{"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/human-object-interaction-detection/papers/5","list_of":"/task/human-object-interaction-detection","task":"Human-Object Interaction Detection","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":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,449],"of":449,"counts":{"archive_papers_tagged":449,"with_a_code_link":173,"where_syntology_ran_a_sample":65,"not_listed_spam_title":0,"listed":449,"listed_where_code_ran":65,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":58,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":58,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/human-object-interaction-detection","prev":"/task/human-object-interaction-detection/papers/4","next":null,"papers":[{"url":null,"slug":"joint-hand-object-3d-reconstruction-from-a","title":"Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion","date":"2020-06-28","arxiv_id":"2006.15561","repositories_listed":0,"syntology":null},{"url":null,"slug":"diagnosing-rarity-in-human-object-interaction","title":"Diagnosing Rarity in Human-Object Interaction Detection","date":"2020-06-10","arxiv_id":"2006.05728","repositories_listed":0,"syntology":null},{"url":"/paper/object-occluded-human-shape-and-pose","slug":"object-occluded-human-shape-and-pose","title":"Object-Occluded Human Shape and Pose Estimation From a Single Color Image","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-human-object-interaction-detection-via","title":"Novel Human-Object Interaction Detection via Adversarial Domain Generalization","date":"2020-05-22","arxiv_id":"2005.11406","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-firearm-carriers-by-identifying","title":"Localizing Firearm Carriers by Identifying Human-Object Pairs","date":"2020-05-19","arxiv_id":"2005.09329","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-approach-to-object-affordance","title":"A Deep Learning Approach to Object Affordance Segmentation","date":"2020-04-18","arxiv_id":"2004.08644","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-priming-for-detecting-human-object","title":"Spatial Priming for Detecting Human-Object Interactions","date":"2020-04-09","arxiv_id":"2004.04851","repositories_listed":0,"syntology":null},{"url":null,"slug":"gid-net-detecting-human-object-interaction","title":"GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency","date":"2020-03-11","arxiv_id":"2003.05242","repositories_listed":0,"syntology":null},{"url":null,"slug":"tppo-a-novel-trajectory-predictor-with-pseudo","title":"TPPO: A Novel Trajectory Predictor with Pseudo Oracle","date":"2020-02-04","arxiv_id":"2002.01852","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-all-interacting-pairs-in-a-single","title":"Classifying All Interacting Pairs in a Single Shot","date":"2020-01-13","arxiv_id":"2001.04360","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-generation-of-human-object","title":"Generating Videos of Zero-Shot Compositions of Actions and Objects","date":"2019-12-05","arxiv_id":"1912.02401","repositories_listed":0,"syntology":null},{"url":null,"slug":"tell-me-what-theyre-holding-weakly-supervised","title":"Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction","date":"2019-11-19","arxiv_id":"1911.08141","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-contextual-attention-for-human-object","title":"Deep Contextual Attention for Human-Object Interaction Detection","date":"2019-10-17","arxiv_id":"1910.07721","repositories_listed":0,"syntology":null},{"url":null,"slug":"relation-parsing-neural-network-for-human","title":"Relation Parsing Neural Network for Human-Object Interaction Detection","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-about-human-object-interactions","title":"Reasoning About Human-Object Interactions Through Dual Attention Networks","date":"2019-09-10","arxiv_id":"1909.04743","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-scene-understanding-single-view-3d","title":"Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense","date":"2019-09-04","arxiv_id":"1909.01507","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-to-spaces2s-embedding-semantics","title":"Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing","date":"2019-06-13","arxiv_id":"1906.05894","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-human-object-interaction-hotspots-1","title":"Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)","date":"2019-06-03","arxiv_id":"1906.01963","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-detect-human-object-interactions-1","title":"Learning to Detect Human-Object Interactions With Knowledge","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-region-adaptive-multi-temporal-dmm","title":"Multi-View Region Adaptive Multi-temporal DMM and RGB Action Recognition","date":"2019-04-12","arxiv_id":"1904.06074","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-human-object-interactions-via","title":"Detecting Human-Object Interactions via Functional Generalization","date":"2019-04-05","arxiv_id":"1904.03181","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-deep-neural-networks-model-nonlinear","title":"Do Deep Neural Networks Model Nonlinear Compositionality in the Neural Representation of Human-Object Interactions?","date":"2019-03-31","arxiv_id":"1904.00431","repositories_listed":0,"syntology":null},{"url":null,"slug":"turbo-learning-framework-for-human-object","title":"Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation","date":"2019-03-15","arxiv_id":"1903.06355","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-learning-for-human-object","title":"Compositional