{"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-classification/papers/4","list_of":"/task/action-classification","task":"Action Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":5,"rows_per_page":100,"rows":[301,400],"of":457,"counts":{"archive_papers_tagged":457,"with_a_code_link":251,"where_syntology_ran_a_sample":83,"not_listed_spam_title":0,"listed":457,"listed_where_code_ran":83,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":75,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":75,"listed_every_run_a_failure_of_syntologys_instrument":8,"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-classification","prev":"/task/action-classification/papers/3","next":"/task/action-classification/papers/5","papers":[{"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":"self-supervised-and-weakly-supervised","title":"Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations","date":"2022-12-06","arxiv_id":"2212.03125","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-crop-aggregation-for-video","title":"Spatio-Temporal Crop Aggregation for Video Representation Learning","date":"2022-11-30","arxiv_id":"2211.17042","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":"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":"egocentric-audio-visual-noise-suppression","title":"Egocentric Audio-Visual Noise Suppression","date":"2022-11-07","arxiv_id":"2211.03643","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":"turbo-training-with-token-dropout","title":"Turbo Training with Token Dropout","date":"2022-10-10","arxiv_id":"2210.04889","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":"self-supervised-learning-for-unintentional","title":"Self-supervised Learning for Unintentional Action Prediction","date":"2022-09-24","arxiv_id":"2209.12074","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":"temporal-action-localization-with-multi","title":"Temporal Action Localization with Multi-temporal Scales","date":"2022-08-16","arxiv_id":"2208.07493","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-an-object-centric-video-representation","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","date":"2022-07-20","arxiv_id":"2207.10075","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-proposal-network-for-temporal","title":"Context-aware Proposal Network for Temporal Action Detection","date":"2022-06-18","arxiv_id":"2206.09082","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":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":"machine-learning-and-signal-processing-based","title":"Machine Learning and Signal Processing Based Analysis of sEMG Signals for Daily Action Classification","date":"2022-04-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deformable-video-transformer","title":"Deformable Video Transformer","date":"2022-03-31","arxiv_id":"2203.16795","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":"/paper/end-to-end-generative-pretraining-for","slug":"end-to-end-generative-pretraining-for","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","date":"2022-01-20","arxiv_id":"2201.08264","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-transformers-a-survey","title":"Video Transformers: A Survey","date":"2022-01-16","arxiv_id":"2201.05991","repositories_listed":0,"syntology":null},{"url":"/paper/merlot-reserve-neural-script-knowledge","slug":"merlot-reserve-neural-script-knowledge","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","date":"2022-01-07","arxiv_id":"2201.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-video-model-transfer-with-dynamic","title":"Improving Video Model Transfer With Dynamic Representation Learning","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/co-training-transformer-with-videos-and","slug":"co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","date":"2021-12-14","arxiv_id":"2112.07175","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":"previts-contrastive-pretraining-with-video","title":"PreViTS: Contrastive Pretraining with Video Tracking Supervision","date":"2021-12-01","arxiv_id":"2112.00804","repositories_listed":0,"syntology":null},{"url":null,"slug":"reformulating-zero-shot-action-recognition","title":"Reformulating Zero-shot Action Recognition for Multi-label Actions","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-for-video-action","title":"Class incremental learning for video action classification","date":"2021-09-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-view-invariant-human-posture","title":"Unsupervised View-Invariant Human Posture Representation","date":"2021-09-17","arxiv_id":"2109.08730","repositories_listed":0,"syntology":null},{"url":"/paper/pose-is-all-you-need-the-pose-only-group","slug":"pose-is-all-you-need-the-pose-only-group","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","date":"2021-08-09","arxiv_id":"2108.04186","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-learning-with-strategic-users-a","title":"Distributed