{"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/7","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":7,"pages_in_order":28,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/action-recognition-in-videos/papers/8","papers":[{"url":"/paper/goca-guided-online-cluster-assignment-for","slug":"goca-guided-online-cluster-assignment-for","title":"GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning","date":"2022-07-20","arxiv_id":"2207.10158","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchically-self-supervised-transformer","slug":"hierarchically-self-supervised-transformer","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","date":"2022-07-20","arxiv_id":"2207.09644","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":5,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierarchically-self-supervised-transformer#ran","syntology_url":"https://syntology.ai/paper/2207.09644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09644"}},"official":{"repos":["yuxiaochen1103/Hi-TRS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/task-adaptive-spatial-temporal-video-sampler","slug":"task-adaptive-spatial-temporal-video-sampler","title":"Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition","date":"2022-07-20","arxiv_id":"2207.09759","repositories_listed":1,"syntology":null},{"url":"/paper/time-is-matter-temporal-self-supervision-for","slug":"time-is-matter-temporal-self-supervision-for","title":"Time Is MattEr: Temporal Self-supervision for Video Transformers","date":"2022-07-19","arxiv_id":"2207.09067","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/time-is-matter-temporal-self-supervision-for#ran","syntology_url":"https://syntology.ai/paper/2207.09067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09067"}},"official":{"repos":["alinlab/temporal-selfsupervision"],"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/learning-from-temporal-spatial-cubism-for","slug":"learning-from-temporal-spatial-cubism-for","title":"Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition","date":"2022-07-17","arxiv_id":"2207.08095","repositories_listed":1,"syntology":null},{"url":"/paper/is-appearance-free-action-recognition","slug":"is-appearance-free-action-recognition","title":"Is Appearance Free Action Recognition Possible?","date":"2022-07-13","arxiv_id":"2207.06261","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-human-vision-inspired-action","slug":"efficient-human-vision-inspired-action","title":"Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling","date":"2022-07-12","arxiv_id":"2207.05249","repositories_listed":1,"syntology":null},{"url":"/paper/skeletal-human-action-recognition-using","slug":"skeletal-human-action-recognition-using","title":"Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network","date":"2022-07-12","arxiv_id":"2207.05493","repositories_listed":1,"syntology":null},{"url":"/paper/vidconv-a-modernized-2d-convnet-for-efficient","slug":"vidconv-a-modernized-2d-convnet-for-efficient","title":"VidConv: A modernized 2D ConvNet for Efficient Video Recognition","date":"2022-07-08","arxiv_id":"2207.03782","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-from-spatio-temporal","slug":"contrastive-learning-from-spatio-temporal","title":"Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition","date":"2022-07-07","arxiv_id":"2207.03065","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-robustness-analysis-of-video","slug":"large-scale-robustness-analysis-of-video","title":"Large-scale Robustness Analysis of Video Action Recognition Models","date":"2022-07-04","arxiv_id":"2207.01398","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-based-action-recognition-via-1","slug":"skeleton-based-action-recognition-via-1","title":"Skeleton-based Action Recognition via Adaptive Cross-Form Learning","date":"2022-06-30","arxiv_id":"2206.15085","repositories_listed":1,"syntology":null},{"url":"/paper/multi-scale-spatial-temporal-graph","slug":"multi-scale-spatial-temporal-graph","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","date":"2022-06-27","arxiv_id":"2206.13028","repositories_listed":1,"syntology":{"n":26,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/multi-scale-spatial-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2206.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13028"}},"official":{"repos":["czhaneva/mst-gcn"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-efficient-image-to-video-transfer","slug":"parameter-efficient-image-to-video-transfer","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","date":"2022-06-27","arxiv_id":"2206.13559","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/parameter-efficient-image-to-video-transfer#ran","syntology_url":"https://syntology.ai/paper/2206.13559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13559"}},"official":{"repos":["linziyi96/st-adapter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-viewpoint-agnostic-visual","slug":"learning-viewpoint-agnostic-visual","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","date":"2022-06-23","arxiv_id":"2206.11895","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"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, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-viewpoint-agnostic-visual#ran","syntology_url":"https://syntology.ai/paper/2206.