{"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/fivr-fine-grained-incident-video-retrieval","title":"FIVR: Fine-grained Incident Video Retrieval","arxiv_id":"1809.04094","date":"2018-09-11","proceeding":null,"authors":["Giorgos Kordopatis-Zilos","Symeon Papadopoulos","Ioannis Patras","Ioannis Kompatsiaris"],"abstract":"This paper introduces the problem of Fine-grained Incident Video Retrieval\n(FIVR). Given a query video, the objective is to retrieve all associated\nvideos, considering several types of associations that range from duplicate\nvideos to videos from the same incident. FIVR offers a single framework that\ncontains several retrieval tasks as special cases. To address the benchmarking\nneeds of all such tasks, we construct and present a large-scale annotated video\ndataset, which we call FIVR-200K, and it comprises 225,960 videos. To create\nthe dataset, we devise a process for the collection of YouTube videos based on\nmajor news events from recent years crawled from Wikipedia and deploy a\nretrieval pipeline for the automatic selection of query videos based on their\nestimated suitability as benchmarks. We also devise a protocol for the\nannotation of the dataset with respect to the four types of video associations\ndefined by FIVR. Finally, we report the results of an experimental study on the\ndataset comparing five state-of-the-art methods developed based on a variety of\nvisual descriptors, highlighting the challenges of the current problem.","url_abs":"http://arxiv.org/abs/1809.04094v2","url_pdf":"http://arxiv.org/pdf/1809.04094v2.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":[{"paper_slug":"fivr-fine-grained-incident-video-retrieval","repo_url":"https://github.com/MKLab-ITI/FIVR-200K","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"fivr-200k","name":"FIVR-200K","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.04094","atlas_url":"https://app.syntology.ai/?focus=1809.04094","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}