Learning with Strategic Users: A Repeated Game Approach","date":"2021-05-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/vidtr-video-transformer-without-convolutions","slug":"vidtr-video-transformer-without-convolutions","title":"VidTr: Video Transformer Without Convolutions","date":"2021-04-23","arxiv_id":"2104.11746","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-query-networks-for-fine-grained","slug":"temporal-query-networks-for-fine-grained","title":"Temporal Query Networks for Fine-grained Video Understanding","date":"2021-04-19","arxiv_id":"2104.09496","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-intermediate-representations-for","slug":"adaptive-intermediate-representations-for","title":"Adaptive Intermediate Representations for Video Understanding","date":"2021-04-14","arxiv_id":"2104.07135","repositories_listed":0,"syntology":null},{"url":null,"slug":"zeus-efficiently-localizing-actions-in-videos","title":"Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning","date":"2021-04-06","arxiv_id":"2104.06142","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-of-single-cell","title":"Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification","date":"2021-03-30","arxiv_id":"2103.16670","repositories_listed":0,"syntology":null},{"url":"/paper/recognizing-actions-in-videos-from-unseen","slug":"recognizing-actions-in-videos-from-unseen","title":"Recognizing Actions in Videos from Unseen Viewpoints","date":"2021-03-30","arxiv_id":"2103.16516","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":"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":"watch-only-once-an-end-to-end-video-action","title":"Watch Only Once: An End-to-End Video Action Detection Framework","date":"2021-01-01","arxiv_id":null,"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},{"url":null,"slug":"hierarchical-human-action-classification-with","title":"Hierarchical Human Action Classification with Network Pruning","date":"2020-12-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-spatio-temporal-action-localization","title":"Real-time Spatio-temporal Action Localization via Learning Motion Representation","date":"2020-11-30","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-aware-action-recognition-pose-motion","title":"Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps","date":"2020-11-26","arxiv_id":"2011.13399","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-attention-mechanism-for-fine-grained","title":"3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks","date":"2020-11-20","arxiv_id":"2012.05342","repositories_listed":0,"syntology":null},{"url":"/paper/improved-soccer-action-spotting-using-both","slug":"improved-soccer-action-spotting-using-both","title":"Improved Soccer Action Spotting using both Audio and Video Streams","date":"2020-11-09","arxiv_id":"2011.04258","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-not-trust-the-neighbors-adversarial-metric","title":"Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation","date":"2020-11-01","arxiv_id":"2011.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-fusion-transformers-for-video","title":"Knowledge Fusion Transformers for Video Action Recognition","date":"2020-09-29","arxiv_id":"2009.13782","repositories_listed":0,"syntology":null},{"url":"/paper/perf-net-pose-empowered-rgb-flow-net","slug":"perf-net-pose-empowered-rgb-flow-net","title":"PERF-Net: Pose Empowered RGB-Flow Net","date":"2020-09-28","arxiv_id":"2009.13087","repositories_listed":0,"syntology":null},{"url":"/paper/haa500-human-centric-atomic-action-dataset","slug":"haa500-human-centric-atomic-action-dataset","title":"HAA500: Human-Centric Atomic Action Dataset with Curated Videos","date":"2020-09-11","arxiv_id":"2009.05224","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-action-recognition-system-for-smart","title":"A novel action recognition system for smart monitoring of elderly people using Action Pattern Image and Series CNN with transfer learning","date":"2020-09-07","arxiv_id":"2009.03285","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-similarity-judgment-based-on-kinematic","title":"Action similarity judgment based on kinematic primitives","date":"2020-08-30","arxiv_id":"2008.13176","repositories_listed":0,"syntology":null},{"url":null,"slug":"biased-mixtures-of-experts-enabling-computer","title":"Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations","date":"2020-08-21","arxiv_id":"2008.09662","repositories_listed":0,"syntology":null},{"url":"/paper/towards-efficient-coarse-to-fine-networks-for","slug":"towards-efficient-coarse-to-fine-networks-for","title":"Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-action-classification-with","slug":"hierarchical-action-classification-with","title":"Hierarchical