{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/noscope-optimizing-neural-network-queries","title":"NoScope: Optimizing Neural Network Queries over Video at Scale","arxiv_id":"1703.02529","date":"2017-03-07","proceeding":null,"authors":["Daniel Kang","John Emmons","Firas Abuzaid","Peter Bailis","Matei Zaharia"],"abstract":"Recent advances in computer vision-in the form of deep neural networks-have\nmade it possible to query increasing volumes of video data with high accuracy.\nHowever, neural network inference is computationally expensive at scale:\napplying a state-of-the-art object detector in real time (i.e., 30+ frames per\nsecond) to a single video requires a $4000 GPU. In response, we present\nNoScope, a system for querying videos that can reduce the cost of neural\nnetwork video analysis by up to three orders of magnitude via\ninference-optimized model search. Given a target video, object to detect, and\nreference neural network, NoScope automatically searches for and trains a\nsequence, or cascade, of models that preserves the accuracy of the reference\nnetwork but is specialized to the target video and are therefore far less\ncomputationally expensive. NoScope cascades two types of models: specialized\nmodels that forego the full generality of the reference model but faithfully\nmimic its behavior for the target video and object; and difference detectors\nthat highlight temporal differences across frames. We show that the optimal\ncascade architecture differs across videos and objects, so NoScope uses an\nefficient cost-based optimizer to search across models and cascades. With this\napproach, NoScope achieves two to three order of magnitude speed-ups\n(265-15,500x real-time) on binary classification tasks over fixed-angle webcam\nand surveillance video while maintaining accuracy within 1-5% of\nstate-of-the-art neural networks.","url_abs":"http://arxiv.org/abs/1703.02529v3","url_pdf":"http://arxiv.org/pdf/1703.02529v3.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":"noscope-optimizing-neural-network-queries","repo_url":"https://github.com/stanford-futuredata/noscope","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.02529","atlas_url":"https://app.syntology.ai/?focus=1703.02529","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1703.02529"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.02529\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.02529"},"call":"get_concepts_for_paper(arxiv_id=\"1703.02529\")"}],"by_repo":[{"repo":"stanford-futuredata/noscope","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"886ff912b1351ff63ec795f4c60eeccc8fa627eb9f717e453c5f91b022e024fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}