Papers with Code 아카이브
Human-Object Interaction Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 6
- 보존된 평가 기록
- 103
Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models
GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction
Visual-Geometric Collaborative Guidance for Affordance Learning
3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications
Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network
AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation
Autonomous Character-Scene Interaction Synthesis from Text Instruction
Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities
DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors
InterTrack: Tracking Human Object Interaction without Object Templates
Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
A Review of Human-Object Interaction Detection
Towards Flexible Visual Relationship Segmentation
UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection
Efficient Human-Object-Interaction (EHOI) Detection via Interaction Label Coding and Conditional Decision
Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection
SkillMimic: Learning Basketball Interaction Skills from Demonstrations
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
Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection
A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap
StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Monocular Human-Object Reconstruction in the Wild
Kinematics-based 3D Human-Object Interaction Reconstruction from Single View
HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions
CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generation
NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning
Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation
HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes
From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos
Learning Granularity-Aware Affordances from Human-Object Interaction for Tool-Based Functional Grasping in Dexterous Robotics
EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.