{"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/17","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":17,"pages_in_order":28,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/task/action-recognition-in-videos/papers/18","papers":[{"url":null,"slug":"blockwise-temporal-spatial-pathway-network","title":"Blockwise Temporal-Spatial Pathway Network","date":"2022-08-05","arxiv_id":"2208.03040","repositories_listed":0,"syntology":null},{"url":null,"slug":"combined-cnn-transformer-encoder-for-enhanced","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","date":"2022-08-03","arxiv_id":"2208.01897","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stream-transformer-architecture-for-long","title":"Two-Stream Transformer Architecture for Long Video Understanding","date":"2022-08-02","arxiv_id":"2208.01753","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-abn-learning-to-generate-sharp","title":"Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition","date":"2022-07-27","arxiv_id":"2207.13306","repositories_listed":0,"syntology":null},{"url":null,"slug":"textbf-p-2-a-a-dataset-and-benchmark-for","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","date":"2022-07-26","arxiv_id":"2207.12730","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-3d-network-protocol-for","title":"Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning","date":"2022-07-23","arxiv_id":"2207.11504","repositories_listed":0,"syntology":null},{"url":"/paper/ae-net-adjoint-enhancement-network-for","slug":"ae-net-adjoint-enhancement-network-for","title":"AE-Net:Adjoint Enhancement Network for Efficient Action Recognition in Video Understanding","date":"2022-07-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/nsnet-non-saliency-suppression-sampler-for","slug":"nsnet-non-saliency-suppression-sampler-for","title":"NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition","date":"2022-07-21","arxiv_id":"2207.10388","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-elderly-monitoring-for-senior","title":"Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition","date":"2022-07-21","arxiv_id":"2207.10519","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-saliency-query-network-for-efficient","slug":"temporal-saliency-query-network-for-efficient","title":"Temporal Saliency Query Network for Efficient Video Recognition","date":"2022-07-21","arxiv_id":"2207.10379","repositories_listed":0,"syntology":null},{"url":"/paper/multi-manifold-attention-for-vision","slug":"multi-manifold-attention-for-vision","title":"Multi-manifold Attention for Vision Transformers","date":"2022-07-18","arxiv_id":"2207.08569","repositories_listed":0,"syntology":null},{"url":null,"slug":"lava-language-audio-vision-alignment-for","title":"LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training","date":"2022-07-16","arxiv_id":"2207.08024","repositories_listed":0,"syntology":null},{"url":"/paper/action-recognition-with-motion","slug":"action-recognition-with-motion","title":"Action Recognition With Motion Diversification and Dynamic Selection","date":"2022-07-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bqn-busy-quiet-net-enabled-by-motion-band","title":"BQN: Busy-Quiet Net Enabled by Motion Band-Pass Module for Action Recognition","date":"2022-07-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compound-prototype-matching-for-few-shot","title":"Compound Prototype Matching for Few-shot Action Recognition","date":"2022-07-12","arxiv_id":"2207.05515","repositories_listed":0,"syntology":null},{"url":null,"slug":"epic-kitchens-100-unsupervised-domain-1","title":"EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022: Team HNU-FPV Technical Report","date":"2022-07-07","arxiv_id":"2207.03095","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-for-human-sensing-using","title":"Unsupervised Learning for Human Sensing Using Radio Signals","date":"2022-07-06","arxiv_id":"2207.02370","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-action-recognition-with","title":"Disentangled Action Recognition with Knowledge Bases","date":"2022-07-04","arxiv_id":"2207.01708","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-transformer-network-with-transfer","title":"Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition","date":"2022-06-30","arxiv_id":"2206.15002","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-adjacency-matrix-configuration-in-gcn","title":"A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition","date":"2022-06-29","arxiv_id":"2206.14344","repositories_listed":0,"syntology":null},{"url":null,"slug":"defending-multimodal-fusion-models-against-1","title":"Defending Multimodal Fusion Models against Single-Source Adversaries","date":"2022-06-25","arxiv_id":"2206.12714","repositories_listed":0,"syntology":null},{"url":"/paper/m-m-mix-a-multimodal-multiview-transformer","slug":"m-m-mix-a-multimodal-multiview-transformer","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","date":"2022-06-20","arxiv_id":"2206.09852","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-using-privileged-information-for","title":"Learning Using Privileged Information for Zero-Shot Action Recognition","date":"2022-06-17","arxiv_id":"2206.08632","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-training-method-for-videopose3d-with","title":"A Training Method For VideoPose3D With Ideology of Action