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11895"}},"official":{"repos":["elicassion/3dtrl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/analysis-and-extensions-of-adversarial","slug":"analysis-and-extensions-of-adversarial","title":"Analysis and Extensions of Adversarial Training for Video Classification","date":"2022-06-16","arxiv_id":"2206.07953","repositories_listed":1,"syntology":null},{"url":"/paper/stand-alone-inter-frame-attention-in-video-1","slug":"stand-alone-inter-frame-attention-in-video-1","title":"Stand-Alone Inter-Frame Attention in Video Models","date":"2022-06-14","arxiv_id":"2206.06931","repositories_listed":1,"syntology":null},{"url":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1","slug":"a-deeper-dive-into-what-deep-spatiotemporal-1","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","date":"2022-06-06","arxiv_id":"2206.02846","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1#ran","syntology_url":"https://syntology.ai/paper/2206.02846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02846"}},"official":{"repos":["YorkUCVIL/Static-Dynamic-Interpretability"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-spike-gating-flow-a-hierarchical","slug":"the-spike-gating-flow-a-hierarchical","title":"The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition","date":"2022-06-04","arxiv_id":"2206.01910","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-video-action-recognition-in","slug":"a-survey-on-video-action-recognition-in","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","date":"2022-06-02","arxiv_id":"2206.01038","repositories_listed":1,"syntology":null},{"url":"/paper/stargazer-a-transformer-based-driver-action","slug":"stargazer-a-transformer-based-driver-action","title":"Stargazer: A transformer-based driver action detection system for intelligent transportation","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-based-action-recognition-via","slug":"skeleton-based-action-recognition-via","title":"Skeleton-based Action Recognition via Temporal-Channel Aggregation","date":"2022-05-31","arxiv_id":"2205.15936","repositories_listed":1,"syntology":null},{"url":"/paper/pstnet-point-spatio-temporal-convolution-on-1","slug":"pstnet-point-spatio-temporal-convolution-on-1","title":"PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences","date":"2022-05-27","arxiv_id":"2205.13713","repositories_listed":1,"syntology":null},{"url":"/paper/cross-architecture-self-supervised-video","slug":"cross-architecture-self-supervised-video","title":"Cross-Architecture Self-supervised Video Representation Learning","date":"2022-05-26","arxiv_id":"2205.13313","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/cross-architecture-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2205.13313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13313"}},"official":{"repos":["guoshengcv/cacl"],"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/mmnet-a-model-based-multimodal-network-for","slug":"mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pso-convolutional-neural-networks-with","slug":"pso-convolutional-neural-networks-with","title":"PSO-Convolutional Neural Networks with Heterogeneous Learning Rate","date":"2022-05-20","arxiv_id":"2205.10456","repositories_listed":1,"syntology":null},{"url":"/paper/pyskl-towards-good-practices-for-skeleton","slug":"pyskl-towards-good-practices-for-skeleton","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","date":"2022-05-19","arxiv_id":"2205.09443","repositories_listed":1,"syntology":null},{"url":"/paper/transrank-self-supervised-video","slug":"transrank-self-supervised-video","title":"TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition","date":"2022-05-04","arxiv_id":"2205.02028","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-relation-guided-set-matching-for-few","slug":"hybrid-relation-guided-set-matching-for-few","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","date":"2022-04-28","arxiv_id":"2204.13423","repositories_listed":1,"syntology":null},{"url":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-human-action-recognition-with","slug":"unsupervised-human-action-recognition-with","title":"Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance","date":"2022-04-21","arxiv_id":"2204.10312","repositories_listed":1,"syntology":null},{"url":"/paper/animal-kingdom-a-large-and-diverse-dataset","slug":"animal-kingdom-a-large-and-diverse-dataset","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","date":"2022-04-18","arxiv_id":"2204.08129","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-alignment-networks-for-long-term","slug":"temporal-alignment-networks-for-long-term","title":"Temporal Alignment Networks for Long-term