{"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/seco-exploring-sequence-supervision-for","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","arxiv_id":"2008.00975","date":"2020-08-03","proceeding":null,"authors":["Ting Yao","Yiheng Zhang","Zhaofan Qiu","Yingwei Pan","Tao Mei"],"abstract":"A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised learning models. In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. We materialize the supervisory signals through determining whether a pair of samples is from one frame or from one video, and whether a triplet of samples is in the correct temporal order. We uniquely regard the signals as the foundation in contrastive learning and derive a particular form named Sequence Contrastive Learning (SeCo). SeCo shows superior results under the linear protocol on action recognition (Kinetics), untrimmed activity recognition (ActivityNet) and object tracking (OTB-100). More remarkably, SeCo demonstrates considerable improvements over recent unsupervised pre-training techniques, and leads the accuracy by 2.96% and 6.47% against fully-supervised ImageNet pre-training in action recognition task on UCF101 and HMDB51, respectively. Source code is available at \\url{https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning}.","url_abs":"https://arxiv.org/abs/2008.00975v2","url_pdf":"https://arxiv.org/pdf/2008.00975v2.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":"seco-exploring-sequence-supervision-for","repo_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"seco-exploring-sequence-supervision-for","repo_url":"https://github.com/amazon-research/video-contrastive-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"seco-exploring-sequence-supervision-for","repo_url":"https://github.com/yihengzhang-cv/mcl-motion-focused-contrastive-learning","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":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.00975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00975"}},"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/yihengzhang-cv/mcl-motion-focused-contrastive-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amazon-research/video-contrastive-learning","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":"d9def42110729a85","entry":"conv1x1","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/resnet_mlp.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/resnet_mlp.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/resnet_mlp.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/resnet_mlp.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"b8c658b30275edd5","entry":"dist_collect","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/util.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/util.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":"b8c658b30275edd5"}},{"code_sha256_prefix":"088dafd9a0b63f68","entry":"get_scheduler","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/lr_scheduler.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/lr_scheduler.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":"088dafd9a0b63f68"}},{"code_sha256_prefix":"e1f51bffd0f854ea","entry":"get_scheduler","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"downstream/finetune/seco_util/lr_scheduler.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/downstream/finetune/seco_util/lr_scheduler.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":"e1f51bffd0f854ea"}},{"code_sha256_prefix":"5f0f7c378e04ba6a","entry":"reduce_tensor","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/util.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/util.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":"5f0f7c378e04ba6a"}},{"code_sha256_prefix":"3e37923456ab1ce2","entry":"resnet18","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/resnet_mlp.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/resnet_mlp.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":"3e37923456ab1ce2"}},{"code_sha256_prefix":"2bc1a6995919387c","entry":"setup_logger","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"seco/logger.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/seco/logger.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":"2bc1a6995919387c"}},{"code_sha256_prefix":"b3e807e95563a2b9","entry":"setup_logger","repo":"YihengZhang-CV/SeCo-Sequence-Contrastive-Learning","repo_kind":"official","path":"downstream/finetune/seco_util/logger.py","file_url":"https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning/blob/HEAD/downstream/finetune/seco_util/logger.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":"b3e807e95563a2b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}