{"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/dsanet-dynamic-segment-aggregation-network","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","arxiv_id":"2105.12085","date":"2021-05-25","proceeding":null,"authors":["Wenhao Wu","Yuxiang Zhao","Yanwu Xu","Xiao Tan","Dongliang He","Zhikang Zou","Jin Ye","YingYing Li","Mingde Yao","ZiChao Dong","Yifeng Shi"],"abstract":"Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolutional operation to aggregate long-range temporal information among adjacent snippets adaptively. The DSA module is an efficient plug-and-play module and can be combined with the off-the-shelf clip-based models (i.e., TSM, I3D) to perform powerful long-range modeling with minimal overhead. The final video architecture, coined as DSANet. We conduct extensive experiments on several video recognition benchmarks (i.e., Mini-Kinetics-200, Kinetics-400, Something-Something V1 and ActivityNet) to show its superiority. Our proposed DSA module is shown to benefit various video recognition models significantly. For example, equipped with DSA modules, the top-1 accuracy of I3D ResNet-50 is improved from 74.9% to 78.2% on Kinetics-400. Codes are available at https://github.com/whwu95/DSANet.","url_abs":"https://arxiv.org/abs/2105.12085v3","url_pdf":"https://arxiv.org/pdf/2105.12085v3.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":"dsanet-dynamic-segment-aggregation-network","repo_url":"https://github.com/whwu95/DSANet","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":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-activitynet","task":"Action Recognition","dataset":"ActivityNet","model":"DSANet (w/ 3D ResNet50)","rank_in_archive_order":6,"of":16,"metrics":{"mAP":"90.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.12085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12085"}},"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/whwu95/DSANet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"official":{"samples":13,"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":"2a69c55d04d13a71","entry":"auto_fp16","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/fp16/decorators.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/fp16/decorators.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":"2a69c55d04d13a71"}},{"code_sha256_prefix":"67976edf323e2f17","entry":"build","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/models/builder.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/models/builder.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":"67976edf323e2f17"}},{"code_sha256_prefix":"7b91d5069635a376","entry":"cast_tensor_type","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/fp16/utils.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/fp16/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":"7b91d5069635a376"}},{"code_sha256_prefix":"1082ce7b7af2c3f7","entry":"collate","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/parallel/collate.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/parallel/collate.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":"1082ce7b7af2c3f7"}},{"code_sha256_prefix":"f739d3fb27d6f608","entry":"confusion_matrix","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/evaluation/accuracy.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/evaluation/accuracy.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":"f739d3fb27d6f608"}},{"code_sha256_prefix":"b99f8dd443d13369","entry":"force_fp32","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/fp16/decorators.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/fp16/decorators.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":"b99f8dd443d13369"}},{"code_sha256_prefix":"72b89f53f5854825","entry":"get_input_device","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/parallel/_functions.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/parallel/_functions.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":"72b89f53f5854825"}},{"code_sha256_prefix":"6a0d65723b2675dc","entry":"master_only","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/dist_utils.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/dist_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":"6a0d65723b2675dc"}},{"code_sha256_prefix":"0ebabe504dafca4b","entry":"mean_class_accuracy","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/evaluation/accuracy.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/evaluation/accuracy.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":"0ebabe504dafca4b"}},{"code_sha256_prefix":"e059fcc920f08632","entry":"patch_forward_method","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/fp16/hooks.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/fp16/hooks.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":"e059fcc920f08632"}},{"code_sha256_prefix":"f0c7f23268d50c1b","entry":"patch_norm_fp32","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/fp16/hooks.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/fp16/hooks.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":"f0c7f23268d50c1b"}},{"code_sha256_prefix":"aa73f0787179b863","entry":"scatter","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/parallel/_functions.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/parallel/_functions.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":"aa73f0787179b863"}},{"code_sha256_prefix":"622de14b270a7195","entry":"softmax","repo":"whwu95/DSANet","repo_kind":"official","path":"codes/core/evaluation/accuracy.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/evaluation/accuracy.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":"622de14b270a7195"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}