{"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/temporal-alignment-networks-for-long-term","title":"Temporal Alignment Networks for Long-term Video","arxiv_id":"2204.02968","date":"2022-04-06","proceeding":"CVPR 2022 1","authors":["Tengda Han","Weidi Xie","Andrew Zisserman"],"abstract":"The objective of this paper is a temporal alignment network that ingests long term video sequences, and associated text sentences, in order to: (1) determine if a sentence is alignable with the video; and (2) if it is alignable, then determine its alignment. The challenge is to train such networks from large-scale datasets, such as HowTo100M, where the associated text sentences have significant noise, and are only weakly aligned when relevant. Apart from proposing the alignment network, we also make four contributions: (i) we describe a novel co-training method that enables to denoise and train on raw instructional videos without using manual annotation, despite the considerable noise; (ii) to benchmark the alignment performance, we manually curate a 10-hour subset of HowTo100M, totalling 80 videos, with sparse temporal descriptions. Our proposed model, trained on HowTo100M, outperforms strong baselines (CLIP, MIL-NCE) on this alignment dataset by a significant margin; (iii) we apply the trained model in the zero-shot settings to multiple downstream video understanding tasks and achieve state-of-the-art results, including text-video retrieval on YouCook2, and weakly supervised video action segmentation on Breakfast-Action; (iv) we use the automatically aligned HowTo100M annotations for end-to-end finetuning of the backbone model, and obtain improved performance on downstream action recognition tasks.","url_abs":"https://arxiv.org/abs/2204.02968v1","url_pdf":"https://arxiv.org/pdf/2204.02968v1.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":"temporal-alignment-networks-for-long-term","repo_url":"https://github.com/tengdahan/temporalalignnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02968"}},"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/tengdahan/temporalalignnet","reach":null}],"summary":{"ran":6,"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":13,"ran":7,"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":"0df2b78f603a930b","entry":"InceptionBlock","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0df2b78f603a930b"}},{"code_sha256_prefix":"8506495852b4f8b4","entry":"MaxPool3dTFPadding","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8506495852b4f8b4"}},{"code_sha256_prefix":"a2c95b29cc4457e1","entry":"ResidualAttentionBlock_Step","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2c95b29cc4457e1"}},{"code_sha256_prefix":"305b2476d6ded39a","entry":"STConv3D","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"305b2476d6ded39a"}},{"code_sha256_prefix":"570b0eeb1de9556e","entry":"SelfGating","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"570b0eeb1de9556e"}},{"code_sha256_prefix":"ef0ab5fa8216c1c7","entry":"TemporalEncoder","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef0ab5fa8216c1c7"}},{"code_sha256_prefix":"86899fbb16005e41","entry":"get_position_embedding_sine","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86899fbb16005e41"}},{"code_sha256_prefix":"56dbdac6a6137e13","entry":"S3D","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"56dbdac6a6137e13"}},{"code_sha256_prefix":"0933997ffa263669","entry":"Sentence_Embedding","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"0933997ffa263669"}},{"code_sha256_prefix":"87987b3797775fe6","entry":"TemporalAligner","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"87987b3797775fe6"}},{"code_sha256_prefix":"9afb254f1519d81b","entry":"Word2VecModel","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"9afb254f1519d81b"}},{"code_sha256_prefix":"8ada3a5d70324060","entry":"get_word2vec_text_module","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"8ada3a5d70324060"}},{"code_sha256_prefix":"24e2a428251d5383","entry":"load_milnce","repo":"tengdahan/temporalalignnet","repo_kind":"listed","path":"model/tan_model.py","file_url":"https://github.com/tengdahan/temporalalignnet/blob/HEAD/model/tan_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":"24e2a428251d5383"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}