{"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-segmentation/papers/2","list_of":"/task/action-segmentation","task":"Action Segmentation","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":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":219,"counts":{"archive_papers_tagged":219,"with_a_code_link":99,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":219,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":25,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":25,"listed_every_run_a_failure_of_syntologys_instrument":2,"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-segmentation","prev":"/task/action-segmentation","next":"/task/action-segmentation/papers/3","papers":[{"url":null,"slug":"m2r2-mulitmodal-robotic-representation-for","title":"M2R2: MulitModal Robotic Representation for Temporal Action Segmentation","date":"2025-04-25","arxiv_id":"2504.18662","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni4d-a-unified-self-supervised-learning","title":"Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videos","date":"2025-04-07","arxiv_id":"2504.04837","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalizing-temporal-action","title":"Towards Generalizing Temporal Action Segmentation to Unseen Views","date":"2025-04-03","arxiv_id":"2504.02512","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-changed-and-what-could-have-changed","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","date":"2025-03-27","arxiv_id":"2503.21055","repositories_listed":0,"syntology":null},{"url":null,"slug":"condensing-action-segmentation-datasets-via","title":"Condensing Action Segmentation Datasets via Generative Network Inversion","date":"2025-03-18","arxiv_id":"2503.14112","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-action-segmentation-transformer","title":"End-to-End Action Segmentation Transformer","date":"2025-03-08","arxiv_id":"2503.06316","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-action-segmentation-via-explicit","title":"Improving action segmentation via explicit similarity measurement","date":"2025-02-15","arxiv_id":"2502.10713","repositories_listed":0,"syntology":null},{"url":null,"slug":"timelogic-a-temporal-logic-benchmark-for","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","date":"2025-01-13","arxiv_id":"2501.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-multi-task-activities-from","title":"Understanding Multi-Task Activities from Single-Task Videos","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-context-consistency-above-all","title":"Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints","date":"2024-12-27","arxiv_id":"2412.19424","repositories_listed":0,"syntology":null},{"url":null,"slug":"stitch-contrast-and-segment-learning-a-human","title":"Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos","date":"2024-12-19","arxiv_id":"2412.14988","repositories_listed":0,"syntology":null},{"url":null,"slug":"2by2-weakly-supervised-learning-for-global","title":"2by2: Weakly-Supervised Learning for Global Action Segmentation","date":"2024-12-17","arxiv_id":"2412.12829","repositories_listed":0,"syntology":null},{"url":null,"slug":"actfusion-a-unified-diffusion-model-for","title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","date":"2024-12-05","arxiv_id":"2412.04353","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-llms-for-temporal-reasoning-in-long","title":"Video LLMs for Temporal Reasoning in Long Videos","date":"2024-12-04","arxiv_id":"2412.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-spatio-temporal-relations-in","title":"Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network","date":"2024-10-10","arxiv_id":"2410.07912","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal2seq-a-unified-framework-for-temporal","title":"Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks","date":"2024-09-27","arxiv_id":"2409.18478","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02024","title":"Faster Diffusion Action Segmentation","date":"2024-08-04","arxiv_id":"2408.02024","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamba4d-efficient-long-sequence-point-cloud","title":"MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models","date":"2024-05-23","arxiv_id":"2405.14338","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoist-former-hand-held-objects-identification","title":"HOIST-Former: Hand-held Objects Identification, Segmentation, and Tracking in the Wild","date":"2024-04-22","arxiv_id":"2404.13819","repositories_listed":0,"syntology":null},{"url":null,"slug":"o-talc-steps-towards-combating","title":"O-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation","date":"2024-04-10","arxiv_id":"2404.06894","repositories_listed":0,"syntology":null},{"url":null,"slug":"coherent-temporal-synthesis-for-incremental","title":"Coherent Temporal Synthesis for Incremental Action Segmentation","date":"2024-03-10","arxiv_id":"2403.06102","repositories_listed":0,"syntology":null},{"url":null,"slug":"adl4d-towards-a-contextually-rich-dataset-for","title":"ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living","date":"2024-02-27","arxiv_id":"2402.17758","repositories_listed":0,"syntology":null},{"url":null,"slug":"vistec-video-modeling-for-sports-technique","title":"ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis","date":"2024-02-25","arxiv_id":"2402.15952","repositories_listed":0,"syntology":null},{"url":null,"slug":"friends-across-time-multi-scale-action","title":"Friends Across Time: Multi-Scale Action Segmentation Transformer for Surgical Phase Recognition","date":"2024-01-22","arxiv_id":"2401.11644","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-over-rgb-automatic-evaluation-of-open","title":"Depth Over RGB: Automatic Evaluation of Open Surgery Skills Using Depth Camera","date":"2024-01-18","arxiv_id":"2401.