Learning for Human Object Interaction","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-as-you-intend-intention-driven-human","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","date":"2018-08-29","arxiv_id":"1808.09796","repositories_listed":0,"syntology":null},{"url":null,"slug":"imapper-interaction-guided-joint-scene-and","title":"iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos","date":"2018-06-20","arxiv_id":"1806.07889","repositories_listed":0,"syntology":null},{"url":null,"slug":"pose-based-two-stream-relational-networks-for","title":"Pose-Based Two-Stream Relational Networks for Action Recognition in Videos","date":"2018-05-22","arxiv_id":"1805.08484","repositories_listed":0,"syntology":null},{"url":"/paper/skeleton-based-action-recognition-with-1","slug":"skeleton-based-action-recognition-with-1","title":"Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning","date":"2018-05-07","arxiv_id":"1805.02335","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-joint-and-object-trajectory","title":"Simultaneous Joint and Object Trajectory Templates for Human Activity Recognition from 3-D Data","date":"2017-11-05","arxiv_id":"1711.01589","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-semantic-abstractions-of-everyday-human","title":"Deep Semantic Abstractions of Everyday Human Activities: On Commonsense Representations of Human Interactions","date":"2017-10-10","arxiv_id":"1710.04076","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-self-organizing-neural-network-architecture","title":"A self-organizing neural network architecture for learning human-object interactions","date":"2017-10-05","arxiv_id":"1710.01916","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-event-representation-as-sparse-as","title":"Learning event representation: As sparse as possible, but not sparser","date":"2017-10-02","arxiv_id":"1710.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-action-recognition-model-from-depth","title":"Learning Action Recognition Model From Depth and Skeleton Videos","date":"2017-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-event-learning-of-human-object","title":"Fine-grained Event Learning of Human-Object Interaction with LSTM-CRF","date":"2017-09-30","arxiv_id":"1710.00262","repositories_listed":0,"syntology":null},{"url":null,"slug":"care-about-you-towards-large-scale-human","title":"Care about you: towards large-scale human-centric visual relationship detection","date":"2017-05-28","arxiv_id":"1705.09892","repositories_listed":0,"syntology":null},{"url":"/paper/recurrent-models-for-situation-recognition","slug":"recurrent-models-for-situation-recognition","title":"Recurrent Models for Situation Recognition","date":"2017-03-18","arxiv_id":"1703.06233","repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-detect-human-object-interactions","slug":"learning-to-detect-human-object-interactions","title":"Learning to Detect Human-Object Interactions","date":"2017-02-17","arxiv_id":"1702.05448","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-holistic-object-recognition-enriching","title":"Beyond Holistic Object Recognition: Enriching Image Understanding with Part States","date":"2016-12-15","arxiv_id":"1612.07310","repositories_listed":0,"syntology":null},{"url":"/paper/jointly-learning-heterogeneous-features-for-1","slug":"jointly-learning-heterogeneous-features-for-1","title":"Jointly learning heterogeneous features for rgb-d activity recognition","date":"2016-12-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-centred-object-co-segmentation","title":"Human Centred Object Co-Segmentation","date":"2016-06-12","arxiv_id":"1606.03774","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-cost-scene-modeling-using-a-density","title":"Low-Cost Scene Modeling using a Density Function Improves Segmentation Performance","date":"2016-05-26","arxiv_id":"1605.08464","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-learning-of-affordances","title":"Weakly Supervised Learning of Affordances","date":"2016-05-10","arxiv_id":"1605.02964","repositories_listed":0,"syntology":null},{"url":"/paper/learning-models-for-actions-and-person-object","slug":"learning-models-for-actions-and-person-object","title":"Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering","date":"2016-04-16","arxiv_id":"1604.04808","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-person-action-object-detection-with","title":"First Person Action-Object Detection with EgoNet","date":"2016-03-15","arxiv_id":"1603.04908","repositories_listed":0,"syntology":null},{"url":"/paper/hico-a-benchmark-for-recognizing-human-object","slug":"hico-a-benchmark-for-recognizing-human-object","title":"HICO: A Benchmark for Recognizing Human-Object Interactions in Images","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interaction-part-mining-a-mid-level-approach","title":"Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-modelling-with-a-handheld-rgb-d-camera","title":"Object Modelling with a Handheld RGB-D Camera","date":"2015-05-21","arxiv_id":"1505.05643","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-human-interactions-in-videos-with","title":"Discovering Human Interactions in Videos with Limited Data Labeling","date":"2015-02-12","arxiv_id":"1502.03851","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuhoi-trento-universal-human-object","title":"TUHOI: Trento Universal Human Object Interaction Dataset","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"9b2d693e5e44b2bec2e0eef74ceeed24061ba5831dc6dba2a075a3012e99c2ca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}