{"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/4","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":4,"pages_in_order":28,"rows_per_page":100,"rows":[301,400],"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/3","next":"/task/action-recognition-in-videos/papers/5","papers":[{"url":"/paper/self-supervised-contrastive-learning-for-9","slug":"self-supervised-contrastive-learning-for-9","title":"Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment","date":"2024-09-06","arxiv_id":"2409.04607","repositories_listed":1,"syntology":null},{"url":"/paper/tasar-transferable-attack-on-skeletal-action","slug":"tasar-transferable-attack-on-skeletal-action","title":"TASAR: Transfer-based Attack on Skeletal Action Recognition","date":"2024-09-04","arxiv_id":"2409.02483","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tasar-transferable-attack-on-skeletal-action#ran","syntology_url":"https://syntology.ai/paper/2409.02483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02483"}},"official":{"repos":["yunfengdiao/Skeleton-Robustness-Benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/respike-residual-frames-based-hybrid-spiking","slug":"respike-residual-frames-based-hybrid-spiking","title":"ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition","date":"2024-09-03","arxiv_id":"2409.01564","repositories_listed":1,"syntology":null},{"url":"/paper/fisher-information-guided-purification","slug":"fisher-information-guided-purification","title":"Fisher Information guided Purification against Backdoor Attacks","date":"2024-09-01","arxiv_id":"2409.00863","repositories_listed":1,"syntology":null},{"url":"/paper/dear-depth-enhanced-action-recognition","slug":"dear-depth-enhanced-action-recognition","title":"DEAR: Depth-Enhanced Action Recognition","date":"2024-08-28","arxiv_id":"2408.15679","repositories_listed":1,"syntology":null},{"url":"/paper/comparative-analysis-violence-recognition","slug":"comparative-analysis-violence-recognition","title":"Comparative Analysis: Violence Recognition from Videos using Transfer Learning","date":"2024-08-26","arxiv_id":"2408.14659","repositories_listed":1,"syntology":null},{"url":"/paper/twlv-i-analysis-and-insights-from-holistic","slug":"twlv-i-analysis-and-insights-from-holistic","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","date":"2024-08-21","arxiv_id":"2408.11318","repositories_listed":1,"syntology":null},{"url":"/paper/tds-clip-temporal-difference-side-network-for","slug":"tds-clip-temporal-difference-side-network-for","title":"TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning","date":"2024-08-20","arxiv_id":"2408.10688","repositories_listed":1,"syntology":null},{"url":"/paper/event-stream-based-human-action-recognition-a","slug":"event-stream-based-human-action-recognition-a","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","date":"2024-08-19","arxiv_id":"2408.09764","repositories_listed":1,"syntology":null},{"url":"/paper/sharp-segmentation-of-hands-and-arms-by-range","slug":"sharp-segmentation-of-hands-and-arms-by-range","title":"SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition","date":"2024-08-19","arxiv_id":"2408.10037","repositories_listed":1,"syntology":null},{"url":"/paper/action-recognition-for-privacy-preserving","slug":"action-recognition-for-privacy-preserving","title":"Action Recognition for Privacy-Preserving Ambient Assisted Living","date":"2024-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/epam-net-an-efficient-pose-driven-attention","slug":"epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","arxiv_id":"2408.05421","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02769","slug":"2408-02769","title":"From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation","date":"2024-08-05","arxiv_id":"2408.02769","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-based-action-recognition-with-3","slug":"skeleton-based-action-recognition-with-3","title":"Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution","date":"2024-07-31","arxiv_id":"2407.21525","repositories_listed":1,"syntology":null},{"url":"/paper/joint-partition-group-attention-for-skeleton","slug":"joint-partition-group-attention-for-skeleton","title":"Joint-Partition Group Attention for skeleton-based action recognition","date":"2024-07-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-temporal-causality-for-advanced","slug":"harnessing-temporal-causality-for-advanced","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","date":"2024-07-25","arxiv_id":"2407.17792","repositories_listed":1,"syntology":null},{"url":"/paper/marine-a-computer-vision-model-for-detecting","slug":"marine-a-computer-vision-model-for-detecting","title":"MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal Videos","date":"2024-07-25","arxiv_id":"2407.18289","repositories_listed":1,"syntology":null},{"url":"/paper/soap-enhancing-spatio-temporal-relation-and","slug":"soap-enhancing-spatio-temporal-relation-and","title":"SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition","date":"2024-07-23","arxiv_id":"2407.16344","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modality-co-learning-for-efficient-1","slug":"multi-modality-co-learning-for-efficient-1","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","date":"2024-07-22","arxiv_id":"2407.15706","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-modality-co-learning-for-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2407.15706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15706"}},"official":{"repos":["liujf69/MMCL-Action"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/quiil-at-t3-challenge-towards-automation-in","slug":"quiil-at-t3-challenge-towards-automation-in","title":"QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person