{"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/papers/8","list_of":"/task/action-recognition","task":"Temporal Action Localization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":15,"rows_per_page":100,"rows":[701,800],"of":1477,"counts":{"archive_papers_tagged":1477,"with_a_code_link":493,"where_syntology_ran_a_sample":87,"not_listed_spam_title":0,"listed":1477,"listed_where_code_ran":87,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":68,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":68,"listed_every_run_a_failure_of_syntologys_instrument":19,"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","prev":"/task/action-recognition/papers/7","next":"/task/action-recognition/papers/9","papers":[{"url":null,"slug":"learning-to-refactor-action-and-co-occurrence-1","title":"Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization","date":"2022-06-23","arxiv_id":"2206.11493","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":"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":"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":null,"slug":"contrastive-language-action-pre-training-for","title":"Contrastive Language-Action Pre-training for Temporal Localization","date":"2022-04-26","arxiv_id":"2204.12293","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":"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":"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":"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":"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":"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":"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":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":"owl-observe-watch-listen-localizing-actions","title":"OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos","date":"2022-02-10","arxiv_id":"2202.04947","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":"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":"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":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":"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":"exploring-denoised-cross-video-contrast-for","title":"Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization","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":"object-relation-reasoning-graph-for-action","title":"Object-Relation Reasoning Graph for Action Recognition","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recurring-the-transformer-for-video-action","title":"Recurring the Transformer for Video Action Recognition","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-transformer-networks-with-self","title":"Temporal Transformer Networks with Self-Supervision for Action Recognition","date":"2021-12-14","arxiv_id":"2112.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-expert-human-action-recognition-with","title":"Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning","date":"2021-12-13","arxiv_id":"2112.07015","repositories_listed":0,"syntology":null},{"url":null,"slug":"stsm-spatio-temporal-shift-module-for","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","date":"2021-12-05","arxiv_id":"2112.02523","repositories_listed":0,"syntology":null},{"url":"/paper/graph-convolutional-module-for-temporal","slug":"graph-convolutional-module-for-temporal","title":"Graph Convolutional Module for Temporal Action Localization in Videos","date":"2021-12-01","arxiv_id":"2112.00302","repositories_listed":0,"syntology":null},{"url":"/paper/low-fidelity-video-encoder-optimization-for","slug":"low-fidelity-video-encoder-optimization-for","title":"Low-Fidelity Video Encoder Optimization for Temporal Action Localization","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-transformers-for-lightweight","title":"Evaluating Transformers for Lightweight Action Recognition","date":"2021-11-18","arxiv_id":"2111.09641","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-semantics-guided-neural-networks","title":"Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition","date":"2021-11-07","arxiv_id":"2111.03993","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-frequency-modulation-for-visually","title":"Gradient Frequency Modulation for Visually Explaining Video Understanding Models","date":"2021-11-01","arxiv_id":"2111.01215","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeleton-based-mutually-assisted-interacted","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","date":"2021-10-28","arxiv_id":"2110.14994","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtm-gray-temporal-model-for-video-recognition","title":"GTM: Gray Temporal Model for Video Recognition","date":"2021-10-20","arxiv_id":"2110.10348","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-learning-on-the-hierarchy","title":"Joint Learning On The Hierarchy Representation for Fine-Grained Human Action Recognition","date":"2021-10-12","arxiv_id":"2110.05853","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-is-graph-structured-graph-module-for","title":"Video Is Graph: Structured Graph Module for Video Action Recognition","date":"2021-10-12","arxiv_id":"2110.05904","repositories_listed":0,"syntology":null},{"url":null,"slug":"saic-cambridge-hupba-fbk-submission-to-the","title":"SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021","date":"2021-10-06","arxiv_id":"2110.02902","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-stage-transformer-for-video-learning","title":"Cross-Stage Transformer for Video Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-localization-with-global","title":"Temporal Action Localization with Global Segmentation Mask Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-temporal-sentence-grounding-in","title":"A