{"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/video-representation-learning-by-dense","title":"Video Representation Learning by Dense Predictive Coding","arxiv_id":"1909.04656","date":"2019-09-10","proceeding":null,"authors":["Tengda Han","Weidi Xie","Andrew Zisserman"],"abstract":"The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.","url_abs":"https://arxiv.org/abs/1909.04656v3","url_pdf":"https://arxiv.org/pdf/1909.04656v3.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":"video-representation-learning-by-dense","repo_url":"https://github.com/TengdaHan/DPC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-action-recognition","task_name":"Self-Supervised Action Recognition"},{"task_slug":"self-supervised-action-recognition-linear","task_name":"Self-Supervised Action Recognition Linear"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"DPC (Modified 3D Resnet-34)","rank_in_archive_order":39,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"Kinetics400","Top-1 Accuracy":"35.7"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"DPC (Modified 3D ResNet-18)","rank_in_archive_order":40,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"Kinetics400","Top-1 Accuracy":"34.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"DPC (Modified 3D Resnet-34)","rank_in_archive_order":33,"of":53,"metrics":{"3-fold Accuracy":"75.7","Frozen":"false","Pre-Training Dataset":"Kinetics400"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"DPC (3D ResNet-18)","rank_in_archive_order":39,"of":53,"metrics":{"3-fold Accuracy":"68.2","Frozen":"false","Pre-Training Dataset":"Kinetics400"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"DPC (3D ResNet-18, Split 1)","rank_in_archive_order":46,"of":53,"metrics":{"3-fold Accuracy":"60.6","Frozen":"false","Pre-Training Dataset":"UCF101"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.04656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04656"}},"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/DPC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"official":{"samples":11,"ran":1,"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":"43c0211ff8dbca5f","entry":"downsample_basic_block","repo":"TengdaHan/DPC","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/backbone/resnet_2d3d.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43c0211ff8dbca5f"}},{"code_sha256_prefix":"d09bfd0a1223d58a","entry":"calc_accuracy","repo":"TengdaHan/DPC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/utils/utils.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":"d09bfd0a1223d58a"}},{"code_sha256_prefix":"029de83819712727","entry":"calc_accuracy_binary","repo":"TengdaHan/DPC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/utils/utils.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":"029de83819712727"}},{"code_sha256_prefix":"f5106fc277f13ca4","entry":"calc_topk_accuracy","repo":"TengdaHan/DPC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/utils/utils.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":"f5106fc277f13ca4"}},{"code_sha256_prefix":"798674d07b9de57d","entry":"check_exists","repo":"TengdaHan/DPC","repo_kind":"official","path":"process_data/src/write_csv.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/process_data/src/write_csv.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":"798674d07b9de57d"}},{"code_sha256_prefix":"931634839b156bde","entry":"conv1x3x3","repo":"TengdaHan/DPC","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/backbone/resnet_2d3d.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":"931634839b156bde"}},{"code_sha256_prefix":"87ddd63faa8e7182","entry":"conv3x3x3","repo":"TengdaHan/DPC","repo_kind":"official","path":"backbone/resnet_2d3d.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/backbone/resnet_2d3d.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":"87ddd63faa8e7182"}},{"code_sha256_prefix":"488a3f6281af3479","entry":"get_split","repo":"TengdaHan/DPC","repo_kind":"official","path":"process_data/src/write_csv.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/process_data/src/write_csv.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":"488a3f6281af3479"}},{"code_sha256_prefix":"205d65f49e6394e0","entry":"pil_loader","repo":"TengdaHan/DPC","repo_kind":"official","path":"dpc/dataset_3d.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/dpc/dataset_3d.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":"205d65f49e6394e0"}},{"code_sha256_prefix":"e164a1c87d234774","entry":"resize_dim","repo":"TengdaHan/DPC","repo_kind":"official","path":"process_data/src/extract_frame.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/process_data/src/extract_frame.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":"e164a1c87d234774"}},{"code_sha256_prefix":"4be1c52b2de00852","entry":"select_resnet","repo":"TengdaHan/DPC","repo_kind":"official","path":"backbone/select_backbone.py","file_url":"https://github.com/TengdaHan/DPC/blob/HEAD/backbone/select_backbone.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":"4be1c52b2de00852"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}