{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/learning-to-detect-human-object-interactions","title":"Learning to Detect Human-Object Interactions","arxiv_id":"1702.05448","date":"2017-02-17","proceeding":null,"authors":["Yu-Wei Chao","Yunfan Liu","Xieyang Liu","Huayi Zeng","Jia Deng"],"abstract":"We study the problem of detecting human-object interactions (HOI) in static\nimages, defined as predicting a human and an object bounding box with an\ninteraction class label that connects them. HOI detection is a fundamental\nproblem in computer vision as it provides semantic information about the\ninteractions among the detected objects. We introduce HICO-DET, a new large\nbenchmark for HOI detection, by augmenting the current HICO classification\nbenchmark with instance annotations. To solve the task, we propose Human-Object\nRegion-based Convolutional Neural Networks (HO-RCNN). At the core of our\nHO-RCNN is the Interaction Pattern, a novel DNN input that characterizes the\nspatial relations between two bounding boxes. Experiments on HICO-DET\ndemonstrate that our HO-RCNN, by exploiting human-object spatial relations\nthrough Interaction Patterns, significantly improves the performance of HOI\ndetection over baseline approaches.","url_abs":"http://arxiv.org/abs/1702.05448v2","url_pdf":"http://arxiv.org/pdf/1702.05448v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[{"slug":"hico-det","name":"HICO-DET","full_name":"HICO-DET"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.05448","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}