Video","date":"2022-04-06","arxiv_id":"2204.02968","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-alignment-networks-for-long-term#ran","syntology_url":"https://syntology.ai/paper/2204.02968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02968"}},"official":null}},{"url":"/paper/occamnets-mitigating-dataset-bias-by-favoring","slug":"occamnets-mitigating-dataset-bias-by-favoring","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","date":"2022-04-05","arxiv_id":"2204.02426","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/occamnets-mitigating-dataset-bias-by-favoring#ran","syntology_url":"https://syntology.ai/paper/2204.02426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02426"}},"official":{"repos":["erobic/occam-nets-v1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/tallformer-temporal-action-localization-with","slug":"tallformer-temporal-action-localization-with","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","date":"2022-04-04","arxiv_id":"2204.01680","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tallformer-temporal-action-localization-with#ran","syntology_url":"https://syntology.ai/paper/2204.01680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01680"}},"official":{"repos":["klauscc/tallformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stochastic-backpropagation-a-memory-efficient","slug":"stochastic-backpropagation-a-memory-efficient","title":"Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models","date":"2022-03-31","arxiv_id":"2203.16755","repositories_listed":1,"syntology":null},{"url":"/paper/cycda-unsupervised-cycle-domain-adaptation","slug":"cycda-unsupervised-cycle-domain-adaptation","title":"CycDA: Unsupervised Cycle Domain Adaptation from Image to Video","date":"2022-03-30","arxiv_id":"2203.16244","repositories_listed":1,"syntology":null},{"url":"/paper/spact-self-supervised-privacy-preservation","slug":"spact-self-supervised-privacy-preservation","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","date":"2022-03-29","arxiv_id":"2203.15205","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/spact-self-supervised-privacy-preservation#ran","syntology_url":"https://syntology.ai/paper/2203.15205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15205"}},"official":{"repos":["daveishan/spact"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/assembly101-a-large-scale-multi-view-video","slug":"assembly101-a-large-scale-multi-view-video","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","date":"2022-03-28","arxiv_id":"2203.14712","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-zero-shot-action-recognition","slug":"rethinking-zero-shot-action-recognition","title":"Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions","date":"2022-03-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/effectively-leveraging-multi-modal-features","slug":"effectively-leveraging-multi-modal-features","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","date":"2022-03-24","arxiv_id":"2203.13281","repositories_listed":1,"syntology":null},{"url":"/paper/fourier-disentangled-space-time-attention-for","slug":"fourier-disentangled-space-time-attention-for","title":"FAR: Fourier Aerial Video Recognition","date":"2022-03-21","arxiv_id":"2203.10694","repositories_listed":1,"syntology":null},{"url":"/paper/online-skeleton-based-action-recognition-with","slug":"online-skeleton-based-action-recognition-with","title":"Continual Spatio-Temporal Graph Convolutional Networks","date":"2022-03-21","arxiv_id":"2203.11009","repositories_listed":1,"syntology":null},{"url":"/paper/direcformer-a-directed-attention-in","slug":"direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","arxiv_id":"2203.10233","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/direcformer-a-directed-attention-in#ran","syntology_url":"https://syntology.ai/paper/2203.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10233"}},"official":{"repos":["uark-cviu/direcformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/group-contextualization-for-video-recognition","slug":"group-contextualization-for-video-recognition","title":"Group Contextualization for Video Recognition","date":"2022-03-18","arxiv_id":"2203.09694","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 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; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/group-contextualization-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/2203.09694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09694"}},"official":{"repos":["haoyanbin918/group-contextualization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-action-recognition-with-transformer","slug":"zero-shot-action-recognition-with-transformer","title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition","date":"2022-03-10","arxiv_id":"2203.05156","repositories_listed":1,"syntology":null},{"url":"/paper/learning-temporal-consistency-for-source-free","slug":"learning-temporal-consistency-for-source-free","title":"Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition","date":"2022-03-09","arxiv_id":"2203.04559","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"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; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-temporal-consistency-for-source-free#ran","syntology_url":"https://syntology.ai/paper/2203.