View","date":"2024-07-18","arxiv_id":"2407.13216","repositories_listed":1,"syntology":null},{"url":"/paper/sa-dvae-improving-zero-shot-skeleton-based","slug":"sa-dvae-improving-zero-shot-skeleton-based","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","date":"2024-07-18","arxiv_id":"2407.13460","repositories_listed":1,"syntology":null},{"url":"/paper/frequency-guidance-matters-skeletal-action","slug":"frequency-guidance-matters-skeletal-action","title":"Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer","date":"2024-07-17","arxiv_id":"2407.12322","repositories_listed":1,"syntology":null},{"url":"/paper/shap-mix-shapley-value-guided-mixing-for-long","slug":"shap-mix-shapley-value-guided-mixing-for-long","title":"Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition","date":"2024-07-17","arxiv_id":"2407.12312","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-split-computing-and-early-exit","slug":"enhancing-split-computing-and-early-exit","title":"Enhancing Split Computing and Early Exit Applications through Predefined Sparsity","date":"2024-07-16","arxiv_id":"2407.11763","repositories_listed":1,"syntology":null},{"url":"/paper/stars-self-supervised-tuning-for-3d-action","slug":"stars-self-supervised-tuning-for-3d-action","title":"STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences","date":"2024-07-15","arxiv_id":"2407.10935","repositories_listed":1,"syntology":null},{"url":"/paper/augmented-neural-fine-tuning-for-efficient","slug":"augmented-neural-fine-tuning-for-efficient","title":"Augmented Neural Fine-Tuning for Efficient Backdoor Purification","date":"2024-07-14","arxiv_id":"2407.10052","repositories_listed":1,"syntology":null},{"url":"/paper/c2c-component-to-composition-learning-for","slug":"c2c-component-to-composition-learning-for","title":"C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition","date":"2024-07-08","arxiv_id":"2407.06113","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/c2c-component-to-composition-learning-for#ran","syntology_url":"https://syntology.ai/paper/2407.06113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06113"}},"official":{"repos":["rongchangli/zscar_c2c"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dailydvs-200-a-comprehensive-benchmark","slug":"dailydvs-200-a-comprehensive-benchmark","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","date":"2024-07-06","arxiv_id":"2407.05106","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"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) · 6 unverified","sample_list":"/paper/dailydvs-200-a-comprehensive-benchmark#ran","syntology_url":"https://syntology.ai/paper/2407.05106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05106"}},"official":{"repos":["qiwang233/dailydvs-200"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/awt-transferring-vision-language-models-via","slug":"awt-transferring-vision-language-models-via","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","date":"2024-07-05","arxiv_id":"2407.04603","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/awt-transferring-vision-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2407.04603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04603"}},"official":{"repos":["MCG-NJU/AWT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/computer-vision-for-clinical-gait-analysis-a","slug":"computer-vision-for-clinical-gait-analysis-a","title":"Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset","date":"2024-07-05","arxiv_id":"2407.04190","repositories_listed":1,"syntology":null},{"url":"/paper/motion-meets-attention-video-motion-prompts","slug":"motion-meets-attention-video-motion-prompts","title":"Motion meets Attention: Video Motion Prompts","date":"2024-07-03","arxiv_id":"2407.03179","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motion-meets-attention-video-motion-prompts#ran","syntology_url":"https://syntology.ai/paper/2407.03179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03179"}},"official":{"repos":["q1xiangchen/vmps"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/advancing-compressed-video-action-recognition","slug":"advancing-compressed-video-action-recognition","title":"Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation","date":"2024-07-02","arxiv_id":"2407.02713","repositories_listed":1,"syntology":null},{"url":"/paper/referring-atomic-video-action-recognition","slug":"referring-atomic-video-action-recognition","title":"Referring Atomic Video Action Recognition","date":"2024-07-02","arxiv_id":"2407.01872","repositories_listed":1,"syntology":null},{"url":"/paper/mask-and-compress-efficient-skeleton-based","slug":"mask-and-compress-efficient-skeleton-based","title":"Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning","date":"2024-07-01","arxiv_id":"2407.01397","repositories_listed":1,"syntology":null},{"url":"/paper/graph-in-graph-neural-network","slug":"graph-in-graph-neural-network","title":"Graph in Graph Neural