OV-COCO

OV-COCO is a benchmark dataset used to evaluate open-vocabulary object detection by assessing the performance of models in recognizing and localizing object categories that were not included in the training set.

Papers using OV-COCO (4)

Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection2026Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition2026MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection2025Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model2024