{"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/cbinfer-exploiting-frame-to-frame-locality","title":"CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams","arxiv_id":"1808.05488","date":"2018-08-15","proceeding":null,"authors":["Lukas Cavigelli","Luca Benini"],"abstract":"The last few years have brought advances in computer vision at an amazing\npace, grounded on new findings in deep neural network construction and training\nas well as the availability of large labeled datasets. Applying these networks\nto images demands a high computational effort and pushes the use of\nstate-of-the-art networks on real-time video data out of reach of embedded\nplatforms. Many recent works focus on reducing network complexity for real-time\ninference on embedded computing platforms. We adopt an orthogonal viewpoint and\npropose a novel algorithm exploiting the spatio-temporal sparsity of pixel\nchanges. This optimized inference procedure resulted in an average speed-up of\n9.1x over cuDNN on the Tegra X2 platform at a negligible accuracy loss of <0.1%\nand no retraining of the network for a semantic segmentation application.\nSimilarly, an average speed-up of 7.0x has been achieved for a pose detection\nDNN and a reduction of 5x of the number of arithmetic operations to be\nperformed for object detection on static camera video surveillance data. These\nthroughput gains combined with a lower power consumption result in an energy\nefficiency of 511 GOp/s/W compared to 70 GOp/s/W for the baseline.","url_abs":"http://arxiv.org/abs/1808.05488v2","url_pdf":"http://arxiv.org/pdf/1808.05488v2.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":"cbinfer-exploiting-frame-to-frame-locality","repo_url":"https://github.com/lukasc-ch/CBinfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cbinfer-exploiting-frame-to-frame-locality","repo_url":"https://github.com/MHersche/eegnet-based-embedded-bci","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.05488","atlas_url":"https://app.syntology.ai/?focus=1808.05488","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":"1808.05488"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.05488\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.05488"},"call":"get_concepts_for_paper(arxiv_id=\"1808.05488\")"}],"by_repo":[{"repo":"lukasc-ch/CBinfer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MHersche/eegnet-based-embedded-bci","kind":"listed","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":"95fb98681d049ff531726ad0e91bd9f4805dcc69b6a76ac17c706e3422ee0e5f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}