Recognition","date":"2022-06-13","arxiv_id":"2206.06430","repositories_listed":0,"syntology":null},{"url":null,"slug":"bringing-image-scene-structure-to-video-via","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","date":"2022-06-13","arxiv_id":"2206.06346","repositories_listed":0,"syntology":null},{"url":"/paper/mlp-3d-a-mlp-like-3d-architecture-with-1","slug":"mlp-3d-a-mlp-like-3d-architecture-with-1","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","date":"2022-06-13","arxiv_id":"2206.06292","repositories_listed":0,"syntology":null},{"url":"/paper/learn2augment-learning-to-composite-videos","slug":"learn2augment-learning-to-composite-videos","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","date":"2022-06-09","arxiv_id":"2206.04790","repositories_listed":0,"syntology":null},{"url":null,"slug":"privhar-recognizing-human-actions-from","title":"PrivHAR: Recognizing Human Actions From Privacy-preserving Lens","date":"2022-06-08","arxiv_id":"2206.03891","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-convolutional-with-attention-for-action","title":"3D Convolutional with Attention for Action Recognition","date":"2022-06-05","arxiv_id":"2206.02203","repositories_listed":0,"syntology":null},{"url":null,"slug":"team-vi-i2r-technical-report-on-epic-kitchens","title":"Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021","date":"2022-06-03","arxiv_id":"2206.02573","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-of-audio-1","title":"Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment","date":"2022-06-02","arxiv_id":"2206.00970","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-versus-3d-convolutional-spiking-neural","title":"2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition","date":"2022-05-26","arxiv_id":"2205.13474","repositories_listed":0,"syntology":null},{"url":null,"slug":"grasens-a-gabor-residual-anti-aliasing","title":"GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi","date":"2022-05-24","arxiv_id":"2205.11945","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-fights-in-videos-a-comparison","title":"Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition","date":"2022-05-23","arxiv_id":"2205.11394","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-recognition-for-american-sign-language","title":"Action Recognition for American Sign Language","date":"2022-05-20","arxiv_id":"2205.12261","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-tolerant-learning-for-audio-visual","title":"Noise-Tolerant Learning for Audio-Visual Action Recognition","date":"2022-05-16","arxiv_id":"2205.07611","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-retime-learning-temporally-varying","title":"Video-ReTime: Learning Temporally Varying Speediness for Time Remapping","date":"2022-05-11","arxiv_id":"2205.05609","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-compressed-video","title":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","date":"2022-05-07","arxiv_id":"2205.03569","repositories_listed":0,"syntology":null},{"url":null,"slug":"handcrafted-localized-phase-features-for","title":"Handcrafted localized phase features for human action recognition","date":"2022-05-05","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/anubis-review-and-benchmark-skeleton-based","slug":"anubis-review-and-benchmark-skeleton-based","title":"ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark","date":"2022-05-04","arxiv_id":"2205.02071","repositories_listed":0,"syntology":null},{"url":"/paper/cross-modal-representation-learning-for-zero","slug":"cross-modal-representation-learning-for-zero","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","date":"2022-05-03","arxiv_id":"2205.01657","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserve-pre-trained-knowledge-transfer","title":"Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition","date":"2022-05-01","arxiv_id":"2205.00506","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-negative-sampling-for-audio-visual","title":"On Negative Sampling for Audio-Visual Contrastive Learning from Movies","date":"2022-04-29","arxiv_id":"2205.00073","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-contrastive-learning-for-self","title":"Self-supervised Contrastive Learning for Audio-Visual Action Recognition","date":"2022-04-28","arxiv_id":"2204.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"humman-multi-modal-4d-human-dataset-for","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","date":"2022-04-28","arxiv_id":"2204.13686","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-centered-prior-guided-and-task","title":"Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training","date":"2022-04-27","arxiv_id":"2204.