Survey on Temporal Sentence Grounding in Videos","date":"2021-09-16","arxiv_id":"2109.08039","repositories_listed":0,"syntology":null},{"url":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-vit-multi-modal-video-transformer-for","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","date":"2021-08-20","arxiv_id":"2108.09322","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-8","slug":"self-supervised-video-representation-learning-8","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","date":"2021-08-19","arxiv_id":"2108.08426","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-motion-prior-for-weakly-supervised","title":"Deep Motion Prior for Weakly-Supervised Temporal Action Localization","date":"2021-08-12","arxiv_id":"2108.05607","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-human-action-recognition","title":"Spatio-Temporal Human Action Recognition Modelwith Flexible-interval Sampling and Normalization","date":"2021-08-12","arxiv_id":"2108.05633","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeleton-cloud-colorization-for-unsupervised","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","date":"2021-08-04","arxiv_id":"2108.01959","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-knowledge-based-multi","title":"Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021","date":"2021-07-27","arxiv_id":"2107.12618","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-for-temporal-sparsity-in-deep-neural","title":"Training for temporal sparsity in deep neural networks, application in video processing","date":"2021-07-15","arxiv_id":"2107.07305","repositories_listed":0,"syntology":null},{"url":null,"slug":"videolightformer-lightweight-action","title":"VideoLightFormer: Lightweight Action Recognition using Transformers","date":"2021-07-01","arxiv_id":"2107.00451","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-temporal-context-and-human-movement","title":"Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos","date":"2021-06-26","arxiv_id":"2106.13967","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-stronger-feature-for-temporal","title":"Exploring Stronger Feature for Temporal Action Localization","date":"2021-06-24","arxiv_id":"2106.13014","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stream-consensus-network-submission-to","title":"Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track","date":"2021-06-21","arxiv_id":"2106.10829","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-temporal-action-4","title":"Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling","date":"2021-06-20","arxiv_id":"2106.11811","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-contrastive-domain-adaptation","title":"Spatio-temporal Contrastive Domain Adaptation for Action Recognition","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"three-birds-with-one-stone-multi-task","title":"Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/relation-modeling-in-spatio-temporal-action","slug":"relation-modeling-in-spatio-temporal-action","title":"Relation Modeling in Spatio-Temporal Action Localization","date":"2021-06-15","arxiv_id":"2106.08061","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsi-temporal-saliency-integration-for-video","title":"TSI: Temporal Saliency Integration for Video Action Recognition","date":"2021-06-02","arxiv_id":"2106.01088","repositories_listed":0,"syntology":null},{"url":null,"slug":"inertial-sensor-data-to-image-encoding-for","title":"Inertial Sensor Data To Image Encoding For Human Action Recognition","date":"2021-05-28","arxiv_id":"2105.13533","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssan-separable-self-attention-network-for","title":"SSAN: Separable Self-Attention Network for Video Representation Learning","date":"2021-05-27","arxiv_id":"2105.13033","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-imaginative-generative-adversarial","title":"The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition","date":"2021-05-27","arxiv_id":"2105.13061","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-proposal-generation-with","title":"Temporal Action Proposal Generation with Transformers","date":"2021-05-25","arxiv_id":"2105.12043","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-human-action-recognition-using","title":"Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model","date":"2021-05-24","arxiv_id":"2105.11312","repositories_listed":0,"syntology":null},{"url":null,"slug":"regina-reasoning-graph-convolutional-networks","title":"REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition","date":"2021-05-14","arxiv_id":"2105.06711","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-in-mind-a-neural-network-approach-to","title":"Action in Mind: A Neural Network Approach to Action Recognition and Segmentation","date":"2021-04-30","arxiv_id":"2104.14870","repositories_listed":0,"syntology":null},{"url":"/paper/action-unit-memory-network-for-weakly","slug":"action-unit-memory-network-for-weakly","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","date":"2021-04-29","arxiv_id":"2104.14135","repositories_listed":0,"syntology":null},{"url":null,"slug":"relevance-detection-in-cataract-surgery","title":"Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization","date":"2021-04-29","arxiv_id":"2104.14280","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-stream-network-for-enriched-action","title":"Three-stream network for enriched Action Recognition","date":"2021-04-27","arxiv_id":"2104.13051","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-convolutional-neural-networks-for-2","title":"3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces","date":"2021-04-23","arxiv_id":"2104.11532","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-pass-filter-for-anti-aliasing-in-temporal","title":"Low