{"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/16","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":16,"pages_in_order":28,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/task/action-recognition-in-videos/papers/17","papers":[{"url":null,"slug":"improving-accuracy-of-zero-shot-action","title":"Improving Zero-Shot Action Recognition using Human Instruction with Text Description","date":"2023-01-21","arxiv_id":"2301.08874","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-spatial-and-temporal-modeling","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","date":"2023-01-19","arxiv_id":"2301.07944","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmae-v-contrastive-masked-autoencoders-for","title":"CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition","date":"2023-01-15","arxiv_id":"2301.06018","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-action-recognition-and-pose","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","date":"2023-01-15","arxiv_id":"2301.06187","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-approaches-for-human","title":"Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation","date":"2023-01-13","arxiv_id":"2301.05575","repositories_listed":0,"syntology":null},{"url":null,"slug":"stprivacy-spatio-temporal-tubelet","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","date":"2023-01-08","arxiv_id":"2301.03046","repositories_listed":0,"syntology":null},{"url":null,"slug":"ego-only-egocentric-action-detection-without","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","date":"2023-01-03","arxiv_id":"2301.01380","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-listen-and-attack-backdoor-attacks","title":"Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition","date":"2023-01-03","arxiv_id":"2301.00986","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-robustness-analysis-of-video","title":"A Large-Scale Robustness Analysis of Video Action Recognition Models","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-exploration-of-multimodal","title":"Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-temporal-context-in-low","title":"Leveraging Temporal Context in Low Representational Power Regimes","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/lote-animal-a-long-time-span-dataset-for","slug":"lote-animal-a-long-time-span-dataset-for","title":"LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mmg-ego4d-multimodal-generalization-in","title":"MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-attention-interaction-network-for","title":"Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regen-a-good-generative-zero-shot-video","title":"ReGen: A good Generative Zero-Shot Video Classifier Should be Rewarded","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/skeletr-towards-skeleton-based-action","slug":"skeletr-towards-skeleton-based-action","title":"SkeleTR: Towards Skeleton-based Action Recognition in the Wild","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-pose-sequence-modeling","title":"Unified Pose Sequence Modeling","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-in-action-recognition-a-review","title":"Transformers in Action Recognition: A Review on Temporal Modeling","date":"2022-12-29","arxiv_id":"2302.01921","repositories_listed":0,"syntology":null},{"url":null,"slug":"smam-self-and-mutual-adaptive-matching-for","title":"SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition","date":"2022-12-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-ethics-privacy-and-regulations","title":"Understanding Ethics, Privacy, and Regulations in Smart Video Surveillance for Public Safety","date":"2022-12-25","arxiv_id":"2212.12936","repositories_listed":0,"syntology":null},{"url":"/paper/deep-set-conditioned-latent-representations-1","slug":"deep-set-conditioned-latent-representations-1","title":"Deep set conditioned latent representations for action recognition","date":"2022-12-21","arxiv_id":"2212.11030","repositories_listed":0,"syntology":null},{"url":null,"slug":"moquad-motion-focused-quadruple-construction","title":"MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning","date":"2022-12-21","arxiv_id":"2212.10870","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-human-action-recognition","title":"A Survey on Human Action Recognition","date":"2022-12-20","arxiv_id":"2301.06082","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-segmentation-learning-using-cascade","title":"Video Segmentation Learning Using Cascade Residual Convolutional Neural Network","date":"2022-12-20","arxiv_id":"2212.10570","repositories_listed":0,"syntology":null},{"url":null,"slug":"icub-do-you-recognize-what-i-am-doing","title":"iCub! Do you recognize what I am doing?: multimodal human action recognition on multisensory-enabled iCub robot","date":"2022-12-17","arxiv_id":"2212.08859","repositories_listed":0,"syntology":null},{"url":null,"slug":"inductive-attention-for-video-action","title":"Inductive Attention for Video Action