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-relevance-analysis-for-video-action","title":"Temporal Relevance Analysis for Video Action Models","date":"2022-04-25","arxiv_id":"2204.11929","repositories_listed":0,"syntology":null},{"url":null,"slug":"icar-bridging-image-classification-and-image","title":"iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition","date":"2022-04-22","arxiv_id":"2204.10760","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-video-based-action-quality","title":"A Survey of Video-based Action Quality Assessment","date":"2022-04-20","arxiv_id":"2204.09271","repositories_listed":0,"syntology":null},{"url":null,"slug":"fencenet-fine-grained-footwork-recognition-in","title":"FenceNet: Fine-grained Footwork Recognition in Fencing","date":"2022-04-20","arxiv_id":"2204.09434","repositories_listed":0,"syntology":null},{"url":null,"slug":"stau-a-spatiotemporal-aware-unit-for-video","title":"STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond","date":"2022-04-20","arxiv_id":"2204.09456","repositories_listed":0,"syntology":null},{"url":null,"slug":"thorn-temporal-human-object-relation-network","title":"THORN: Temporal Human-Object Relation Network for Action Recognition","date":"2022-04-20","arxiv_id":"2204.09468","repositories_listed":0,"syntology":null},{"url":null,"slug":"actar-actor-driven-pose-embeddings-for-video","title":"ActAR: Actor-Driven Pose Embeddings for Video Action Recognition","date":"2022-04-19","arxiv_id":"2204.08671","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-performance-evaluation-of-action","title":"Performance Evaluation of Action Recognition Models on Low Quality Videos","date":"2022-04-19","arxiv_id":"2204.09166","repositories_listed":0,"syntology":null},{"url":null,"slug":"invisible-to-visible-privacy-aware-human","title":"Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder","date":"2022-04-15","arxiv_id":"2204.07280","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-agnostic-multi-domain-learning-with","title":"Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition","date":"2022-04-15","arxiv_id":"2204.07270","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-convolutional-networks-for-action","title":"3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition","date":"2022-04-13","arxiv_id":"2204.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-integration-of-dialog","title":"Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding","date":"2022-04-11","arxiv_id":"2204.05169","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-my-driver-observation-model-overconfident","title":"Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates","date":"2022-04-10","arxiv_id":"2204.04674","repositories_listed":0,"syntology":null},{"url":null,"slug":"sos-self-supervised-learning-over-sets-of","title":"SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition","date":"2022-04-10","arxiv_id":"2204.04796","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-representations-for-video","title":"Probabilistic Representations for Video Contrastive Learning","date":"2022-04-08","arxiv_id":"2204.03946","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-augmentation-on-selective","title":"Frequency Selective Augmentation for Video Representation Learning","date":"2022-04-08","arxiv_id":"2204.03865","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-self-supervised-representation","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","date":"2022-04-06","arxiv_id":"2204.03101","repositories_listed":0,"syntology":null},{"url":null,"slug":"seal-a-large-scale-video-dataset-of-multi","title":"MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization","date":"2022-04-06","arxiv_id":"2204.02688","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-dense-pose-estimation","title":"Direct Dense Pose Estimation","date":"2022-04-04","arxiv_id":"2204.01263","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectmix-data-augmentation-by-copy-pasting","title":"ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition","date":"2022-04-01","arxiv_id":"2204.00239","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformer-with-cross-attention-by","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","date":"2022-04-01","arxiv_id":"2204.00452","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-focus-for-skeleton-based","title":"SpatioTemporal Focus for Skeleton-based Action Recognition","date":"2022-03-31","arxiv_id":"2203.16767","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-augmentations-for-video","title":"Controllable Augmentations for Video Representation Learning","date":"2022-03-30","arxiv_id":"2203.16632","repositories_listed":0,"syntology":null},{"url":"/paper/class-incremental-learning-for-action-1","slug":"class-incremental-learning-for-action-1","title":"Class-Incremental Learning for Action Recognition in Videos","date":"2022-03-25","arxiv_id":"2203.13611","repositories_listed":0,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"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) · 5 unverified","sample_list":"/paper/class-incremental-learning-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2203.13611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13611"}},"official":null}},{"url":null,"slug":"locate-end-to-end-localization-of-actions-in","title":"LocATe: End-to-end Localization of Actions in 3D with Transformers","date":"2022-03-21","arxiv_id":"2203.