{"url":"/dataset/msvd-ctn","name":"MSVD-CTN","full_name":"MSVD Causal-Temporal Narrative","description_markdown":"# MSVD-CTN Dataset\r\n\r\nThis dataset contains CTN annotations for the MSVD-CTN benchmark dataset in JSON format. It has three files for the train, test, and validation splits. \r\nFor project details, visit https://narrativebridge.github.io/.\r\n\r\n## Dataset Structure\r\n\r\nEach JSON file contains a dictionary where the keys are the video IDs and the values are the corresponding Causal-Temporal Narrative (CTN) captions. The CTN captions are represented as a dictionary with two keys: \"Cause\" and \"Effect\", containing the cause and effect statements, respectively.\r\n\r\nExample:\r\n\r\n```json\r\n{\r\n  \"video_id_1\": {\r\n    \"Cause\": \"a person performed an action\",\r\n    \"Effect\": \"a specific outcome occurred\"\r\n  },\r\n  \"video_id_2\": {\r\n    \"Cause\": \"another cause statement\",\r\n    \"Effect\": \"another effect statement\"\r\n  }\r\n}\r\n```\r\n\r\n## Loading the Datasets\r\n\r\nTo load the datasets, use a JSON parsing library in your preferred programming language. For example, in Python, you can use the `json` module:\r\n\r\n```python\r\nimport json\r\n\r\nwith open(\"msvd_CTN_train.json\", \"r\") as f:\r\n    msvd_train_data = json.load(f)\r\n\r\n# Access the CTN captions\r\nfor video_id, ctn_caption in msvd_train_data.items():\r\n    cause = ctn_caption[\"Cause\"]\r\n    effect = ctn_caption[\"Effect\"]\r\n    # Process the cause and effect statements as needed\r\n```\r\n## License\r\n\r\nThe MSVD-CTN benchmark dataset is licensed under the Creative Commons Attribution Non Commercial No Derivatives 4.0 International (CC BY-NC-ND 4.0) license.","description_withheld":null,"homepage":"https://narrativebridge.github.io/","introduced_date":"2024-06-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/narrativebridge-enhancing-video-captioning","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","first_author":"Asmar Nadeem","url":null},"license":{"name":"Creative Commons Attribution Non Commercial No Derivatives 4.0","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Video Captioning on MS","url":"/task/video-captioning-on-ms","datasets_with_task":"/datasets/task/video-captioning-on-ms"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MSVD-CTN"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-captioning-on-msvd-ctn","task":"Video Captioning","dataset_variant":"MSVD-CTN","rows":4,"metrics":["CIDEr","ROUGE-L","SPICE"],"first_row_in_archive_order":{"model":"CEN","paper":"/paper/narrativebridge-enhancing-video-captioning","metrics":{"CIDEr":"63.51","ROUGE-L":"31.46","SPICE":"19.25"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/narrativebridge-enhancing-video-captioning","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","date":"2024-06-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/git-towards-generalist-vision-transformer","title":"GiT: Towards Generalist Vision Transformer through Universal Language Interface","date":"2024-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sem-pos-grammatically-and-semantically","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","date":"2023-03-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-knowledge-for-video-captioning-with","title":"Action knowledge for video captioning with graph neural networks","date":"2023-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}