{"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/nextvlad-an-efficient-neural-network-to","title":"NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification","arxiv_id":"1811.05014","date":"2018-11-12","proceeding":null,"authors":["Rongcheng Lin","Jing Xiao","Jianping Fan"],"abstract":"This paper introduces a fast and efficient network architecture, NeXtVLAD, to\naggregate frame-level features into a compact feature vector for large-scale\nvideo classification. Briefly speaking, the basic idea is to decompose a\nhigh-dimensional feature into a group of relatively low-dimensional vectors\nwith attention before applying NetVLAD aggregation over time. This NeXtVLAD\napproach turns out to be both effective and parameter efficient in aggregating\ntemporal information. In the 2nd Youtube-8M video understanding challenge, a\nsingle NeXtVLAD model with less than 80M parameters achieves a GAP score of\n0.87846 in private leaderboard. A mixture of 3 NeXtVLAD models results in\n0.88722, which is ranked 3rd over 394 teams. The code is publicly available at\nhttps://github.com/linrongc/youtube-8m.","url_abs":"http://arxiv.org/abs/1811.05014v1","url_pdf":"http://arxiv.org/pdf/1811.05014v1.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":"nextvlad-an-efficient-neural-network-to","repo_url":"https://github.com/linrongc/youtube-8m","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"efficient-neural-network","task_name":"Efficient Neural Network"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.05014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05014"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linrongc/youtube-8m","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"named_in_paper":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2f3219b9915649d3","entry":"FramePooling","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"model_utils.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f3219b9915649d3"}},{"code_sha256_prefix":"c7c286e6493b9cf6","entry":"SampleRandomFrames","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"model_utils.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7c286e6493b9cf6"}},{"code_sha256_prefix":"604001c4ca602f10","entry":"SampleRandomSequence","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"model_utils.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"604001c4ca602f10"}},{"code_sha256_prefix":"427f933cdb30be37","entry":"calculate_hit_at_one","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"eval_util.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/eval_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"427f933cdb30be37"}},{"code_sha256_prefix":"a3d2406f6ce64e29","entry":"calculate_precision_at_equal_recall_rate","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"eval_util.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/eval_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3d2406f6ce64e29"}},{"code_sha256_prefix":"557deb04a3b96763","entry":"flatten","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"eval_util.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/eval_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"557deb04a3b96763"}},{"code_sha256_prefix":"03117d2e243f0f99","entry":"to_csv_row","repo":"linrongc/youtube-8m","repo_kind":"named_in_paper","path":"convert_prediction_from_json_to_csv.py","file_url":"https://github.com/linrongc/youtube-8m/blob/HEAD/convert_prediction_from_json_to_csv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03117d2e243f0f99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}