{"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/3","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":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"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/2","next":"/task/human-object-interaction-detection/papers/4","papers":[{"url":null,"slug":"interactedit-zero-shot-editing-of-human","title":"InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images","date":"2025-03-12","arxiv_id":"2503.09130","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-hoi-reconstruction-transformer","title":"End-to-End HOI Reconstruction Transformer with Graph-based Encoding","date":"2025-03-08","arxiv_id":"2503.06012","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-infants-to-ai-incorporating-infant-like","title":"From Infants to AI: Incorporating Infant-like Learning in Models Boosts Efficiency and Generalization in Learning Social Prediction Tasks","date":"2025-03-05","arxiv_id":"2503.03361","repositories_listed":0,"syntology":null},{"url":null,"slug":"eigenactor-variant-body-object-interaction","title":"EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning","date":"2025-03-01","arxiv_id":"2503.00382","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-affordancellm-harnessing-large-language","title":"3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds","date":"2025-02-27","arxiv_id":"2502.20041","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-motion-prediction-reconstruction-and","title":"Human Motion Prediction, Reconstruction, and Generation","date":"2025-02-21","arxiv_id":"2502.15956","repositories_listed":0,"syntology":null},{"url":null,"slug":"rhino-learning-real-time-humanoid-human","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","date":"2025-02-18","arxiv_id":"2502.13134","repositories_listed":0,"syntology":null},{"url":null,"slug":"hummingbird-high-fidelity-image-generation","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","date":"2025-02-07","arxiv_id":"2502.05153","repositories_listed":0,"syntology":null},{"url":null,"slug":"functional-3d-scene-synthesis-through-human","title":"Functional 3D Scene Synthesis through Human-Scene Optimization","date":"2025-02-05","arxiv_id":"2502.06819","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnihuman-1-rethinking-the-scaling-up-of-one","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","date":"2025-02-03","arxiv_id":"2502.01061","repositories_listed":0,"syntology":null},{"url":null,"slug":"eye-gaze-as-a-signal-for-conveying-user","title":"Eye Gaze as a Signal for Conveying User Attention in Contextual AI Systems","date":"2025-01-23","arxiv_id":"2501.13878","repositories_listed":0,"syntology":null},{"url":"/paper/dynamic-scene-understanding-from-vision","slug":"dynamic-scene-understanding-from-vision","title":"Dynamic Scene Understanding from Vision-Language Representations","date":"2025-01-20","arxiv_id":"2501.11653","repositories_listed":0,"syntology":null},{"url":null,"slug":"david-modeling-dynamic-affordance-of-3d","title":"DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models","date":"2025-01-14","arxiv_id":"2501.08333","repositories_listed":0,"syntology":null},{"url":null,"slug":"chainhoi-joint-based-kinematic-chain-modeling","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chathuman-chatting-about-3d-humans-with-tools","title":"ChatHuman: Chatting about 3D Humans with Tools","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"horp-human-object-relation-priors-guided-hoi","title":"HORP: Human-Object Relation Priors Guided HOI Detection","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-advancing-large-scale-versatile-3d","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"personahoi-effortlessly-improving-face","title":"PersonaHOI: Effortlessly Improving Face Personalization in Human-Object Interaction Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pico-reconstructing-3d-people-in-contact-with","title":"PICO: Reconstructing 3D People In Contact with Objects","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-mamba-hypergraph-guided-region","title":"Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-guided-action-enhancing-3d-human","title":"Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diffgrasp-whole-body-grasping-synthesis","title":"Diffgrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model","date":"2024-12-30","arxiv_id":"2412.20657","repositories_listed":0,"syntology":null},{"url":null,"slug":"syncdiff-synchronized-motion-diffusion-for","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","date":"2024-12-28","arxiv_id":"2412.20104","repositories_listed":0,"syntology":null},{"url":null,"slug":"zerohsi-zero-shot-4d-human-scene-interaction","title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","date":"2024-12-24","arxiv_id":"2412.18600","repositories_listed":0,"syntology":null},{"url":null,"slug":"contexthoi-spatial-context-learning-for-human","title":"ContextHOI: Spatial