Network","date":"2024-06-30","arxiv_id":"2407.00696","repositories_listed":1,"syntology":null},{"url":"/paper/videomambapro-a-leap-forward-for-mamba-in","slug":"videomambapro-a-leap-forward-for-mamba-in","title":"Snakes and Ladders: Two Steps Up for VideoMamba","date":"2024-06-27","arxiv_id":"2406.19006","repositories_listed":1,"syntology":null},{"url":"/paper/egovideo-exploring-egocentric-foundation","slug":"egovideo-exploring-egocentric-foundation","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","date":"2024-06-26","arxiv_id":"2406.18070","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egovideo-exploring-egocentric-foundation#ran","syntology_url":"https://syntology.ai/paper/2406.18070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18070"}},"official":{"repos":["opengvlab/egovideo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/expressive-keypoints-for-skeleton-based","slug":"expressive-keypoints-for-skeleton-based","title":"Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation","date":"2024-06-26","arxiv_id":"2406.18011","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-hand-gesture-recognition","slug":"real-time-hand-gesture-recognition","title":"Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN","date":"2024-06-21","arxiv_id":"2406.15003","repositories_listed":1,"syntology":null},{"url":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","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":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/part-aware-unified-representation-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2406.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13327"}},"official":{"repos":["azzh1/purls"],"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/enhancing-human-action-recognition-with-gan","slug":"enhancing-human-action-recognition-with-gan","title":"Enhancing human action recognition with GAN-based data augmentation","date":"2024-06-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/smart-scene-motion-aware-human-action","slug":"smart-scene-motion-aware-human-action","title":"SMART: Scene-motion-aware human action recognition framework for mental disorder group","date":"2024-06-07","arxiv_id":"2406.04649","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-skeleton-action","slug":"self-supervised-skeleton-action","title":"Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond","date":"2024-06-05","arxiv_id":"2406.02978","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-meets-the-skeleton","slug":"vision-language-meets-the-skeleton","title":"Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning","date":"2024-05-31","arxiv_id":"2405.20606","repositories_listed":1,"syntology":null},{"url":"/paper/egosurgery-phase-a-dataset-of-surgical-phase","slug":"egosurgery-phase-a-dataset-of-surgical-phase","title":"EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery Videos","date":"2024-05-30","arxiv_id":"2405.19644","repositories_listed":1,"syntology":null},{"url":"/paper/from-forest-to-zoo-great-ape-behavior","slug":"from-forest-to-zoo-great-ape-behavior","title":"From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave","date":"2024-05-30","arxiv_id":"2405.20025","repositories_listed":1,"syntology":null},{"url":"/paper/egonce-do-egocentric-video-language-models","slug":"egonce-do-egocentric-video-language-models","title":"EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?","date":"2024-05-28","arxiv_id":"2405.17719","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 1 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/egonce-do-egocentric-video-language-models#ran","syntology_url":"https://syntology.ai/paper/2405.17719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17719"}},"official":{"repos":["xuboshen/egoncepp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flow-snapshot-neurons-in-action-deep-neural","slug":"flow-snapshot-neurons-in-action-deep-neural","title":"Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception","date":"2024-05-26","arxiv_id":"2405.16493","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-or-fine-recognising-action-end-states","slug":"coarse-or-fine-recognising-action-end-states","title":"Coarse or Fine? Recognising Action End States without Labels","date":"2024-05-13","arxiv_id":"2405.07723","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-efficient-and-effective-point","slug":"rethinking-efficient-and-effective-point","title":"Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba","date":"2024-05-09","arxiv_id":"2405.06116","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rethinking-efficient-and-effective-point#ran","syntology_url":"https://syntology.ai/paper/2405.06116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06116"}},"official":{"repos":["rhwxmx/eventmamba"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hdbn-a-novel-hybrid-dual-branch-network-for","slug":"hdbn-a-novel-hybrid-dual-branch-network-for","title":"HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition","date":"2024-04-24","arxiv_id":"2404.15719","repositories_listed":1,"syntology":null},{"url":"/paper/cofinal-enhancing-action-quality-assessment","slug":"cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","date":"2024-04-22","arxiv_id":"2404.13999","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cofinal-enhancing-action-quality-assessment#ran","syntology_url":"https://syntology.ai/paper/2404.13999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13999"}},"official":{"repos":["zhoukanglei/cofinal_aqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/attack-on-scene-flow-using-point-clouds","slug":"attack-on-scene-flow-using-point-clouds","title":"Attack