{"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/weakly-supervised-action-segmentation-with","title":"Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment","arxiv_id":"1803.10699","date":"2018-03-28","proceeding":"CVPR 2018 6","authors":["Li Ding","Chenliang Xu"],"abstract":"In this work, we address the task of weakly-supervised human action\nsegmentation in long, untrimmed videos. Recent methods have relied on expensive\nlearning models, such as Recurrent Neural Networks (RNN) and Hidden Markov\nModels (HMM). However, these methods suffer from expensive computational cost,\nthus are unable to be deployed in large scale. To overcome the limitations, the\nkeys to our design are efficiency and scalability. We propose a novel action\nmodeling framework, which consists of a new temporal convolutional network,\nnamed Temporal Convolutional Feature Pyramid Network (TCFPN), for predicting\nframe-wise action labels, and a novel training strategy for weakly-supervised\nsequence modeling, named Iterative Soft Boundary Assignment (ISBA), to align\naction sequences and update the network in an iterative fashion. The proposed\nframework is evaluated on two benchmark datasets, Breakfast and Hollywood\nExtended, with four different evaluation metrics. Extensive experimental\nresults show that our methods achieve competitive or superior performance to\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1803.10699v1","url_pdf":"http://arxiv.org/pdf/1803.10699v1.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":"weakly-supervised-action-segmentation-with","repo_url":"https://github.com/ld-ing/TCFPN-ISBA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10699"}},"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/ld-ing/TCFPN-ISBA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"447d62a8aaf794fa","entry":"IOU","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/weak_model.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/weak_model.py","link_basis":"first_harvest_node","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":"447d62a8aaf794fa"}},{"code_sha256_prefix":"98987430faeae0e4","entry":"WaveNet_activation","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/tf_models.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/tf_models.py","link_basis":"plan_row","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":"98987430faeae0e4"}},{"code_sha256_prefix":"8004ab3df5eb8302","entry":"accuracy","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","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":"8004ab3df5eb8302"}},{"code_sha256_prefix":"a1626b36aac8dda8","entry":"accuracy_wo_bg","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","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":"a1626b36aac8dda8"}},{"code_sha256_prefix":"f697d40c53839400","entry":"channel_normalization","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/tf_models.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/tf_models.py","link_basis":"first_harvest_node","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":"f697d40c53839400"}},{"code_sha256_prefix":"05d3a1ae264e9961","entry":"dice_coeff","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/weak_model.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/weak_model.py","link_basis":"first_harvest_node","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":"05d3a1ae264e9961"}},{"code_sha256_prefix":"681223622b9eab57","entry":"dice_loss","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/weak_model.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/weak_model.py","link_basis":"first_harvest_node","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":"681223622b9eab57"}},{"code_sha256_prefix":"7f7a53e95b6da888","entry":"macro_accuracy","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","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":"7f7a53e95b6da888"}},{"code_sha256_prefix":"8eb9376364bd190f","entry":"max_filter","repo":"ld-ing/TCFPN-ISBA","repo_kind":"official","path":"utils/tf_models.py","file_url":"https://github.com/ld-ing/TCFPN-ISBA/blob/HEAD/utils/tf_models.py","link_basis":"first_harvest_node","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":"8eb9376364bd190f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}