Context Learning for Human-Object Interaction Detection","date":"2024-12-12","arxiv_id":"2412.09050","repositories_listed":0,"syntology":null},{"url":null,"slug":"orchestrating-the-symphony-of-prompt","title":"Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection","date":"2024-12-11","arxiv_id":"2412.08506","repositories_listed":0,"syntology":null},{"url":null,"slug":"tridi-trilateral-diffusion-of-3d-humans","title":"TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions","date":"2024-12-09","arxiv_id":"2412.06334","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifting-motion-to-the-3d-world-via-2d","title":"Lifting Motion to the 3D World via 2D Diffusion","date":"2024-11-27","arxiv_id":"2411.18808","repositories_listed":0,"syntology":null},{"url":null,"slug":"ood-hoi-text-driven-3d-whole-body-human","title":"OOD-HOI: Text-Driven 3D Whole-Body Human-Object Interactions Generation Beyond Training Domains","date":"2024-11-27","arxiv_id":"2411.18660","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-hoi-vision-language-models-for","title":"VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis","date":"2024-11-27","arxiv_id":"2411.18038","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchorcrafter-animate-cyberanchors-saling","title":"AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation","date":"2024-11-26","arxiv_id":"2411.17383","repositories_listed":0,"syntology":null},{"url":null,"slug":"glover-generalizable-open-vocabulary","title":"GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping","date":"2024-11-19","arxiv_id":"2411.12286","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-object-interaction-detection","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","date":"2024-10-26","arxiv_id":"2410.20155","repositories_listed":0,"syntology":null},{"url":null,"slug":"cl-hoi-cross-level-human-object-interaction","title":"CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models","date":"2024-10-21","arxiv_id":"2410.15657","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspdiffusion-synthesizing-realistic-whole","title":"GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction","date":"2024-10-17","arxiv_id":"2410.13911","repositories_listed":0,"syntology":null},{"url":null,"slug":"3darticcyclists-generating-simulated-dynamic","title":"3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications","date":"2024-10-14","arxiv_id":"2410.10782","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":"avatargo-zero-shot-4d-human-object","title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","date":"2024-10-09","arxiv_id":"2410.07164","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-character-scene-interaction","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","date":"2024-10-04","arxiv_id":"2410.03187","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-methodological-survey-of","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","date":"2024-09-15","arxiv_id":"2409.09678","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamhoi-subject-driven-generation-of-3d","title":"DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors","date":"2024-09-12","arxiv_id":"2409.08278","repositories_listed":0,"syntology":null},{"url":null,"slug":"intertrack-tracking-human-object-interaction","title":"InterTrack: Tracking Human Object Interaction without Object Templates","date":"2024-08-25","arxiv_id":"2408.13953","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-2d-invariant-affordance-knowledge","title":"Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding","date":"2024-08-23","arxiv_id":"2408.13024","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-human-object-interaction","title":"A Review of Human-Object Interaction Detection","date":"2024-08-20","arxiv_id":"2408.10641","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-flexible-visual-relationship","title":"Towards Flexible Visual Relationship Segmentation","date":"2024-08-15","arxiv_id":"2408.08305","repositories_listed":0,"syntology":null},{"url":null,"slug":"uahoi-uncertainty-aware-robust-interaction","title":"UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection","date":"2024-08-14","arxiv_id":"2408.07430","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-human-object-interaction-ehoi","title":"Efficient Human-Object-Interaction (EHOI) Detection via Interaction Label Coding and Conditional Decision","date":"2024-08-13","arxiv_id":"2408.07018","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-hoi-using-a-training-free","title":"An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set","date":"2024-08-11","arxiv_id":"2408.05772","repositories_listed":0,"syntology":null},{"url":null,"slug":"kinematics-based-3d-human-object-interaction","title":"Kinematics-based 3D Human-Object Interaction Reconstruction from Single