V-COCO

The V-COCO dataset is a benchmark that contains images annotated with human-object interactions, used to evaluate the performance of models in detecting and classifying these interactions.

Papers using V-COCO (17)

Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection2026CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection2025QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection2025Relational Context Learning for Human-Object Interaction Detection2023 · 57 citesLearning Human-Object Interaction Detection using Interaction Points2020 · 35 citesVisual Compositional Learning for Human-Object Interaction Detection2020 · 12 citesEnd-to-End Human Object Interaction Detection with HOI Transformer2021 · 5 citesEfficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer2021 · 5 citesGTNet:Guided Transformer Network for Detecting Human-Object Interactions2021 · 4 citesUnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection2023 · 4 citesPrompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection2023 · 3 citesExploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection2022 · 2 citesWhat to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions2022 · 1 citesExploring Predicate Visual Context in Detecting Human-Object Interactions2023 · 1 citesHuman Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior2021Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model2024Detecting Visual Relationships Using Box Attention2018