Pass Filter for Anti-aliasing in Temporal Action Localization","date":"2021-04-23","arxiv_id":"2104.11403","repositories_listed":0,"syntology":null},{"url":null,"slug":"skimming-and-scanning-for-untrimmed-video","title":"Skimming and Scanning for Untrimmed Video Action Recognition","date":"2021-04-21","arxiv_id":"2104.10492","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-based-timestamp-image-encoding-network","title":"Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation","date":"2021-04-12","arxiv_id":"2104.05145","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-mutual-supervision-for-weakly","slug":"adaptive-mutual-supervision-for-weakly","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","date":"2021-04-06","arxiv_id":"2104.02357","repositories_listed":0,"syntology":null},{"url":null,"slug":"composable-augmentation-encoding-for-video","title":"Composable Augmentation Encoding for Video Representation Learning","date":"2021-04-01","arxiv_id":"2104.00616","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-temporal-action-3","title":"Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context","date":"2021-03-30","arxiv_id":"2103.16155","repositories_listed":0,"syntology":null},{"url":"/paper/acsnet-action-context-separation-network-for","slug":"acsnet-action-context-separation-network-for","title":"ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization","date":"2021-03-28","arxiv_id":"2103.15088","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-fidelity-end-to-end-video-encoder-pre","title":"Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization","date":"2021-03-28","arxiv_id":"2103.15233","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcmnet-position-sensitive-context-modeling","title":"PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization","date":"2021-03-09","arxiv_id":"2103.05270","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-recognize-actions-on-objects-in","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","date":"2021-02-16","arxiv_id":"2102.08065","repositories_listed":0,"syntology":null},{"url":null,"slug":"adafuse-adaptive-temporal-fusion-network-for-1","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","date":"2021-02-10","arxiv_id":"2102.05775","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-action-recognition-using-spatio","title":"Video Action Recognition Using spatio-temporal optical flow video frames","date":"2021-02-05","arxiv_id":"2103.05101","repositories_listed":0,"syntology":null},{"url":null,"slug":"gcf-net-gated-clip-fusion-network-for-video","title":"GCF-Net: Gated Clip Fusion Network for Video Action Recognition","date":"2021-02-02","arxiv_id":"2102.01285","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeletonvis-interactive-visualization-for","title":"SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models","date":"2021-01-26","arxiv_id":"2101.10586","repositories_listed":0,"syntology":null},{"url":"/paper/activity-graph-transformer-for-temporal","slug":"activity-graph-transformer-for-temporal","title":"Activity Graph Transformer for Temporal Action Localization","date":"2021-01-21","arxiv_id":"2101.08540","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-human-action","title":"Bridging the gap between Human Action Recognition and Online Action Detection","date":"2021-01-21","arxiv_id":"2101.08851","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-recognition-based-on-multi-scale","title":"Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences","date":"2021-01-19","arxiv_id":"2101.07618","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-action-recognition-for-lane-change","title":"Video action recognition for lane-change classification and prediction of surrounding vehicles","date":"2021-01-13","arxiv_id":"2101.05043","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-weakly-labeled-web-videos-via","title":"Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts","date":"2021-01-11","arxiv_id":"2101.03713","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-contrastive-graph-for-self","title":"Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval","date":"2021-01-04","arxiv_id":"2101.00820","repositories_listed":0,"syntology":null},{"url":null,"slug":"cag-qil-context-aware-actionness-grouping-via","title":"CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"divide-and-conquer-for-single-frame-temporal","title":"Divide and Conquer for Single-Frame Temporal Action Localization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-sub-pseudo-labels-for-learning-from","title":"Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"geometric-deep-neural-network-using-rigid-and","title":"Geometric Deep Neural Network Using Rigid and Non-Rigid Transformations for Human Action Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-and-accurate-compressed-video-action","title":"Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain","date":"2020-12-26","arxiv_id":"2012.13726","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-recognition-from-various-data","title":"Human Action Recognition from Various Data Modalities: A Review","date":"2020-12-22","arxiv_id":"2012.11866","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-action-localization-and","title":"Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN","date":"2020-12-17","arxiv_id":"2012.09542","repositories_listed":0,"syntology":null}],"record_sha256":"0c8792a478fbdf9989bfe068a1d03c02027676b0c02d1a73b29053d8563eeee7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}