View","date":"2024-07-19","arxiv_id":"2407.14043","repositories_listed":0,"syntology":null},{"url":null,"slug":"f-hoi-toward-fine-grained-semantic-aligned-3d","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","date":"2024-07-17","arxiv_id":"2407.12435","repositories_listed":0,"syntology":null},{"url":null,"slug":"himo-a-new-benchmark-for-full-body-human","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","date":"2024-07-17","arxiv_id":"2407.12371","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyclehoi-improving-human-object-interaction","title":"CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generation","date":"2024-07-16","arxiv_id":"2407.11433","repositories_listed":0,"syntology":null},{"url":null,"slug":"node-adapter-neural-ordinary-differential","title":"NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning","date":"2024-07-11","arxiv_id":"2407.08672","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoimotion-forecasting-human-motion-during","title":"HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes","date":"2024-07-02","arxiv_id":"2407.02633","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-category-to-scenery-an-end-to-end","title":"From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos","date":"2024-07-01","arxiv_id":"2407.00917","repositories_listed":0,"syntology":null},{"url":null,"slug":"egogaussian-dynamic-scene-understanding-from","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","date":"2024-06-28","arxiv_id":"2406.19811","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-aware-3d-scene-generation-with","title":"Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models","date":"2024-06-26","arxiv_id":"2406.18159","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-object-interaction-from-human-level","title":"Human-Object Interaction from Human-Level Instructions","date":"2024-06-25","arxiv_id":"2406.17840","repositories_listed":0,"syntology":null},{"url":null,"slug":"coohoi-learning-cooperative-human-object","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","date":"2024-06-20","arxiv_id":"2406.14558","repositories_listed":0,"syntology":null},{"url":null,"slug":"llavidal-benchmarking-large-language-vision","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","date":"2024-06-13","arxiv_id":"2406.09390","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-human-object-interaction-detection","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","date":"2024-06-11","arxiv_id":"2406.07221","repositories_listed":0,"syntology":null},{"url":null,"slug":"egochoir-capturing-3d-human-object","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","date":"2024-05-22","arxiv_id":"2405.13659","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-observer-gaze-zero-shot","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","date":"2024-05-16","arxiv_id":"2405.09931","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtualmodel-generating-object-id-retentive","title":"VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing","date":"2024-05-16","arxiv_id":"2405.09985","repositories_listed":0,"syntology":null},{"url":"/paper/cinepile-a-long-video-question-answering","slug":"cinepile-a-long-video-question-answering","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","date":"2024-05-14","arxiv_id":"2405.08813","repositories_listed":0,"syntology":null},{"url":null,"slug":"chathuman-language-driven-3d-human","title":"ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning","date":"2024-05-07","arxiv_id":"2405.04533","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-interactive-semantic-alignment-for","title":"Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model","date":"2024-04-19","arxiv_id":"2404.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-human-interaction-motions-in","title":"Generating Human Interaction Motions in Scenes with Text Control","date":"2024-04-16","arxiv_id":"2404.10685","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-m3-capture-multiple-humans-and-objects","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","date":"2024-03-30","arxiv_id":"2404.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"interdreamer-zero-shot-text-to-3d-dynamic","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","date":"2024-03-28","arxiv_id":"2403.19652","repositories_listed":0,"syntology":null},{"url":null,"slug":"force-dataset-and-method-for-intuitive","title":"FORCE: Physics-aware Human-object Interaction","date":"2024-03-17","arxiv_id":"2403.11237","repositories_listed":0,"syntology":null},{"url":null,"slug":"thor-text-to-human-object-interaction","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","date":"2024-03-17","arxiv_id":"2403.11208","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-human-centered-dynamic-scene","title":"Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning","date":"2024-03-15","arxiv_id":"2403.10107","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-human-object-interaction","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","date":"2024-03-12","arxiv_id":"2403.