Anticipation","date":"2022-12-17","arxiv_id":"2212.08830","repositories_listed":0,"syntology":null},{"url":"/paper/cross-modal-learning-with-3d-deformable","slug":"cross-modal-learning-with-3d-deformable","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","date":"2022-12-12","arxiv_id":"2212.05638","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstructing-humpty-dumpty-multi-feature","title":"Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition","date":"2022-12-12","arxiv_id":"2212.06023","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-prototype-enhanced-network-for-few","title":"Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition","date":"2022-12-09","arxiv_id":"2212.04873","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptonomyvit-multi-task-prompt-learning","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","date":"2022-12-08","arxiv_id":"2212.04821","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-actions-to-events-a-transfer-learning","title":"From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks","date":"2022-11-30","arxiv_id":"2211.17045","repositories_listed":0,"syntology":null},{"url":null,"slug":"hand-guided-high-resolution-feature","title":"Hand Guided High Resolution Feature Enhancement for Fine-Grained Atomic Action Segmentation within Complex Human Assemblies","date":"2022-11-24","arxiv_id":"2211.13694","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-appearance-a-video-representation-for","title":"Dynamic Appearance: A Video Representation for Action Recognition with Joint Training","date":"2022-11-23","arxiv_id":"2211.12748","repositories_listed":0,"syntology":null},{"url":"/paper/global-temporal-difference-network-for-action","slug":"global-temporal-difference-network-for-action","title":"Global Temporal Difference Network for Action Recognition","date":"2022-11-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"query-efficient-cross-dataset-transferable","title":"Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition","date":"2022-11-23","arxiv_id":"2211.13171","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-transformer-a-multi-purpose-solution","title":"Event Transformer+. A multi-purpose solution for efficient event data processing","date":"2022-11-22","arxiv_id":"2211.12222","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-prompting-for-few-shot-action","title":"Knowledge Prompting for Few-shot Action Recognition","date":"2022-11-22","arxiv_id":"2211.12030","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-human-motion-generation-from-the-text-via","title":"3d human motion generation from the text via gesture action classification and the autoregressive model","date":"2022-11-18","arxiv_id":"2211.10003","repositories_listed":0,"syntology":null},{"url":null,"slug":"problem-behaviors-recognition-in-videos-using","title":"Language-Assisted Deep Learning for Autistic Behaviors Recognition","date":"2022-11-17","arxiv_id":"2211.09310","repositories_listed":0,"syntology":null},{"url":null,"slug":"confies-controllable-neural-face-avatars","title":"CoNFies: Controllable Neural Face Avatars","date":"2022-11-16","arxiv_id":"2211.08610","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-temporal-data-augmentation-for","title":"Extending Temporal Data Augmentation for Video Action Recognition","date":"2022-11-09","arxiv_id":"2211.04888","repositories_listed":0,"syntology":null},{"url":"/paper/could-giant-pretrained-image-models-extract","slug":"could-giant-pretrained-image-models-extract","title":"Could Giant Pretrained Image Models Extract Universal Representations?","date":"2022-11-03","arxiv_id":"2211.02043","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-and-learning-static-vs-dynamic","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","date":"2022-11-03","arxiv_id":"2211.01783","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-computer-vision-algorithms-for","title":"Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing","date":"2022-11-02","arxiv_id":"2211.01037","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-condensed-frame-for-memory","title":"Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning","date":"2022-11-02","arxiv_id":"2211.00833","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-audio-speaking-status-detection-in-crowded","title":"No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration","date":"2022-11-01","arxiv_id":"2211.00549","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-viewpoint-transportation-plan-for","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","date":"2022-10-30","arxiv_id":"2210.16820","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-representation-of-human-motion","title":"Learning Joint Representation of Human Motion and Language","date":"2022-10-27","arxiv_id":"2210.15187","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2model-model-induction-for-zero-shot","title":"Text2Model: Text-based Model Induction for Zero-shot Image Classification","date":"2022-10-27","arxiv_id":"2210.15182","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-domain-adaptation-for-action","title":"Adversarial Domain Adaptation for Action Recognition Around the