on Scene Flow using Point Clouds","date":"2024-04-21","arxiv_id":"2404.13621","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-actions-and-walking-to-llm-generated","slug":"aligning-actions-and-walking-to-llm-generated","title":"Aligning Actions and Walking to LLM-Generated Textual Descriptions","date":"2024-04-18","arxiv_id":"2404.12192","repositories_listed":1,"syntology":null},{"url":"/paper/vg4d-vision-language-model-goes-4d-video","slug":"vg4d-vision-language-model-goes-4d-video","title":"VG4D: Vision-Language Model Goes 4D Video Recognition","date":"2024-04-17","arxiv_id":"2404.11605","repositories_listed":1,"syntology":null},{"url":"/paper/in-my-perspective-in-my-hands-accurate","slug":"in-my-perspective-in-my-hands-accurate","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","date":"2024-04-14","arxiv_id":"2404.09308","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/in-my-perspective-in-my-hands-accurate#ran","syntology_url":"https://syntology.ai/paper/2404.09308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09308"}},"official":{"repos":["wiktormucha/effhandegonet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-attack-detection-for-action","slug":"multimodal-attack-detection-for-action","title":"Multimodal Attack Detection for Action Recognition Models","date":"2024-04-13","arxiv_id":"2404.10790","repositories_listed":1,"syntology":null},{"url":"/paper/an-animation-based-augmentation-approach-for","slug":"an-animation-based-augmentation-approach-for","title":"An Animation-based Augmentation Approach for Action Recognition from Discontinuous Video","date":"2024-04-10","arxiv_id":"2404.06741","repositories_listed":1,"syntology":null},{"url":"/paper/actnetformer-transformer-resnet-hybrid-method","slug":"actnetformer-transformer-resnet-hybrid-method","title":"ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos","date":"2024-04-09","arxiv_id":"2404.06243","repositories_listed":1,"syntology":null},{"url":"/paper/tim-a-time-interval-machine-for-audio-visual","slug":"tim-a-time-interval-machine-for-audio-visual","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","date":"2024-04-08","arxiv_id":"2404.05559","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tim-a-time-interval-machine-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2404.05559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05559"}},"official":{"repos":["jacobchalk/tim"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangled-pre-training-for-human-object","slug":"disentangled-pre-training-for-human-object","title":"Disentangled Pre-training for Human-Object Interaction Detection","date":"2024-04-02","arxiv_id":"2404.01725","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/disentangled-pre-training-for-human-object#ran","syntology_url":"https://syntology.ai/paper/2404.01725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01725"}},"official":{"repos":["xingaoli/dp-hoi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-guided-interpretable-video","slug":"language-model-guided-interpretable-video","title":"Language Model Guided Interpretable Video Action Reasoning","date":"2024-04-02","arxiv_id":"2404.01591","repositories_listed":1,"syntology":null},{"url":"/paper/prego-online-mistake-detection-in-procedural","slug":"prego-online-mistake-detection-in-procedural","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","date":"2024-04-02","arxiv_id":"2404.01933","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prego-online-mistake-detection-in-procedural#ran","syntology_url":"https://syntology.ai/paper/2404.01933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01933"}},"official":{"repos":["aleflabo/prego"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omnivid-a-generative-framework-for-universal#ran","syntology_url":"https://syntology.ai/paper/2403.17935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17935"}},"official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/degcn-deformable-graph-convolutional-networks","slug":"degcn-deformable-graph-convolutional-networks","title":"DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2024-03-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/understanding-long-videos-in-one-multimodal","slug":"understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","date":"2024-03-25","arxiv_id":"2403.16998","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-long-videos-in-one-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}},"official":{"repos":["kahnchana/mvu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/gcn-devlstm-path-development-for-skeleton","slug":"gcn-devlstm-path-development-for-skeleton","title":"GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition","date":"2024-03-22","arxiv_id":"2403.15212","repositories_listed":1,"syntology":null},{"url":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}},"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exact-language-guided-conceptual-reasoning","slug":"exact-language-guided-conceptual-reasoning","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","date":"2024-03-19","arxiv_id":"2403.12534","repositories_listed":1,"syntology":null},{"url":"/paper/a-lie-group-approach-to-riemannian-batch","slug":"a-lie-group-approach-to-riemannian-batch","title":"A