{"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/transnet-v2-an-effective-deep-network","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","arxiv_id":"2008.04838","date":"2020-08-11","proceeding":null,"authors":["Tomáš Souček","Jakub Lokoč"],"abstract":"Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachable ideal. In this paper, we share the current version of our deep network TransNet V2 that reaches state-of-the-art performance on respected benchmarks. A trained instance of the model is provided so it can be instantly utilized by the community for a highly efficient analysis of large video archives. Furthermore, the network architecture, as well as our experience with the training process, are detailed, including simple code snippets for convenient usage of the proposed model and visualization of results.","url_abs":"https://arxiv.org/abs/2008.04838v1","url_pdf":"https://arxiv.org/pdf/2008.04838v1.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":"transnet-v2-an-effective-deep-network","repo_url":"https://github.com/soCzech/TransNetV2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transnet-v2-an-effective-deep-network","repo_url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transnet-v2-an-effective-deep-network","repo_url":"https://github.com/soCzech/MasterThesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"transnet-v2-an-effective-deep-network","repo_url":"https://github.com/wqliu657/TransNetV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"camera-shot-boundary-detection","task_name":"Camera shot boundary detection"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camera-shot-boundary-detection-on-clipshots","task":"Camera shot boundary detection","dataset":"ClipShots","model":"TransNet V2","rank_in_archive_order":2,"of":4,"metrics":{"F1 score":"77.9"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2008.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.04838"}},"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/soCzech/MasterThesis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soCzech/TransNetV2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wqliu657/TransNetV2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":12,"ran":0,"repositories":1},"listed":{"samples":3,"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":"7af38278c93d587f","entry":"check_and_fix_dicts","repo":"soCzech/TransNetV2","repo_kind":"official","path":"inference-pytorch/convert_weights.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/inference-pytorch/convert_weights.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":"7af38278c93d587f"}},{"code_sha256_prefix":"cec13b69d85253c3","entry":"compute_normalization_fixed_point","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/bi_tempered_loss.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/bi_tempered_loss.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":"cec13b69d85253c3"}},{"code_sha256_prefix":"8b38bd5a0be9bce7","entry":"evaluate_scenes","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/metrics_utils.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/metrics_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":"8b38bd5a0be9bce7"}},{"code_sha256_prefix":"a6d36281c438e25b","entry":"exp_t","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/bi_tempered_loss.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/bi_tempered_loss.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":"a6d36281c438e25b"}},{"code_sha256_prefix":"7d243f22f59049e3","entry":"get_batches","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/evaluate.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/evaluate.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":"7d243f22f59049e3"}},{"code_sha256_prefix":"a574b706c69a2e4a","entry":"get_scenes_from_transition_frames","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/consolidate_datasets.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/consolidate_datasets.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":"a574b706c69a2e4a"}},{"code_sha256_prefix":"c19395bc49d7798c","entry":"graph","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/metrics_utils.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/metrics_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":"c19395bc49d7798c"}},{"code_sha256_prefix":"e047237f9926614c","entry":"log_t","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/bi_tempered_loss.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/bi_tempered_loss.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":"e047237f9926614c"}},{"code_sha256_prefix":"e6c126c38a88b3c8","entry":"main_process","repo":"shallwe999/TransNetV2-SBD-Visualize","repo_kind":"listed","path":"transnetv2.py","file_url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize/blob/HEAD/transnetv2.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":"e6c126c38a88b3c8"}},{"code_sha256_prefix":"3da0df168740c1aa","entry":"predictions_to_scenes","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/metrics_utils.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/metrics_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":"3da0df168740c1aa"}},{"code_sha256_prefix":"fa843917bfca3cfb","entry":"read_predictions","repo":"shallwe999/TransNetV2-SBD-Visualize","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize/blob/HEAD/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":"fa843917bfca3cfb"}},{"code_sha256_prefix":"732def07b44046eb","entry":"read_scenes","repo":"shallwe999/TransNetV2-SBD-Visualize","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize/blob/HEAD/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":"732def07b44046eb"}},{"code_sha256_prefix":"61c9ba481effd824","entry":"remap_name","repo":"soCzech/TransNetV2","repo_kind":"official","path":"inference-pytorch/convert_weights.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/inference-pytorch/convert_weights.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":"61c9ba481effd824"}},{"code_sha256_prefix":"c35a46af5bf2323c","entry":"remap_tensor","repo":"soCzech/TransNetV2","repo_kind":"official","path":"inference-pytorch/convert_weights.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/inference-pytorch/convert_weights.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":"c35a46af5bf2323c"}},{"code_sha256_prefix":"4f1f9a4527adf939","entry":"scenes2zero_one_representation","repo":"soCzech/TransNetV2","repo_kind":"official","path":"training/create_dataset.py","file_url":"https://github.com/soCzech/TransNetV2/blob/HEAD/training/create_dataset.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":"4f1f9a4527adf939"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}