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04559"}},"official":{"repos":["xuyu0010/atcon"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/quantification-of-occlusion-handling","slug":"quantification-of-occlusion-handling","title":"Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework","date":"2022-03-08","arxiv_id":"2203.04113","repositories_listed":1,"syntology":null},{"url":"/paper/domain-knowledge-informed-self-supervised","slug":"domain-knowledge-informed-self-supervised","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","date":"2022-02-28","arxiv_id":"2202.14019","repositories_listed":1,"syntology":null},{"url":"/paper/meta-path-analysis-on-spatio-temporal-graphs","slug":"meta-path-analysis-on-spatio-temporal-graphs","title":"Meta-path Analysis on Spatio-Temporal Graphs for Pedestrian Trajectory Prediction","date":"2022-02-27","arxiv_id":"2202.13427","repositories_listed":1,"syntology":null},{"url":"/paper/on-modality-bias-recognition-and-reduction","slug":"on-modality-bias-recognition-and-reduction","title":"On Modality Bias Recognition and Reduction","date":"2022-02-25","arxiv_id":"2202.12690","repositories_listed":1,"syntology":null},{"url":"/paper/student-dangerous-behavior-detection-in","slug":"student-dangerous-behavior-detection-in","title":"Student Dangerous Behavior Detection in School","date":"2022-02-19","arxiv_id":"2202.09550","repositories_listed":1,"syntology":null},{"url":"/paper/actionformer-localizing-moments-of-actions","slug":"actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","date":"2022-02-16","arxiv_id":"2202.07925","repositories_listed":1,"syntology":null},{"url":"/paper/vision-models-are-more-robust-and-fair-when","slug":"vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","arxiv_id":"2202.08360","repositories_listed":1,"syntology":null},{"url":"/paper/czu-mhad-a-multimodal-dataset-for-human","slug":"czu-mhad-a-multimodal-dataset-for-human","title":"CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors","date":"2022-02-07","arxiv_id":"2202.03283","repositories_listed":1,"syntology":null},{"url":"/paper/adg-pose-automated-dataset-generation-for","slug":"adg-pose-automated-dataset-generation-for","title":"ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation","date":"2022-02-01","arxiv_id":"2202.00753","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-temporal-information-in-a-single","slug":"capturing-temporal-information-in-a-single","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","date":"2022-01-25","arxiv_id":"2201.10394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"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; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/capturing-temporal-information-in-a-single#ran","syntology_url":"https://syntology.ai/paper/2201.10394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10394"}},"official":{"repos":["kiyoon/channel_sampling"],"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/memvit-memory-augmented-multiscale-vision","slug":"memvit-memory-augmented-multiscale-vision","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","date":"2022-01-20","arxiv_id":"2201.08383","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-10","slug":"self-supervised-video-representation-learning-10","title":"Self-supervised Video Representation Learning with Cascade Positive Retrieval","date":"2022-01-20","arxiv_id":"2201.07989","repositories_listed":1,"syntology":null},{"url":"/paper/multi-level-second-order-few-shot-learning","slug":"multi-level-second-order-few-shot-learning","title":"Multi-level Second-order Few-shot Learning","date":"2022-01-15","arxiv_id":"2201.05916","repositories_listed":1,"syntology":null},{"url":"/paper/multiview-transformers-for-video-recognition","slug":"multiview-transformers-for-video-recognition","title":"Multiview Transformers for Video Recognition","date":"2022-01-12","arxiv_id":"2201.04288","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-tuples-transformer-for","slug":"spatio-temporal-tuples-transformer-for","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","date":"2022-01-08","arxiv_id":"2201.02849","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":3,"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/spatio-temporal-tuples-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2201.02849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.02849"}},"official":{"repos":["heleiqiu/sttformer"],"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/e2-go-motion-motion-augmented-event-stream","slug":"e2-go-motion-motion-augmented-event-stream","title":"E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/infogcn-representation-learning-for-human","slug":"infogcn-representation-learning-for-human","title":"InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/recur-attend-or-convolve-frame-dependency","slug":"recur-attend-or-convolve-frame-dependency","title":"Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition","date":"2021-12-22","arxiv_id":"2112.12175","repositories_listed":1,"syntology":null},{"url":"/paper/precondition-and-effect-reasoning-for-action","slug":"precondition-and-effect-reasoning-for-action","title":"Precondition