Lie Group Approach to Riemannian Batch Normalization","date":"2024-03-17","arxiv_id":"2403.11261","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-lie-group-approach-to-riemannian-batch#ran","syntology_url":"https://syntology.ai/paper/2403.11261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11261"}},"official":{"repos":["gitzh-chen/liebn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/skeleton-based-human-action-recognition-with-1","slug":"skeleton-based-human-action-recognition-with-1","title":"Skeleton-Based Human Action Recognition with Noisy Labels","date":"2024-03-15","arxiv_id":"2403.09975","repositories_listed":1,"syntology":null},{"url":"/paper/eventrpg-event-data-augmentation-with","slug":"eventrpg-event-data-augmentation-with","title":"EventRPG: Event Data Augmentation with Relevance Propagation Guidance","date":"2024-03-14","arxiv_id":"2403.09274","repositories_listed":1,"syntology":{"n":16,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/eventrpg-event-data-augmentation-with#ran","syntology_url":"https://syntology.ai/paper/2403.09274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09274"}},"official":{"repos":["myuansun/eventrpg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-utility-of-3d-hand-poses-for-action","slug":"on-the-utility-of-3d-hand-poses-for-action","title":"On the Utility of 3D Hand Poses for Action Recognition","date":"2024-03-14","arxiv_id":"2403.09805","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/on-the-utility-of-3d-hand-poses-for-action#ran","syntology_url":"https://syntology.ai/paper/2403.09805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09805"}},"official":{"repos":["s-shamil/HandFormer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/skateformer-skeletal-temporal-transformer-for","slug":"skateformer-skeletal-temporal-transformer-for","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","date":"2024-03-14","arxiv_id":"2403.09508","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skateformer-skeletal-temporal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2403.09508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09508"}},"official":{"repos":["KAIST-VICLab/SkateFormer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/attention-prompt-tuning-parameter-efficient","slug":"attention-prompt-tuning-parameter-efficient","title":"Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling","date":"2024-03-11","arxiv_id":"2403.06978","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-multimodal-cognitive-assistant-for","slug":"real-time-multimodal-cognitive-assistant-for","title":"Real-Time Multimodal Cognitive Assistant for Emergency Medical Services","date":"2024-03-11","arxiv_id":"2403.06734","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-micro-action-recognition-dataset","slug":"benchmarking-micro-action-recognition-dataset","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","date":"2024-03-08","arxiv_id":"2403.05234","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/benchmarking-micro-action-recognition-dataset#ran","syntology_url":"https://syntology.ai/paper/2403.05234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05234"}},"official":{"repos":["vut-hfut/micro-action"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-relations-of-informative-frames-in","slug":"temporal-relations-of-informative-frames-in","title":"Temporal Relations of Informative Frames in Action Recognition","date":"2024-03-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video-relationship-detection-using-mixture-of-1","slug":"video-relationship-detection-using-mixture-of-1","title":"Video Relationship Detection Using Mixture of Experts","date":"2024-03-06","arxiv_id":"2403.03994","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-clip-based-video-learners-in-cross","slug":"rethinking-clip-based-video-learners-in-cross","title":"Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition","date":"2024-03-03","arxiv_id":"2403.01560","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-3d-point-cloud-sequences-as-2d-videos","slug":"dynamic-3d-point-cloud-sequences-as-2d-videos","title":"Dynamic 3D Point Cloud Sequences as 2D Videos","date":"2024-03-02","arxiv_id":"2403.01129","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-nd-selective-state-space-modeling-for","slug":"mamba-nd-selective-state-space-modeling-for","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","date":"2024-02-08","arxiv_id":"2402.05892","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":11,"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/mamba-nd-selective-state-space-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2402.05892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05892"}},"official":{"repos":["jacklishufan/mamba-nd"],"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/froster-frozen-clip-is-a-strong-teacher-for","slug":"froster-frozen-clip-is-a-strong-teacher-for","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","date":"2024-02-05","arxiv_id":"2402.03241","repositories_listed":1,"syntology":null},{"url":"/paper/taylor-videos-for-action-recognition","slug":"taylor-videos-for-action-recognition","title":"Taylor