Action Classification with Network Pruning","date":"2020-07-30","arxiv_id":"2007.15244","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-fusion-network-for-temporal-action","title":"Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)","date":"2020-06-13","arxiv_id":"2006.07520","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionbytes-learning-from-trimmed-videos-to","title":"ActionBytes: Learning From Trimmed Videos to Localize Actions","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-dictionary-design-for-action","title":"Discriminative Dictionary Design for Action Classification in Still Images and Videos","date":"2020-05-20","arxiv_id":"2005.10149","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ava-kinetics-localized-human-actions","title":"The AVA-Kinetics Localized Human Actions Video Dataset","date":"2020-05-01","arxiv_id":"2005.00214","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensembles-of-deep-neural-networks-for-action","title":"Ensembles of Deep Neural Networks for Action Recognition in Still Images","date":"2020-03-22","arxiv_id":"2003.09893","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-recognition-using-local-two","title":"Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines","date":"2020-02-19","arxiv_id":"2002.09423","repositories_listed":0,"syntology":null},{"url":"/paper/hallucinating-statistical-moment-and-subspace","slug":"hallucinating-statistical-moment-and-subspace","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","date":"2020-01-14","arxiv_id":"2001.04627","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-liars-walk-detecting-deception-with-gait","title":"The Liar's Walk: Detecting Deception with Gait and Gesture","date":"2019-12-14","arxiv_id":"1912.06874","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapnet-adaptability-decomposing-encoder","title":"AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization","date":"2019-11-27","arxiv_id":"1911.11961","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-recognition-in-drone-videos","title":"Human Action Recognition in Drone Videos using a Few Aerial Training Examples","date":"2019-10-22","arxiv_id":"1910.10027","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-sequence-classification","title":"Human Action Sequence Classification","date":"2019-10-07","arxiv_id":"1910.02602","repositories_listed":0,"syntology":null},{"url":"/paper/toyota-smarthome-real-world-activities-of","slug":"toyota-smarthome-real-world-activities-of","title":"Toyota Smarthome: Real-World Activities of Daily Living","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action","slug":"weakly-supervised-temporal-action","title":"Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-action-segmentation-using-the","title":"Fine-grained Action Segmentation using the Semi-Supervised Action GAN","date":"2019-09-20","arxiv_id":"1909.09269","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-specific-action-classification-for","title":"Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video","date":"2019-09-20","arxiv_id":"1909.09566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-three-stream-network-for-action","title":"Multi-Modal Three-Stream Network for Action Recognition","date":"2019-09-08","arxiv_id":"1909.03466","repositories_listed":0,"syntology":null},{"url":"/paper/190807625","slug":"190807625","title":"Action recognition with spatial-temporal discriminative filter banks","date":"2019-08-20","arxiv_id":"1908.07625","repositories_listed":0,"syntology":null},{"url":"/paper/stm-spatiotemporal-and-motion-encoding-for","slug":"stm-spatiotemporal-and-motion-encoding-for","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","date":"2019-08-07","arxiv_id":"1908.02486","repositories_listed":0,"syntology":null},{"url":"/paper/two-stream-video-classification-with-cross","slug":"two-stream-video-classification-with-cross","title":"Two-Stream Video Classification with Cross-Modality Attention","date":"2019-08-01","arxiv_id":"1908.00497","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-priors-and-meta-learning-for","title":"Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition","date":"2019-07-22","arxiv_id":"1907.09382","repositories_listed":0,"syntology":null},{"url":"/paper/a-short-note-on-the-kinetics-700-human-action","slug":"a-short-note-on-the-kinetics-700-human-action","title":"A Short Note on the Kinetics-700 Human Action Dataset","date":"2019-07-15","arxiv_id":"1907.06987","repositories_listed":0,"syntology":null},{"url":null,"slug":"delving-into-3d-action-anticipation-from","title":"Delving into 3D Action Anticipation from Streaming