{"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/how-much-temporal-long-term-context-is-needed","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","arxiv_id":"2308.11358","date":"2023-08-22","proceeding":"ICCV 2023 1","authors":["Emad Bahrami","Gianpiero Francesca","Juergen Gall"],"abstract":"Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While transformers can model the long-term context of a video, this becomes computationally prohibitive for long videos. Recent works on temporal action segmentation thus combine temporal convolutional networks with self-attentions that are computed only for a local temporal window. While these approaches show good results, their performance is limited by their inability to capture the full context of a video. In this work, we try to answer how much long-term temporal context is required for temporal action segmentation by introducing a transformer-based model that leverages sparse attention to capture the full context of a video. We compare our model with the current state of the art on three datasets for temporal action segmentation, namely 50Salads, Breakfast, and Assembly101. Our experiments show that modeling the full context of a video is necessary to obtain the best performance for temporal action segmentation.","url_abs":"https://arxiv.org/abs/2308.11358v2","url_pdf":"https://arxiv.org/pdf/2308.11358v2.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":"how-much-temporal-long-term-context-is-needed","repo_url":"https://github.com/ltcontext/ltcontext","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"LTContext","rank_in_archive_order":6,"of":28,"metrics":{"Acc":"87.7","Edit":"83.2","F1@10%":"89.4","F1@25%":"87.7","F1@50%":"82.0"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-assembly101","task":"Action Segmentation","dataset":"Assembly101","model":"LTContext","rank_in_archive_order":2,"of":7,"metrics":{"Edit":"30.4","F1@10%":"33.9","F1@25%":"30.0","F1@50%":"22.6","MoF":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"LTContext","rank_in_archive_order":10,"of":37,"metrics":{"Acc":"74.2","Average F1":"70.1","Edit":"77.0","F1@10%":"77.6","F1@25%":"72.6","F1@50%":"60.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11358"}},"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/ltcontext/ltcontext","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"a3c5c349ae92e32c","entry":"construct_optimizer","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/optimizer.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a3c5c349ae92e32c"}},{"code_sha256_prefix":"da97b2878d365e41","entry":"get_epoch_lr","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/optimizer.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"da97b2878d365e41"}},{"code_sha256_prefix":"2399cfec24000d94","entry":"get_loss_func","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/loss.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2399cfec24000d94"}},{"code_sha256_prefix":"89736b7f0b2556b1","entry":"patchify","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/attention_utils.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"89736b7f0b2556b1"}},{"code_sha256_prefix":"286e98f2ad765c4b","entry":"scaled_dot_product_attention","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/attention_utils.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"286e98f2ad765c4b"}},{"code_sha256_prefix":"1da4800fb29c6527","entry":"scaled_query_key_mult","repo":"ltcontext/ltcontext","repo_kind":"official","path":"ltc/model/attention_utils.py","file_url":"https://github.com/ltcontext/ltcontext/blob/HEAD/ltc/model/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1da4800fb29c6527"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}