and Effect Reasoning for Action Recognition","date":"2021-12-19","arxiv_id":"2112.10057","repositories_listed":1,"syntology":null},{"url":"/paper/tell-me-what-you-see-a-zero-shot-action","slug":"tell-me-what-you-see-a-zero-shot-action","title":"Tell me what you see: A zero-shot action recognition method based on natural language descriptions","date":"2021-12-18","arxiv_id":"2112.09976","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-and-evaluation-of-kinect-based","slug":"analysis-and-evaluation-of-kinect-based","title":"Analysis and Evaluation of Kinect-based Action Recognition Algorithms","date":"2021-12-16","arxiv_id":"2112.08626","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-object-states-vs-detecting-objects","slug":"detecting-object-states-vs-detecting-objects","title":"Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study","date":"2021-12-15","arxiv_id":"2112.08281","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-shuffling-for-defending-deep-action","slug":"temporal-shuffling-for-defending-deep-action","title":"Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks","date":"2021-12-15","arxiv_id":"2112.07921","repositories_listed":1,"syntology":null},{"url":"/paper/svip-sequence-verification-for-procedures-in","slug":"svip-sequence-verification-for-procedures-in","title":"SVIP: Sequence VerIfication for Procedures in Videos","date":"2021-12-13","arxiv_id":"2112.06447","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-relation-modeling-for-few","slug":"spatio-temporal-relation-modeling-for-few","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","date":"2021-12-09","arxiv_id":"2112.05132","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-visual-language-models-for","slug":"prompting-visual-language-models-for","title":"Prompting Visual-Language Models for Efficient Video Understanding","date":"2021-12-08","arxiv_id":"2112.04478","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prompting-visual-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2112.04478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04478"}},"official":{"repos":["ju-chen/Efficient-Prompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/topology-aware-convolutional-neural-network","slug":"topology-aware-convolutional-neural-network","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","date":"2021-12-08","arxiv_id":"2112.04178","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-from-extremely-augmented","slug":"contrastive-learning-from-extremely-augmented","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","date":"2021-12-07","arxiv_id":"2112.03590","repositories_listed":1,"syntology":null},{"url":"/paper/e-2-go-motion-motion-augmented-event-stream","slug":"e-2-go-motion-motion-augmented-event-stream","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","date":"2021-12-07","arxiv_id":"2112.03596","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-continuous-manifold-learning-for","slug":"efficient-continuous-manifold-learning-for","title":"Deep Efficient Continuous Manifold Learning for Time Series Modeling","date":"2021-12-03","arxiv_id":"2112.03379","repositories_listed":1,"syntology":null},{"url":"/paper/bevt-bert-pretraining-of-video-transformers","slug":"bevt-bert-pretraining-of-video-transformers","title":"BEVT: BERT Pretraining of Video Transformers","date":"2021-12-02","arxiv_id":"2112.01529","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-transformer","slug":"self-supervised-video-transformer","title":"Self-supervised Video Transformer","date":"2021-12-02","arxiv_id":"2112.01514","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/self-supervised-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2112.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01514"}},"official":{"repos":["kahnchana/svt"],"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/dynamic-normalization-and-relay-for-video","slug":"dynamic-normalization-and-relay-for-video","title":"Dynamic Normalization and Relay for Video Action Recognition","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mau-a-motion-aware-unit-for-video-prediction","slug":"mau-a-motion-aware-unit-for-video-prediction","title":"MAU: A Motion-Aware Unit for Video Prediction and Beyond","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/anonymization-for-skeleton-action-recognition","slug":"anonymization-for-skeleton-action-recognition","title":"Anonymization for Skeleton Action Recognition","date":"2021-11-30","arxiv_id":"2111.15129","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-temporal-gradient-for-semi","slug":"learning-from-temporal-gradient-for-semi","title":"Learning from Temporal Gradient for Semi-supervised Action