{"url":"/dataset/cc3m-tagmask","name":"CC3M-TagMask","full_name":null,"description_markdown":"The dataset offers tag and mask annotations for image-text pairs from the CC3M validation set. Tag annotations denote words that aptly describe the relationship between the image and the corresponding text. These annotations provide valuable insights into the semantic connection between each pair's visual and textual elements.","description_withheld":null,"homepage":"https://github.com/shjo-april/TTD","introduced_date":"2024-03-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/ttd-text-tag-self-distillation-enhancing","title":"TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias","first_author":"Sanghyun Jo","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Segmentation","url":"/task/segmentation","datasets_with_task":"/datasets/task/segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CC3M-TagMask"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-text-classification-on-cc3m","task":"Multi-Label Text Classification","dataset_variant":"CC3M-TagMask","rows":6,"metrics":["Precision","Recall","F1","Accuracy","mAP"],"first_row_in_archive_order":{"model":"TTD (w/ fine-tuning)","paper":"/paper/ttd-text-tag-self-distillation-enhancing","metrics":{"Accuracy":"88.6","F1":"82.8","Precision":"88.3","Recall":"78.0","mAP":"93.7"},"code_links":[{"title":"shjo-april/TTD","url":"https://github.com/shjo-april/TTD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-cc3m-tagmask","task":"Semantic Segmentation","dataset_variant":"CC3M-TagMask","rows":4,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"TTD (TCL)","paper":"/paper/ttd-text-tag-self-distillation-enhancing","metrics":{"mIoU":"65.5"},"code_links":[{"title":"shjo-april/TTD","url":"https://github.com/shjo-april/TTD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ttd-text-tag-self-distillation-enhancing","title":"TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias","date":"2024-03-30","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/qwen-technical-report","title":"Qwen Technical Report","date":"2023-09-28","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-generate-text-grounded-mask-for","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","date":"2022-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/denseclip-extract-free-dense-labels-from-clip","title":"Extract Free Dense Labels from CLIP","date":"2021-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nltk-the-natural-language-toolkit","title":"NLTK: The Natural Language Toolkit","date":"2002-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":13,"samples_ran":4,"samples_unverified":9,"pointer_only_for_licence":1,"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."}