{"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/recognizing-objects-in-the-wild-where-do-we","title":"Recognizing Objects In-the-wild: Where Do We Stand?","arxiv_id":"1709.05862","date":"2017-09-18","proceeding":null,"authors":["Mohammad Reza Loghmani","Barbara Caputo","Markus Vincze"],"abstract":"The ability to recognize objects is an essential skill for a robotic system\nacting in human-populated environments. Despite decades of effort from the\nrobotic and vision research communities, robots are still missing good visual\nperceptual systems, preventing the use of autonomous agents for real-world\napplications. The progress is slowed down by the lack of a testbed able to\naccurately represent the world perceived by the robot in-the-wild. In order to\nfill this gap, we introduce a large-scale, multi-view object dataset collected\nwith an RGB-D camera mounted on a mobile robot. The dataset embeds the\nchallenges faced by a robot in a real-life application and provides a useful\ntool for validating object recognition algorithms. Besides describing the\ncharacteristics of the dataset, the paper evaluates the performance of a\ncollection of well-established deep convolutional networks on the new dataset\nand analyzes the transferability of deep representations from Web images to\nrobotic data. Despite the promising results obtained with such representations,\nthe experiments demonstrate that object classification with real-life robotic\ndata is far from being solved. Finally, we provide a comparative study to\nanalyze and highlight the open challenges in robot vision, explaining the\ndiscrepancies in the performance.","url_abs":"http://arxiv.org/abs/1709.05862v2","url_pdf":"http://arxiv.org/pdf/1709.05862v2.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":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[{"slug":"arid","name":"ARID","full_name":"Autonomous Robot Indoor Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}