Recognition","date":"2021-11-25","arxiv_id":"2111.13241","repositories_listed":1,"syntology":null},{"url":"/paper/m2a-motion-aware-attention-for-accurate-video","slug":"m2a-motion-aware-attention-for-accurate-video","title":"M2A: Motion Aware Attention for Accurate Video Action Recognition","date":"2021-11-18","arxiv_id":"2111.09976","repositories_listed":1,"syntology":null},{"url":"/paper/sequentialpointnet-a-strong-parallelized","slug":"sequentialpointnet-a-strong-parallelized","title":"Real-time 3D human action recognition based on Hyperpoint sequence","date":"2021-11-16","arxiv_id":"2111.08492","repositories_listed":1,"syntology":null},{"url":"/paper/ubnormal-new-benchmark-for-supervised-open","slug":"ubnormal-new-benchmark-for-supervised-open","title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","date":"2021-11-16","arxiv_id":"2111.08644","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":1,"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/ubnormal-new-benchmark-for-supervised-open#ran","syntology_url":"https://syntology.ai/paper/2111.08644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08644"}},"official":{"repos":["lilygeorgescu/ubnormal"],"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/a-central-difference-graph-convolutional","slug":"a-central-difference-graph-convolutional","title":"A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition","date":"2021-11-13","arxiv_id":"2111.06995","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-modeling-for-action-1","slug":"sequence-to-sequence-modeling-for-action-1","title":"Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution","date":"2021-11-03","arxiv_id":"2111.02521","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sequence-to-sequence-modeling-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2111.02521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02521"}},"official":null}},{"url":"/paper/relational-self-attention-what-s-missing-in","slug":"relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","arxiv_id":"2111.01673","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/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}},"official":{"repos":["KimManjin/RSA"],"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/revisiting-spatio-temporal-layouts-for","slug":"revisiting-spatio-temporal-layouts-for","title":"Revisiting spatio-temporal layouts for compositional action recognition","date":"2021-11-02","arxiv_id":"2111.01936","repositories_listed":1,"syntology":null},{"url":"/paper/metavd-a-meta-video-dataset-for-enhancing","slug":"metavd-a-meta-video-dataset-for-enhancing","title":"MetaVD: A Meta Video Dataset for enhancing human action recognition datasets","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/re-id-ar-improved-person-re-identification-in","slug":"re-id-ar-improved-person-re-identification-in","title":"Re-ID-AR: Improved Person Re-identification in Video via Joint Weakly Supervised Action Recognition","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/with-a-little-help-from-my-temporal-context","slug":"with-a-little-help-from-my-temporal-context","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","date":"2021-11-01","arxiv_id":"2111.01024","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-action-recognition-from-diverse","slug":"zero-shot-action-recognition-from-diverse","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","date":"2021-10-26","arxiv_id":"2110.13479","repositories_listed":1,"syntology":null},{"url":"/paper/a-variational-graph-autoencoder-for","slug":"a-variational-graph-autoencoder-for","title":"A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction","date":"2021-10-25","arxiv_id":"2110.13280","repositories_listed":1,"syntology":null},{"url":"/paper/logsig-rnn-a-novel-network-for-robust-and","slug":"logsig-rnn-a-novel-network-for-robust-and","title":"Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition","date":"2021-10-25","arxiv_id":"2110.13008","repositories_listed":1,"syntology":null},{"url":"/paper/lstc-boosting-atomic-action-detection-with","slug":"lstc-boosting-atomic-action-detection-with","title":"LSTC: Boosting Atomic Action Detection with Long-Short-Term Context","date":"2021-10-19","arxiv_id":"2110.09819","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-debiasing-inference-for","slug":"counterfactual-debiasing-inference-for","title":"Counterfactual Debiasing Inference for Compositional Action Recognition","date":"2021-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/team-net-multi-modal-learning-for-video","slug":"team-net-multi-modal-learning-for-video","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","date":"2021-10-17","arxiv_id":"2110.08814","repositories_listed":1,"syntology":null},{"url":"/paper/video-based-cattle-identification-and-action","slug":"video-based-cattle-identification-and-action","title":"Video-based cattle identification and action recognition","date":"2021-10-14","arxiv_id":"2110.07103","repositories_listed":1,"syntology":null}],"record_sha256":"05b2f5b1d992eeddd0aed795f6108a5d096bee251b405be0e6ab4fb30bd1c3b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}