{"url":"/task/object-detection-in-indoor-scenes","name":"Object Detection In Indoor Scenes","slug":"object-detection-in-indoor-scenes","description_markdown":"Object detection in indoor scenes is the task of performing object detection within an indoor environment.\r\n\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Faster Bounding Box Annotation for Object Detection in Indoor Scenes](https://arxiv.org/pdf/1807.03142v1.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":9,"papers_with_code":4,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/object-detection-in-indoor-scenes-on-sun-rgb","slug":"object-detection-in-indoor-scenes-on-sun-rgb","dataset":"SUN RGB-D","dataset_url":"/dataset/sun-rgb-d","rows_in_archive":7,"metrics":["AP 0.5"],"first_row_in_archive_order":{"model":"YONOD + CPPM (RGB + Depth)","paper_title":"Unified Object Detector for Different Modalities based on Vision Transformers","paper_url":"/paper/you-only-need-one-detector-unified-object","paper_date":"2022-07-03","arxiv_id":"2207.01071","code_links":[{"title":"liketheflower/uoddm","url":"https://github.com/liketheflower/uoddm"}],"syntology":null}}],"datasets":[{"url":"/dataset/sun-rgb-d","name":"SUN RGB-D","full_name":"SUN RGB-D","num_papers_in_archive":477},{"url":"/dataset/kitchen-scenes","name":"Kitchen Scenes","full_name":"","num_papers_in_archive":4},{"url":"/dataset/isod","name":"ISOD","full_name":"Indoor Small Object Dataset","num_papers_in_archive":1},{"url":"/dataset/bottles-and-cups-dataset-household-objects","name":"Bottles and Cups Dataset | Household Objects","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/electronics-object-image-dataset-computer","name":"Electronics Object Image Dataset | Computer Parts","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/masks-dataset-indoor-object-images","name":"Masks Dataset | Unattended Mask Images","full_name":"","num_papers_in_archive":0},{"url":"/dataset/mobile-phone-dataset-smartphone-feature-phone","name":"Mobile Phone Dataset | Smartphone & Feature Phone","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/stairs-image-dataset-parts-of-house-indoor","name":"Stairs Image Dataset | Parts of House | Indoor","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/suitcase-luggage-dataset-indoor-object-image","name":"Suitcase/Luggage Dataset Indoor Object Image","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/transparent-object-images-indoor-object","name":"Transparent Object Images | Indoor Object Dataset","full_name":"datacluster.ai","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":9,"items":[{"url":"/paper/frustum-pointnets-for-3d-object-detection","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","date":"2017-11-22","arxiv_id":"1711.08488","repositories_listed":68,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/simcrosstrans-a-simple-cross-modality","title":"simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers","date":"2022-03-20","arxiv_id":"2203.10456","repositories_listed":3,"syntology":null},{"url":"/paper/you-only-need-one-detector-unified-object","title":"Unified Object Detector for Different Modalities based on Vision Transformers","date":"2022-07-03","arxiv_id":"2207.01071","repositories_listed":1,"syntology":null},{"url":"/paper/learning-rich-features-from-rgb-d-images-for","title":"Learning Rich Features from RGB-D Images for Object Detection and Segmentation","date":"2014-07-22","arxiv_id":"1407.5736","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}