{"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/convolutional-rnn-an-enhanced-model-for","title":"Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data","arxiv_id":"1602.05875","date":"2016-02-18","proceeding":null,"authors":["Gil Keren","Björn Schuller"],"abstract":"Traditional convolutional layers extract features from patches of data by\napplying a non-linearity on an affine function of the input. We propose a model\nthat enhances this feature extraction process for the case of sequential data,\nby feeding patches of the data into a recurrent neural network and using the\noutputs or hidden states of the recurrent units to compute the extracted\nfeatures. By doing so, we exploit the fact that a window containing a few\nframes of the sequential data is a sequence itself and this additional\nstructure might encapsulate valuable information. In addition, we allow for\nmore steps of computation in the feature extraction process, which is\npotentially beneficial as an affine function followed by a non-linearity can\nresult in too simple features. Using our convolutional recurrent layers we\nobtain an improvement in performance in two audio classification tasks,\ncompared to traditional convolutional layers. Tensorflow code for the\nconvolutional recurrent layers is publicly available in\nhttps://github.com/cruvadom/Convolutional-RNN.","url_abs":"http://arxiv.org/abs/1602.05875v3","url_pdf":"http://arxiv.org/pdf/1602.05875v3.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":"convolutional-rnn-an-enhanced-model-for","repo_url":"https://github.com/cruvadom/Convolutional-RNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"convolutional-rnn-an-enhanced-model-for","repo_url":"https://github.com/fmohaghegh/OceanWavePrediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"convolutional-rnn-an-enhanced-model-for","repo_url":"https://github.com/rickyHong/Conv-RNN-repl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.05875","atlas_url":"https://app.syntology.ai/?focus=1602.05875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.05875"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/cruvadom/Convolutional-RNN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fmohaghegh/OceanWavePrediction","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rickyHong/Conv-RNN-repl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":1,"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":"a8b0b6ae101b2131","entry":"crnn","repo":"cruvadom/Convolutional-RNN","repo_kind":"official","path":"CRNN.py","file_url":"https://github.com/cruvadom/Convolutional-RNN/blob/HEAD/CRNN.py","link_basis":"first_harvest_node","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":"a8b0b6ae101b2131"}},{"code_sha256_prefix":"c5ca6d473712d194","entry":"next_batch","repo":"fmohaghegh/OceanWavePrediction","repo_kind":"listed","path":"Training.py","file_url":"https://github.com/fmohaghegh/OceanWavePrediction/blob/HEAD/Training.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5ca6d473712d194"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}