Clock","date":"2022-10-25","arxiv_id":"2210.17412","repositories_listed":0,"syntology":null},{"url":null,"slug":"clean-text-and-full-body-transformer","title":"Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation","date":"2022-10-24","arxiv_id":"2210.13326","repositories_listed":0,"syntology":null},{"url":null,"slug":"baby-physical-safety-monitoring-in-smart-home","title":"Baby Physical Safety Monitoring in Smart Home Using Action Recognition System","date":"2022-10-22","arxiv_id":"2210.12527","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-human-pose-estimation-in-multi-view","title":"3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections","date":"2022-10-21","arxiv_id":"2210.11826","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-action-recognition-in-hand","title":"Transformer-based Action recognition in hand-object interacting scenarios","date":"2022-10-20","arxiv_id":"2210.11387","repositories_listed":0,"syntology":null},{"url":"/paper/star-transformer-a-spatio-temporal-cross-1","slug":"star-transformer-a-spatio-temporal-cross-1","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","date":"2022-10-14","arxiv_id":"2210.07503","repositories_listed":0,"syntology":null},{"url":null,"slug":"pose-guided-graph-convolutional-networks-for","title":"Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2022-10-10","arxiv_id":"2210.06192","repositories_listed":0,"syntology":null},{"url":null,"slug":"students-taught-by-multimodal-teachers-are","title":"Students taught by multimodal teachers are superior action recognizers","date":"2022-10-09","arxiv_id":"2210.04331","repositories_listed":0,"syntology":null},{"url":null,"slug":"blanketset-a-clinical-real-word-action","title":"BlanketSet -- A clinical real-world in-bed action recognition and qualitative semi-synchronised MoCap dataset","date":"2022-10-07","arxiv_id":"2210.03600","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-aligned-concave-curve-illumination","title":"Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation","date":"2022-10-07","arxiv_id":"2210.03792","repositories_listed":0,"syntology":null},{"url":null,"slug":"focal-and-global-spatial-temporal-transformer","title":"Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition","date":"2022-10-06","arxiv_id":"2210.02693","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignment-guided-temporal-attention-for-video","title":"Alignment-guided Temporal Attention for Video Action Recognition","date":"2022-09-30","arxiv_id":"2210.00132","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-driven-ai-paradigm-for-human","title":"Application-Driven AI Paradigm for Human Action Recognition","date":"2022-09-30","arxiv_id":"2209.15271","repositories_listed":0,"syntology":null},{"url":null,"slug":"rest-retrieve-self-train-for-generative","title":"REST: REtrieve & Self-Train for generative action recognition","date":"2022-09-29","arxiv_id":"2209.15000","repositories_listed":0,"syntology":null},{"url":null,"slug":"speeding-up-action-recognition-using-dynamic","title":"Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain","date":"2022-09-29","arxiv_id":"2209.14757","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-spiking-neural-networks","title":"Attention Spiking Neural Networks","date":"2022-09-28","arxiv_id":"2209.13929","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resolution-action-recognition-for-tiny","title":"Low-Resolution Action Recognition for Tiny Actions Challenge","date":"2022-09-28","arxiv_id":"2209.14711","repositories_listed":0,"syntology":null},{"url":null,"slug":"ani-gifs-a-benchmark-dataset-for-domain","title":"Ani-GIFs: A benchmark dataset for domain generalization of action recognition from GIFs","date":"2022-09-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-self-supervised-training-for","title":"Leveraging Self-Supervised Training for Unintentional Action Recognition","date":"2022-09-23","arxiv_id":"2209.11870","repositories_listed":0,"syntology":null},{"url":null,"slug":"view-invariant-skeleton-based-action","title":"View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning","date":"2022-09-23","arxiv_id":"2209.11634","repositories_listed":0,"syntology":null},{"url":"/paper/avt-audio-video-transformer-for-multimodal","slug":"avt-audio-video-transformer-for-multimodal","title":"AVT: Audio-Video Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"futh-net-fusing-temporal-relations-and","title":"FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification","date":"2022-09-22","arxiv_id":"2209.11316","repositories_listed":0,"syntology":null},{"url":"/paper/multiscale-multimodal-transformer-for","slug":"multiscale-multimodal-transformer-for","title":"Multiscale Multimodal Transformer for Multimodal Action Recognition","date":"2022-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-local-component-aware-graph","title":"Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition","date":"2022-09-21","arxiv_id":"2209.10073","repositories_listed":0,"syntology":null},{"url":null,"slug":"meccano-a-multimodal-egocentric-dataset-for","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","date":"2022-09-19","arxiv_id":"2209.08691","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-frequency-based","title":"Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition","date":"2022-09-15","arxiv_id":"2209.09194","repositories_listed":0,"syntology":null},{"url":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformers-for-action-recognition-a","title":"Vision