","date":"2021-04-13","arxiv_id":"2104.06070","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-6","slug":"self-supervised-video-representation-learning-6","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","date":"2021-04-02","arxiv_id":"2104.00862","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-motion-learning-from-static","slug":"self-supervised-motion-learning-from-static","title":"Self-supervised Motion Learning from Static Images","date":"2021-04-01","arxiv_id":"2104.00240","repositories_listed":1,"syntology":null},{"url":"/paper/learning-representational-invariances-for","slug":"learning-representational-invariances-for","title":"Learning Representational Invariances for Data-Efficient Action Recognition","date":"2021-03-30","arxiv_id":"2103.16565","repositories_listed":1,"syntology":null},{"url":"/paper/no-frame-left-behind-full-video-action","slug":"no-frame-left-behind-full-video-action","title":"No frame left behind: Full Video Action Recognition","date":"2021-03-29","arxiv_id":"2103.15395","repositories_listed":1,"syntology":null},{"url":"/paper/gprar-graph-convolutional-network-based-pose","slug":"gprar-graph-convolutional-network-based-pose","title":"GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction","date":"2021-03-25","arxiv_id":"2103.14113","repositories_listed":1,"syntology":null},{"url":"/paper/action-net-multipath-excitation-for-action","slug":"action-net-multipath-excitation-for-action","title":"ACTION-Net: Multipath Excitation for Action Recognition","date":"2021-03-11","arxiv_id":"2103.07372","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/action-net-multipath-excitation-for-action#ran","syntology_url":"https://syntology.ai/paper/2103.07372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07372"}},"official":{"repos":["V-Sense/ACTION-Net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videomoco-contrastive-video-representation","slug":"videomoco-contrastive-video-representation","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","date":"2021-03-10","arxiv_id":"2103.05905","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/videomoco-contrastive-video-representation#ran","syntology_url":"https://syntology.ai/paper/2103.05905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05905"}},"official":{"repos":["tinapan-pt/VideoMoCo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/basar-black-box-attack-on-skeletal-action","slug":"basar-black-box-attack-on-skeletal-action","title":"BASAR:Black-box Attack on Skeletal Action Recognition","date":"2021-03-09","arxiv_id":"2103.05266","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-robustness-of-skeleton","slug":"understanding-the-robustness-of-skeleton","title":"Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack","date":"2021-03-09","arxiv_id":"2103.05347","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/understanding-the-robustness-of-skeleton#ran","syntology_url":"https://syntology.ai/paper/2103.05347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05347"}},"official":{"repos":["realcrane/SMART"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vipriors-1-visual-inductive-priors-for-data","slug":"vipriors-1-visual-inductive-priors-for-data","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","date":"2021-03-05","arxiv_id":"2103.03768","repositories_listed":1,"syntology":null},{"url":"/paper/domain-and-view-point-agnostic-hand-action","slug":"domain-and-view-point-agnostic-hand-action","title":"Domain and View-point Agnostic Hand Action Recognition","date":"2021-03-03","arxiv_id":"2103.02303","repositories_listed":1,"syntology":null},{"url":"/paper/a-body-part-embedding-model-with-datasets-for","slug":"a-body-part-embedding-model-with-datasets-for","title":"A Body Part Embedding Model With Datasets for Measuring 2D Human Motion Similarity","date":"2021-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-action-recognition-towards-novel","slug":"one-shot-action-recognition-towards-novel","title":"One-shot action recognition in challenging therapy scenarios","date":"2021-02-17","arxiv_id":"2102.08997","repositories_listed":1,"syntology":null},{"url":"/paper/win-fail-action-recognition","slug":"win-fail-action-recognition","title":"Win-Fail Action Recognition","date":"2021-02-15","arxiv_id":"2102.07355","repositories_listed":1,"syntology":null},{"url":"/paper/learning-self-similarity-in-space-and-time-as-1","slug":"learning-self-similarity-in-space-and-time-as-1","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","date":"2021-02-14","arxiv_id":"2102.07092","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-self-similarity-in-space-and-time-as-1#ran","syntology_url":"https://syntology.ai/paper/2102.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07092"}},"official":{"repos":["arunos728/SELFY"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-action-recognition-with","slug":"semi-supervised-action-recognition-with","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","date":"2021-02-04","arxiv_id":"2102.02751","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semi-supervised-action-recognition-with#ran","syntology_url":"https://syntology.ai/paper/2102.