{"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/tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","arxiv_id":"2001.09099","date":"2020-01-24","proceeding":"ECCV 2020 8","authors":["Jie Lei","Licheng Yu","Tamara L. Berg","Mohit Bansal"],"abstract":"We introduce TV show Retrieval (TVR), a new multimodal retrieval dataset. TVR requires systems to understand both videos and their associated subtitle (dialogue) texts, making it more realistic. The dataset contains 109K queries collected on 21.8K videos from 6 TV shows of diverse genres, where each query is associated with a tight temporal window. The queries are also labeled with query types that indicate whether each of them is more related to video or subtitle or both, allowing for in-depth analysis of the dataset and the methods that built on top of it. Strict qualification and post-annotation verification tests are applied to ensure the quality of the collected data. Further, we present several baselines and a novel Cross-modal Moment Localization (XML ) network for multimodal moment retrieval tasks. The proposed XML model uses a late fusion design with a novel Convolutional Start-End detector (ConvSE), surpassing baselines by a large margin and with better efficiency, providing a strong starting point for future work. We have also collected additional descriptions for each annotated moment in TVR to form a new multimodal captioning dataset with 262K captions, named TV show Caption (TVC). Both datasets are publicly available. TVR: https://tvr.cs.unc.edu, TVC: https://tvr.cs.unc.edu/tvc.html.","url_abs":"https://arxiv.org/abs/2001.09099v2","url_pdf":"https://arxiv.org/pdf/2001.09099v2.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":"tvr-a-large-scale-dataset-for-video-subtitle","repo_url":"https://github.com/jayleicn/TVCaption","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tvr-a-large-scale-dataset-for-video-subtitle","repo_url":"https://github.com/jayleicn/TVRetrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-corpus-moment-retrieval","task_name":"Video Corpus Moment Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"tvc","name":"TVC","full_name":"TV show Captions"},{"slug":"tvr","name":"TVR","full_name":"TV show Retrieval"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-tvr","task":"Video Retrieval","dataset":"TVR","model":"XML (Lei et al., 2020)","rank_in_archive_order":2,"of":2,"metrics":{"R@10":"8.93"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2001.09099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.09099"}},"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/jayleicn/TVCaption","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jayleicn/TVRetrieval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_honours":2,"ran_draft_wrong":3,"unverified":11},"by_repo_kind":{"official":{"samples":19,"ran":8,"repositories":2}},"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":"ea2ba2c075c6b18b","entry":"compute_temporal_iou","repo":"jayleicn/TVRetrieval","repo_kind":"official","path":"utils/temporal_nms.py","file_url":"https://github.com/jayleicn/TVRetrieval/blob/HEAD/utils/temporal_nms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea2ba2c075c6b18b"}},{"code_sha256_prefix":"cef10190a6f8f7e9","entry":"flat_list_of_lists","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/local_utils.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/local_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cef10190a6f8f7e9"}},{"code_sha256_prefix":"69e3a274f98c15af","entry":"gelu","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/transformer/model.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/model.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69e3a274f98c15af"}},{"code_sha256_prefix":"2d946250dd2f5a4f","entry":"load_json","repo":"jayleicn/TVCaption","repo_kind":"official","path":"utils/basic_utils.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/utils/basic_utils.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":"2d946250dd2f5a4f"}},{"code_sha256_prefix":"53d425eb1278ddda","entry":"load_json","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/local_utils.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/local_utils.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":"53d425eb1278ddda"}},{"code_sha256_prefix":"f1d1cccccf038785","entry":"load_jsonl","repo":"jayleicn/TVCaption","repo_kind":"official","path":"standalone_eval/evaluate.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/standalone_eval/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1d1cccccf038785"}},{"code_sha256_prefix":"570ad34bd1af44a8","entry":"load_pickle","repo":"jayleicn/TVCaption","repo_kind":"official","path":"utils/basic_utils.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/utils/basic_utils.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":"570ad34bd1af44a8"}},{"code_sha256_prefix":"1c17153fb5488283","entry":"mask_logits","repo":"jayleicn/TVRetrieval","repo_kind":"official","path":"baselines/crossmodal_moment_localization/model_xml.py","file_url":"https://github.com/jayleicn/TVRetrieval/blob/HEAD/baselines/crossmodal_moment_localization/model_xml.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c17153fb5488283"}},{"code_sha256_prefix":"ff6297422c0e1b92","entry":"caption_collate","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/transformer/tvc_dataset.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/tvc_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":"ff6297422c0e1b92"}},{"code_sha256_prefix":"edb929dece68582e","entry":"count_parameters","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/local_utils.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/local_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":"edb929dece68582e"}},{"code_sha256_prefix":"07940cb25a48bfc4","entry":"length_penalty_builder","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/transformer/decode_strategy.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/decode_strategy.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":"07940cb25a48bfc4"}},{"code_sha256_prefix":"a81aaf990607f138","entry":"load_glove","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/build_vocab.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/build_vocab.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":"a81aaf990607f138"}},{"code_sha256_prefix":"286f821a3988fcbe","entry":"pool_across_time","repo":"jayleicn/TVRetrieval","repo_kind":"official","path":"utils/model_utils.py","file_url":"https://github.com/jayleicn/TVRetrieval/blob/HEAD/utils/model_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":"286f821a3988fcbe"}},{"code_sha256_prefix":"bff9917618d44658","entry":"prepare_batch_inputs","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/transformer/tvc_dataset.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/tvc_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":"bff9917618d44658"}},{"code_sha256_prefix":"a45f62024eb3d2c5","entry":"remove_nonascii","repo":"jayleicn/TVCaption","repo_kind":"official","path":"standalone_eval/evaluate.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/standalone_eval/evaluate.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":"a45f62024eb3d2c5"}},{"code_sha256_prefix":"712ae5d2ea349b4d","entry":"sort_res","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/translate.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/translate.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":"712ae5d2ea349b4d"}},{"code_sha256_prefix":"c1ba877d826f25af","entry":"step_collate","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/transformer/tvc_dataset.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/tvc_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":"c1ba877d826f25af"}},{"code_sha256_prefix":"d235ed6d33e43a98","entry":"temporal_non_maximum_suppression","repo":"jayleicn/TVRetrieval","repo_kind":"official","path":"utils/temporal_nms.py","file_url":"https://github.com/jayleicn/TVRetrieval/blob/HEAD/utils/temporal_nms.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":"d235ed6d33e43a98"}},{"code_sha256_prefix":"69b8b31e44791260","entry":"tile","repo":"jayleicn/TVCaption","repo_kind":"official","path":"baselines/multimodal_transformer/translator.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/translator.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":"69b8b31e44791260"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}