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"point3d-tracking-actions-as-moving-points","title":"Point3D: tracking actions as moving points with 3D CNNs","date":"2022-03-20","arxiv_id":"2203.10584","repositories_listed":0,"syntology":null},{"url":null,"slug":"know-your-sensors-unicode-x2013-a-modality","title":"Know your sensORs -- A Modality Study For Surgical Action Classification","date":"2022-03-16","arxiv_id":"2203.08674","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-lstm-a-robust-classifier-for-video","title":"Context-LSTM: a robust classifier for video detection on UCF101","date":"2022-03-13","arxiv_id":"2203.06610","repositories_listed":0,"syntology":null},{"url":"/paper/tfcnet-temporal-fully-connected-networks-for","slug":"tfcnet-temporal-fully-connected-networks-for","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","date":"2022-03-11","arxiv_id":"2203.05928","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-folding-and-hyperspace-coding-for-multi","title":"Data-Folding and Hyperspace Coding for Multi-Dimensonal Time-Series Data Imaging","date":"2022-03-10","arxiv_id":"2203.05235","repositories_listed":0,"syntology":null},{"url":null,"slug":"part-level-action-parsing-via-a-pose-guided","title":"Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework","date":"2022-03-09","arxiv_id":"2203.04476","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-prototype-transport-for-zero-shot","title":"Universal Prototype Transport for Zero-Shot Action Recognition and Localization","date":"2022-03-08","arxiv_id":"2203.03971","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-recognition-based-on-the-integration","title":"Behavior Recognition Based on the Integration of Multigranular Motion Features","date":"2022-03-07","arxiv_id":"2203.03097","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-irrelevant-modality-dropout-for","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","date":"2022-03-06","arxiv_id":"2203.03014","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-human-action-recognition-for-human","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","date":"2022-02-26","arxiv_id":"2202.13096","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeleton-sequence-and-rgb-frame-based-multi","title":"Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition","date":"2022-02-23","arxiv_id":"2202.11374","repositories_listed":0,"syntology":null},{"url":null,"slug":"going-deeper-into-recognizing-actions-in-dark","title":"Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study","date":"2022-02-19","arxiv_id":"2202.09545","repositories_listed":0,"syntology":null},{"url":null,"slug":"haa4d-few-shot-human-atomic-action","title":"HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment","date":"2022-02-15","arxiv_id":"2202.07308","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-bone-fusion-graph-convolutional-network","title":"Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition","date":"2022-02-08","arxiv_id":"2202.04075","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapped-representation-learning-for","title":"Bootstrapped Representation Learning for Skeleton-Based Action Recognition","date":"2022-02-04","arxiv_id":"2202.02232","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-to-a-t-spatio-temporal-focus-for","title":"Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition","date":"2022-02-04","arxiv_id":"2202.02314","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-conventional-vision-models-on","title":"Benchmarking Conventional Vision Models on Neuromorphic Fall Detection and Action Recognition Dataset","date":"2022-01-28","arxiv_id":"2201.12285","repositories_listed":0,"syntology":null},{"url":null,"slug":"head-and-eye-egocentric-gesture-recognition","title":"Head and eye egocentric gesture recognition for human-robot interaction using eyewear cameras","date":"2022-01-27","arxiv_id":"2201.11500","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantically-video-coding-instill-static","title":"Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks","date":"2022-01-25","arxiv_id":"2201.10162","repositories_listed":0,"syntology":null},{"url":"/paper/action-keypoint-network-for-efficient-video","slug":"action-keypoint-network-for-efficient-video","title":"Action Keypoint Network for Efficient Video Recognition","date":"2022-01-17","arxiv_id":"2201.06304","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-world-graph-convolution-networks-rw-gcns","title":"Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance","date":"2022-01-15","arxiv_id":"2201.05739","repositories_listed":0,"syntology":null},{"url":null,"slug":"hand-object-interaction-reasoning","title":"Hand-Object Interaction Reasoning","date":"2022-01-13","arxiv_id":"2201.04906","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-labeling-of-human-action-for","title":"Semantic Labeling of Human Action For Visually Impaired And Blind People Scene Interaction","date":"2022-01-12","arxiv_id":"2201.04706","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-video-representation-learning-with-1","title":"Boosting Video Representation Learning with Multi-Faceted Integration","date":"2022-01-11","arxiv_id":"2201.04023","repositories_listed":0,"syntology":null},{"url":null,"slug":"representing-videos-as-discriminative-sub-1","title":"Representing Videos as Discriminative Sub-graphs for Action Recognition","date":"2022-01-11","arxiv_id":"2201.04027","repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-video-action-reasoning-via-learnable","title":"Complex Video Action Reasoning via Learnable Markov Logic Network","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-before-align-leveraging-cross-modal","title":"Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-video-representations-of-human","title":"Learning Video Representations of Human Motion From Synthetic Data","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"8bc1dd7616d6da5ad703d7ebc1a028f46f4a8343391664ba1573945485dc5f0a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}