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02751"}},"official":{"repos":["CVIR/TCL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-transformer-network","slug":"video-transformer-network","title":"Video Transformer Network","date":"2021-02-01","arxiv_id":"2102.00719","repositories_listed":1,"syntology":null},{"url":"/paper/ntu60-x-towards-skeleton-based-recognition-of","slug":"ntu60-x-towards-skeleton-based-recognition-of","title":"NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions","date":"2021-01-27","arxiv_id":"2101.11529","repositories_listed":1,"syntology":null},{"url":"/paper/syntactically-guided-generative-embeddings-1","slug":"syntactically-guided-generative-embeddings-1","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","date":"2021-01-27","arxiv_id":"2101.11530","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-action-recognition-with-prototype","slug":"few-shot-action-recognition-with-prototype","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","date":"2021-01-20","arxiv_id":"2101.08085","repositories_listed":1,"syntology":null},{"url":"/paper/tclr-temporal-contrastive-learning-for-video","slug":"tclr-temporal-contrastive-learning-for-video","title":"TCLR: Temporal Contrastive Learning for Video Representation","date":"2021-01-20","arxiv_id":"2101.07974","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tclr-temporal-contrastive-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2101.07974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07974"}},"official":{"repos":["DAVEISHAN/TCLR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/temporally-guided-articulated-hand-pose","slug":"temporally-guided-articulated-hand-pose","title":"Temporally Guided Articulated Hand Pose Tracking in Surgical Videos","date":"2021-01-12","arxiv_id":"2101.04281","repositories_listed":1,"syntology":null},{"url":"/paper/learning-self-similarity-in-space-and-time-as","slug":"learning-self-similarity-in-space-and-time-as","title":"Learning Self-Similarity in Space and Time as a Generalized Motion for Action Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tensor-representations-for-action-recognition","slug":"tensor-representations-for-action-recognition","title":"Tensor Representations for Action Recognition","date":"2020-12-28","arxiv_id":"2012.14371","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-dml-deep-metric-learning-for","slug":"skeleton-dml-deep-metric-learning-for","title":"Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition","date":"2020-12-26","arxiv_id":"2012.13823","repositories_listed":1,"syntology":null},{"url":"/paper/tdn-temporal-difference-networks-for","slug":"tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","arxiv_id":"2012.10071","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tdn-temporal-difference-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.10071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10071"}},"official":{"repos":["MCG-NJU/TDN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flavr-flow-agnostic-video-representations-for","slug":"flavr-flow-agnostic-video-representations-for","title":"FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation","date":"2020-12-15","arxiv_id":"2012.08512","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/online-action-recognition","slug":"online-action-recognition","title":"Online Action Recognition","date":"2020-12-14","arxiv_id":"2012.07464","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-relational-modeling-with-self","slug":"temporal-relational-modeling-with-self","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","date":"2020-12-14","arxiv_id":"2012.07508","repositories_listed":1,"syntology":null},{"url":"/paper/msaf-multimodal-split-attention-fusion","slug":"msaf-multimodal-split-attention-fusion","title":"MSAF: Multimodal Split Attention Fusion","date":"2020-12-13","arxiv_id":"2012.07175","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-study-of-deep-video-action","slug":"a-comprehensive-study-of-deep-video-action","title":"A Comprehensive Study of Deep Video Action Recognition","date":"2020-12-11","arxiv_id":"2012.06567","repositories_listed":1,"syntology":null},{"url":"/paper/avinet-diving-deep-into-audio-visual-saliency","slug":"avinet-diving-deep-into-audio-visual-saliency","title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","date":"2020-12-11","arxiv_id":"2012.06170","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-temporal-transformer-network-for-1","slug":"spatial-temporal-transformer-network-for-1","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","date":"2020-12-11","arxiv_id":"2012.06399","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-fusion-of-multi-level-features","slug":"interactive-fusion-of-multi-level-features","title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","date":"2020-12-10","arxiv_id":"2012.05689","repositories_listed":1,"syntology":null},{"url":"/paper/learning-view-disentangled-human-pose","slug":"learning-view-disentangled-human-pose","title":"Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization","date":"2020-12-02","arxiv_id":"2012.01405","repositories_listed":1,"syntology":null},{"url":"/paper/video-anomaly-detection-by-estimating","slug":"video-anomaly-detection-by-estimating","title":"Video Anomaly Detection by Estimating Likelihood of Representations","date":"2020-12-02","arxiv_id":"2012.01468","repositories_listed":1,"syntology":null},{"url":"/paper/diverse-temporal-aggregation-and-depthwise","slug":"diverse-temporal-aggregation-and-depthwise","title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","date":"2020-12-01","arxiv_id":"2012.00317","repositories_listed":1,"syntology":null}],"record_sha256":"3f548959a33812f6d645d07c246b976bf5e1e4d2d6d46fcc8c689d535168bbd6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}