Videos","date":"2019-06-15","arxiv_id":"1906.06521","repositories_listed":0,"syntology":null},{"url":"/paper/hallucinating-bag-of-words-and-fisher-vector","slug":"hallucinating-bag-of-words-and-fisher-vector","title":"Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs","date":"2019-06-13","arxiv_id":"1906.05910","repositories_listed":0,"syntology":null},{"url":"/paper/learning-spatio-temporal-representation-with-3","slug":"learning-spatio-temporal-representation-with-3","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","date":"2019-06-13","arxiv_id":"1906.05571","repositories_listed":0,"syntology":null},{"url":"/paper/faster-recurrent-networks-for-video","slug":"faster-recurrent-networks-for-video","title":"FASTER Recurrent Networks for Efficient Video Classification","date":"2019-06-10","arxiv_id":"1906.04226","repositories_listed":0,"syntology":null},{"url":"/paper/video-modeling-with-correlation-networks","slug":"video-modeling-with-correlation-networks","title":"Video Modeling with Correlation Networks","date":"2019-06-07","arxiv_id":"1906.03349","repositories_listed":0,"syntology":null},{"url":null,"slug":"190600634","title":"How Much Does Audio Matter to Recognize Egocentric Object Interactions?","date":"2019-06-03","arxiv_id":"1906.00634","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-action-localization-by-progressive-1","title":"Improving Action Localization by Progressive Cross-stream Cooperation","date":"2019-05-28","arxiv_id":"1905.11575","repositories_listed":0,"syntology":null},{"url":"/paper/neural-message-passing-on-hybrid-spatio","slug":"neural-message-passing-on-hybrid-spatio","title":"Representation Learning on Visual-Symbolic Graphs for Video Understanding","date":"2019-05-17","arxiv_id":"1905.07385","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-generator-classifier-for-efficient","title":"Unified Generator-Classifier for Efficient Zero-Shot Learning","date":"2019-05-11","arxiv_id":"1905.04511","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-motion-prediction-via-pattern","title":"Human Motion Prediction via Pattern Completion in Latent Representation Space","date":"2019-04-18","arxiv_id":"1904.09039","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-action-forecasting","title":"Relational Action Forecasting","date":"2019-04-08","arxiv_id":"1904.04231","repositories_listed":0,"syntology":null},{"url":"/paper/activity-driven-weakly-supervised-object","slug":"activity-driven-weakly-supervised-object","title":"Activity Driven Weakly Supervised Object Detection","date":"2019-04-02","arxiv_id":"1904.01665","repositories_listed":0,"syntology":null},{"url":null,"slug":"startnet-online-detection-of-action-start-in","title":"StartNet: Online Detection of Action Start in Untrimmed Videos","date":"2019-03-23","arxiv_id":"1903.09868","repositories_listed":0,"syntology":null},{"url":"/paper/dmc-net-generating-discriminative-motion-cues","slug":"dmc-net-generating-discriminative-motion-cues","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","date":"2019-01-11","arxiv_id":"1901.03460","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-sequence-gan-for-group-activity","title":"Multi-Level Sequence GAN for Group Activity Recognition","date":"2018-12-18","arxiv_id":"1812.07124","repositories_listed":0,"syntology":null},{"url":"/paper/evolving-space-time-neural-architectures-for","slug":"evolving-space-time-neural-architectures-for","title":"Evolving Space-Time Neural Architectures for Videos","date":"2018-11-26","arxiv_id":"1811.10636","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-proposal-based-solution-to-spatio-temporal","title":"A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos","date":"2018-11-20","arxiv_id":"1811.08496","repositories_listed":0,"syntology":null},{"url":null,"slug":"informed-democracy-voting-based-novelty","title":"Informed Democracy: Voting-based Novelty Detection for Action Recognition","date":"2018-10-30","arxiv_id":"1810.12819","repositories_listed":0,"syntology":null},{"url":"/paper/a2-nets-double-attention-networks","slug":"a2-nets-double-attention-networks","title":"$A^2$-Nets: Double Attention Networks","date":"2018-10-27","arxiv_id":"1810.11579","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-action-tubes","title":"Predicting Action Tubes","date":"2018-08-23","arxiv_id":"1808.07712","repositories_listed":0,"syntology":null},{"url":null,"slug":"interaction-aware-spatio-temporal-pyramid","title":"Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification","date":"2018-08-03","arxiv_id":"1808.01106","repositories_listed":0,"syntology":null},{"url":"/paper/multi-fiber-networks-for-video-recognition","slug":"multi-fiber-networks-for-video-recognition","title":"Multi-Fiber Networks for Video Recognition","date":"2018-07-30","arxiv_id":"1807.11195","repositories_listed":0,"syntology":null}],"record_sha256":"4a47a6808f55864dbbad310b56488f9b2e8861351f305e7aeeed1611efdec8c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}