Videos for Action Recognition","date":"2024-02-05","arxiv_id":"2402.03019","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":3,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/taylor-videos-for-action-recognition#ran","syntology_url":"https://syntology.ai/paper/2402.03019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03019"}},"official":{"repos":["leiwangr/video-ar"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":3,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-mutual-excitation-for-hand-to-hand","slug":"learning-mutual-excitation-for-hand-to-hand","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","date":"2024-02-04","arxiv_id":"2402.02431","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-mutual-excitation-for-hand-to-hand#ran","syntology_url":"https://syntology.ai/paper/2402.02431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02431"}},"official":{"repos":["nkliuyifang/me-gcn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autogcn-towards-generic-human-activity","slug":"autogcn-towards-generic-human-activity","title":"AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search","date":"2024-02-02","arxiv_id":"2402.01313","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-augmentation-training-makes","slug":"adversarial-augmentation-training-makes","title":"Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts","date":"2024-01-21","arxiv_id":"2401.11406","repositories_listed":1,"syntology":null},{"url":"/paper/image-based-human-re-identification-which","slug":"image-based-human-re-identification-which","title":"Image-based human re-identification: Which covariates are actually (the most) important?","date":"2024-01-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/haltingvt-adaptive-token-halting-transformer","slug":"haltingvt-adaptive-token-halting-transformer","title":"HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition","date":"2024-01-10","arxiv_id":"2401.04975","repositories_listed":1,"syntology":null},{"url":"/paper/explore-human-parsing-modality-for-action-1","slug":"explore-human-parsing-modality-for-action-1","title":"Explore Human Parsing Modality for Action Recognition","date":"2024-01-04","arxiv_id":"2401.02138","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/explore-human-parsing-modality-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2401.02138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02138"}},"official":{"repos":["liujf69/EPP-Net-Action"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/blockgcn-redefine-topology-awareness-for","slug":"blockgcn-redefine-topology-awareness-for","title":"BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/skeleton2vec-a-self-supervised-learning","slug":"skeleton2vec-a-self-supervised-learning","title":"Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence","date":"2024-01-01","arxiv_id":"2401.00921","repositories_listed":1,"syntology":null},{"url":"/paper/a-dense-sparse-complementary-network-for","slug":"a-dense-sparse-complementary-network-for","title":"A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities","date":"2023-12-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temp3d-temporally-continuous-3d-human-pose","slug":"temp3d-temporally-continuous-3d-human-pose","title":"STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation","date":"2023-12-24","arxiv_id":"2312.16221","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-temporal-decoupling-contrastive","slug":"spatial-temporal-decoupling-contrastive","title":"Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition","date":"2023-12-23","arxiv_id":"2312.15144","repositories_listed":1,"syntology":null},{"url":"/paper/generative-model-based-feature-knowledge","slug":"generative-model-based-feature-knowledge","title":"Generative Model-based Feature Knowledge Distillation for Action Recognition","date":"2023-12-14","arxiv_id":"2312.08644","repositories_listed":1,"syntology":null},{"url":"/paper/online-action-recognition-for-human-risk","slug":"online-action-recognition-for-human-risk","title":"Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables","date":"2023-12-14","arxiv_id":"2401.05365","repositories_listed":1,"syntology":null},{"url":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"9 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}},"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-geometric-understanding-of-spatio","slug":"towards-a-geometric-understanding-of-spatio","title":"Towards a geometric understanding of Spatio Temporal Graph Convolution Networks","date":"2023-12-12","arxiv_id":"2312.07777","repositories_listed":1,"syntology":null},{"url":"/paper/x4d-sceneformer-enhanced-scene-understanding","slug":"x4d-sceneformer-enhanced-scene-understanding","title":"X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer","date":"2023-12-12","arxiv_id":"2312.07378","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/x4d-sceneformer-enhanced-scene-understanding#ran","syntology_url":"https://syntology.ai/paper/2312.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07378"}},"official":{"repos":["jinglinglingling/x4d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"3ace5e9cba2e49abbc4656075dfd200da433a4bd4732d455ef33dd86d9d41216","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}