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-imitation-of-human-actions","title":"Robotic Imitation of Human Actions","date":"2024-01-16","arxiv_id":"2401.08381","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-detection-in-egocentric-procedural-task","title":"Error Detection in Egocentric Procedural Task Videos","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hoist-former-hand-held-objects-identification-1","title":"HOIST-Former: Hand-held Objects Identification Segmentation and Tracking in the Wild","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sfgans-self-supervised-future-generator-for","title":"SFGANS Self-supervised Future Generator for human ActioN Segmentation","date":"2023-12-31","arxiv_id":"2401.00438","repositories_listed":0,"syntology":null},{"url":null,"slug":"synchronization-is-all-you-need-exocentric-to","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","date":"2023-12-05","arxiv_id":"2312.02638","repositories_listed":0,"syntology":null},{"url":"/paper/adafocus-towards-end-to-end-weakly-supervised","slug":"adafocus-towards-end-to-end-weakly-supervised","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","date":"2023-11-28","arxiv_id":"2311.17118","repositories_listed":0,"syntology":null},{"url":null,"slug":"casr-refining-action-segmentation-via","title":"CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships","date":"2023-11-21","arxiv_id":"2311.12401","repositories_listed":0,"syntology":null},{"url":null,"slug":"nsm4d-neural-scene-model-based-online-4d","title":"NSM4D: Neural Scene Model Based Online 4D Point Cloud Sequence Understanding","date":"2023-10-12","arxiv_id":"2310.08326","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-segmentation-using-2d-skeleton","title":"Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion","date":"2023-09-12","arxiv_id":"2309.06462","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-enhanced-hierarchical-transformer","title":"Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentation","date":"2023-08-31","arxiv_id":"2308.16552","repositories_listed":0,"syntology":null},{"url":"/paper/bit-bi-level-temporal-modeling-for-efficient","slug":"bit-bi-level-temporal-modeling-for-efficient","title":"BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation","date":"2023-08-28","arxiv_id":"2308.14900","repositories_listed":0,"syntology":null},{"url":null,"slug":"lac-latent-action-composition-for-skeleton","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","date":"2023-08-28","arxiv_id":"2308.14500","repositories_listed":0,"syntology":null},{"url":null,"slug":"dpmix-mixture-of-depth-and-point-cloud-video","title":"DPMix: Mixture of Depth and Point Cloud Video Experts for 4D Action Segmentation","date":"2023-07-31","arxiv_id":"2307.16803","repositories_listed":0,"syntology":null},{"url":"/paper/sf-tmn-slowfast-temporal-modeling-network-for","slug":"sf-tmn-slowfast-temporal-modeling-network-for","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","date":"2023-06-15","arxiv_id":"2306.08859","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transformer-backbone-for-egocentric","title":"Enhancing Transformer Backbone for Egocentric Video Action Segmentation","date":"2023-05-19","arxiv_id":"2305.11365","repositories_listed":0,"syntology":null},{"url":null,"slug":"med-vt-multiscale-encoder-decoder-video","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","date":"2023-04-12","arxiv_id":"2304.05930","repositories_listed":0,"syntology":null},{"url":null,"slug":"therbligs-in-action-video-understanding","title":"Therbligs in Action: Video Understanding through Motion Primitives","date":"2023-04-06","arxiv_id":"2304.03631","repositories_listed":0,"syntology":null},{"url":null,"slug":"dir-as-decoupling-individual-identification","title":"DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation","date":"2023-04-04","arxiv_id":"2304.02110","repositories_listed":0,"syntology":null},{"url":null,"slug":"taec-unsupervised-action-segmentation-with","title":"TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering","date":"2023-03-09","arxiv_id":"2303.05166","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-segment-transformer-for-action","title":"Temporal Segment Transformer for Action