Transformers for Action Recognition: A Survey","date":"2022-09-13","arxiv_id":"2209.05700","repositories_listed":0,"syntology":null},{"url":null,"slug":"maivar-multimodal-audio-image-and-video","title":"MAiVAR: Multimodal Audio-Image and Video Action Recognizer","date":"2022-09-11","arxiv_id":"2209.04780","repositories_listed":0,"syntology":null},{"url":null,"slug":"polito-iit-cini-submission-to-the-epic","title":"PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition","date":"2022-09-09","arxiv_id":"2209.04525","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-self-knowledge-distillation-approach","title":"A Novel Self-Knowledge Distillation Approach with Siamese Representation Learning for Action Recognition","date":"2022-09-03","arxiv_id":"2209.01311","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-spatio-temporal-specialization","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","date":"2022-09-03","arxiv_id":"2209.01425","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-contrastive-learning-with-curriculum","title":"Temporal Contrastive Learning with Curriculum","date":"2022-09-02","arxiv_id":"2209.00760","repositories_listed":0,"syntology":null},{"url":null,"slug":"casper-cognitive-architecture-for-social","title":"CASPER: Cognitive Architecture for Social Perception and Engagement in Robots","date":"2022-09-01","arxiv_id":"2209.01012","repositories_listed":0,"syntology":null},{"url":null,"slug":"maple-masked-pseudo-labeling-autoencoder-for","title":"MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition","date":"2022-09-01","arxiv_id":"2209.00407","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeletonmae-spatial-temporal-masked","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","date":"2022-09-01","arxiv_id":"2209.02399","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-satisfaction-modeling-with-domain","title":"User Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue Systems","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-mixer-for-multi-modal-action","title":"Modality Mixer for Multi-modal Action Recognition","date":"2022-08-24","arxiv_id":"2208.11314","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-attention-free-video-shift","title":"Efficient Attention-free Video Shift Transformers","date":"2022-08-23","arxiv_id":"2208.11108","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-auxiliary-or-adversarial-tasks","title":"Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding","date":"2022-08-22","arxiv_id":"2208.10077","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-on-action-recognition-for-accident","title":"Review on Action Recognition for Accident Detection in Smart City Transportation Systems","date":"2022-08-20","arxiv_id":"2208.09588","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-compositional-representations","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","date":"2022-08-19","arxiv_id":"2208.09424","repositories_listed":0,"syntology":null},{"url":null,"slug":"part-aware-prototypical-graph-network-for-one","title":"Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition","date":"2022-08-19","arxiv_id":"2208.09150","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-in-human-analysis-a-survey","title":"Synthetic Data in Human Analysis: A Survey","date":"2022-08-19","arxiv_id":"2208.09191","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-cross-modal-knowledge","title":"Progressive Cross-modal Knowledge Distillation for Human Action Recognition","date":"2022-08-17","arxiv_id":"2208.08090","repositories_listed":0,"syntology":null},{"url":null,"slug":"extern-leveraging-endo-temporal","title":"Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation","date":"2022-08-10","arxiv_id":"2208.05187","repositories_listed":0,"syntology":null},{"url":null,"slug":"babynet-a-lightweight-network-for-infant","title":"BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications","date":"2022-08-09","arxiv_id":"2208.04950","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-activity-recognition-using-cascaded","title":"Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework","date":"2022-08-09","arxiv_id":"2208.05034","repositories_listed":0,"syntology":null},{"url":"/paper/spatial-temporal-pyramid-graph-reasoning-for","slug":"spatial-temporal-pyramid-graph-reasoning-for","title":"Spatial-Temporal Pyramid Graph Reasoning for Action Recognition","date":"2022-08-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-based-human-action-recognition-using","title":"Video-based Human Action Recognition using Deep Learning: A Review","date":"2022-08-07","arxiv_id":"2208.03775","repositories_listed":0,"syntology":null},{"url":null,"slug":"afe-cnn-3d-skeleton-based-action-recognition","title":"AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement","date":"2022-08-06","arxiv_id":"2208.03444","repositories_listed":0,"syntology":null}],"record_sha256":"10d95dd6a9d42c8b072d7d0603ef9817273f87655da860f187dd51cf62a188a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}