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-distribution-learning-adapter-for","title":"Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning","date":"2024-03-10","arxiv_id":"2403.06059","repositories_listed":0,"syntology":null},{"url":null,"slug":"freea-human-object-interaction-detection","title":"FreeA: Human-object Interaction Detection using Free Annotation Labels","date":"2024-03-04","arxiv_id":"2403.01840","repositories_listed":0,"syntology":null},{"url":null,"slug":"parahome-parameterizing-everyday-home","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","date":"2024-01-18","arxiv_id":"2401.10232","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordancellm-grounding-affordance-from","title":"AffordanceLLM: Grounding Affordance from Vision Language Models","date":"2024-01-12","arxiv_id":"2401.06341","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-self-and-cross-triplet-correlations","title":"Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection","date":"2024-01-11","arxiv_id":"2401.05676","repositories_listed":0,"syntology":null},{"url":null,"slug":"rhobin-challenge-reconstruction-of-human","title":"RHOBIN Challenge: Reconstruction of Human Object Interaction","date":"2024-01-07","arxiv_id":"2401.04143","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-causal-group-activity-recognition-via","title":"Bi-Causal: Group Activity Recognition via Bidirectional Causality","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bilateral-adaptation-for-human-object","title":"Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-syntactic-interaction-clues-for","title":"Discovering Syntactic Interaction Clues for Human-Object Interaction Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-pose-aware-human-object-interaction","title":"Exploring Pose-Aware Human-Object Interaction via Hybrid Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-m-3-capture-multiple-humans-and-objects","title":"HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hoianimator-generating-text-prompt-human","title":"HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-observer-gaze-zero-shot-1","title":"Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pose2gaze-generating-realistic-human-gaze","title":"Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses","date":"2023-12-19","arxiv_id":"2312.12042","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniondet-union-level-detector-towards-real-1","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","date":"2023-12-19","arxiv_id":"2312.12664","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-from-augmented-label","title":"Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI","date":"2023-12-17","arxiv_id":"2312.10586","repositories_listed":0,"syntology":null},{"url":null,"slug":"primitive-based-3d-human-object-interaction","title":"Primitive-based 3D Human-Object Interaction Modelling and Programming","date":"2023-12-17","arxiv_id":"2312.10714","repositories_listed":0,"syntology":null},{"url":null,"slug":"lemon-learning-3d-human-object-interaction","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","date":"2023-12-14","arxiv_id":"2312.08963","repositories_listed":0,"syntology":null},{"url":null,"slug":"template-free-reconstruction-of-human-object","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","date":"2023-12-12","arxiv_id":"2312.07063","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-diff-text-driven-synthesis-of-3d-human","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","date":"2023-12-11","arxiv_id":"2312.06553","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-m-hoi-inertia-aware-monocular-capture-of-3d","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","date":"2023-12-10","arxiv_id":"2312.08869","repositories_listed":0,"syntology":null},{"url":null,"slug":"physhoi-physics-based-imitation-of-dynamic","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","date":"2023-12-07","arxiv_id":"2312.04393","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-human-object-interaction","title":"Controllable Human-Object Interaction Synthesis","date":"2023-12-06","arxiv_id":"2312.03913","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-interaction-representation-for","title":"Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection","date":"2023-12-04","arxiv_id":"2312.01713","repositories_listed":0,"syntology":null},{"url":null,"slug":"handypriors-physically-consistent-perception","title":"HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors","date":"2023-11-28","arxiv_id":"2311.16552","repositories_listed":0,"syntology":null},{"url":null,"slug":"cg-hoi-contact-guided-3d-human-object","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","date":"2023-11-27","arxiv_id":"2311.16097","repositories_listed":0,"syntology":null}],"record_sha256":"4d254a5120a0d6b6da04b20aacc11de7df6a0061765c77c2e4bb9021dc4d0b4c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}