Segmentation","date":"2023-02-25","arxiv_id":"2302.13074","repositories_listed":0,"syntology":null},{"url":"/paper/aspnet-action-segmentation-with-shared","slug":"aspnet-action-segmentation-with-shared","title":"ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lac-latent-action-composition-for-skeleton-1","title":"LAC - Latent Action Composition for Skeleton-based Action Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-game-video-augmentation-for-action","title":"Markov Game Video Augmentation for Action Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-the-label-bias-for-timestamp","title":"Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-action-segmentation-via-contextually","title":"Video Action Segmentation via Contextually Refined Temporal Keypoints","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-action-segmentation-and-1","title":"Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"c2f-tcn-a-framework-for-semi-and-fully","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","date":"2022-12-20","arxiv_id":"2212.11078","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":"distill-and-collect-for-semi-supervised","title":"Distill and Collect for Semi-Supervised Temporal Action Segmentation","date":"2022-11-02","arxiv_id":"2211.01311","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-action-segmentation-from-timestamp","title":"Robust Action Segmentation from Timestamp Supervision","date":"2022-10-12","arxiv_id":"2210.06501","repositories_listed":0,"syntology":null},{"url":"/paper/semantic2graph-graph-based-multi-modal","slug":"semantic2graph-graph-based-multi-modal","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","date":"2022-09-13","arxiv_id":"2209.05653","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-circular-window-based-cascade-transformer","title":"A Circular Window-based Cascade Transformer for Online Action Detection","date":"2022-08-30","arxiv_id":"2208.14209","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generalized-robust-framework-for-timestamp","title":"A Generalized & Robust Framework For Timestamp Supervision in Temporal Action Segmentation","date":"2022-07-20","arxiv_id":"2207.10137","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-framework-for-few-shot-skeleton","title":"An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation","date":"2022-07-20","arxiv_id":"2207.09925","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-action-affinity-and-continuity-for","title":"Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation","date":"2022-07-18","arxiv_id":"2207.08653","repositories_listed":0,"syntology":null},{"url":null,"slug":"turning-to-a-teacher-for-timestamp-supervised","title":"Turning to a Teacher for Timestamp Supervised Temporal Action Segmentation","date":"2022-07-02","arxiv_id":"2207.00712","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-temporally-dynamic-data","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","date":"2022-06-30","arxiv_id":"2206.15015","repositories_listed":0,"syntology":null},{"url":null,"slug":"timestamp-supervised-action-segmentation-with","title":"Timestamp-Supervised Action Segmentation with Graph Convolutional Networks","date":"2022-06-30","arxiv_id":"2206.15031","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-phase-recognition-in-laparoscopic","title":"Surgical Phase Recognition in Laparoscopic Cholecystectomy","date":"2022-06-14","arxiv_id":"2206.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-wireless-vision-dataset-for-privacy","title":"A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition","date":"2022-05-24","arxiv_id":"2205.11962","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-parsing-using-context-features","title":"Action parsing using context features","date":"2022-05-20","arxiv_id":"2205.10008","repositories_listed":0,"syntology":null},{"url":"/paper/maximization-and-restoration-action","slug":"maximization-and-restoration-action","title":"Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction","date":"2022-05-02","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-online-action-segmentation","title":"Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos","date":"2022-03-24","arxiv_id":"2203.13309","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":"transformers-in-action-weakly-supervised","title":"Transformers in Action: Weakly Supervised Action Segmentation","date":"2022-01-14","arxiv_id":"2201.05675","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-unsupervised-action-boundary","title":"Fast and Unsupervised Action Boundary Detection for Action Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"long-short-view-feature-decomposition-via","title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","date":"2021-09-23","arxiv_id":"2109.11593","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":"temporal-action-segmentation-with-high-level","title":"Temporal Action Segmentation with High-level Complex Activity Labels","date":"2021-08-15","arxiv_id":"2108.06706","repositories_listed":0,"syntology":null},{"url":"/paper/fifa-fast-inference-approximation-for-action","slug":"fifa-fast-inference-approximation-for-action","title":"FIFA: Fast Inference Approximation for Action Segmentation","date":"2021-08-09","arxiv_id":"2108.03894","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-action-segmentation-for","title":"Unsupervised Action Segmentation for Instructional Videos","date":"2021-06-07","arxiv_id":"2106.03738","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-action-segmentation-with-self","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","date":"2021-05-29","arxiv_id":"2105.14158","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/unsupervised-discriminative-embedding-for-sub","slug":"unsupervised-discriminative-embedding-for-sub","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","date":"2021-04-30","arxiv_id":"2105.00067","repositories_listed":0,"syntology":null},{"url":"/paper/action-segmentation-with-mixed-temporal","slug":"action-segmentation-with-mixed-temporal","title":"Action Segmentation with Mixed Temporal Domain Adaptation","date":"2021-04-15","arxiv_id":"2104.07461","repositories_listed":0,"syntology":null},{"url":"/paper/action-shuffle-alternating-learning-for","slug":"action-shuffle-alternating-learning-for","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","date":"2021-04-05","arxiv_id":"2104.02116","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchor-constrained-viterbi-for-set-supervised","title":"Anchor-Constrained Viterbi for Set-Supervised Action Segmentation","date":"2021-04-05","arxiv_id":"2104.02113","repositories_listed":0,"syntology":null},{"url":"/paper/depthwise-separable-temporal-convolutional","slug":"depthwise-separable-temporal-convolutional","title":"Depthwise Separable Temporal Convolutional Network for Action Segmentation","date":"2021-01-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/relational-graph-learning-on-visual-and","slug":"relational-graph-learning-on-visual-and","title":"Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery","date":"2020-11-03","arxiv_id":"2011.01619","repositories_listed":0,"syntology":null},{"url":"/paper/actor-and-action-modular-network-for-text","slug":"actor-and-action-modular-network-for-text","title":"Actor and Action Modular Network for Text-based Video Segmentation","date":"2020-11-02","arxiv_id":"2011.00786","repositories_listed":0,"syntology":null},{"url":"/paper/improving-action-segmentation-via-graph-based","slug":"improving-action-segmentation-via-graph-based","title":"Improving Action Segmentation via Graph-Based Temporal Reasoning","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"motion2vec-semi-supervised-representation","title":"Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos","date":"2020-05-31","arxiv_id":"2006.00545","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-evaluating-weakly-supervised-action","title":"On Evaluating Weakly Supervised Action Segmentation Methods","date":"2020-05-19","arxiv_id":"2005.09743","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-attention-network-for-action-1","title":"Hierarchical Attention Network for Action Segmentation","date":"2020-05-07","arxiv_id":"2005.03209","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-weakly-supervised-video-actor","title":"Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection","date":"2020-03-29","arxiv_id":"2003.13141","repositories_listed":0,"syntology":null},{"url":null,"slug":"set-constrained-viterbi-for-set-supervised","title":"Set-Constrained Viterbi for Set-Supervised Action Segmentation","date":"2020-02-27","arxiv_id":"2002.11925","repositories_listed":0,"syntology":null},{"url":"/paper/automatic-gesture-recognition-in-robot","slug":"automatic-gesture-recognition-in-robot","title":"Automatic Gesture Recognition in Robot-assisted Surgery with Reinforcement Learning and Tree Search","date":"2020-02-20","arxiv_id":"2002.08718","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-visual-temporal-embedding-for","title":"Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences","date":"2020-01-29","arxiv_id":"2001.11122","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":null,"slug":"coupled-generative-adversarial-network-for","title":"Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation","date":"2019-09-20","arxiv_id":"1909.09283","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":"/paper/an-efficient-3d-cnn-for-actionobject","slug":"an-efficient-3d-cnn-for-actionobject","title":"An Efficient 3D CNN for Action/Object Segmentation in Video","date":"2019-07-21","arxiv_id":"1907.08895","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-rnn-hmm-approach-for-weakly","title":"A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation","date":"2019-06-03","arxiv_id":"1906.01028","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":"fine-grained-semantic-segmentation-of-motion","title":"Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks","date":"2019-03-02","arxiv_id":"1903.00695","repositories_listed":0,"syntology":null}],"record_sha256":"d48ef8213ad16e1827f2a149390524e541cf18dbea5a8074bb380ed82d11d1f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}