{"url":"/task/image-sentence-alignment","name":"image-sentence alignment","slug":"image-sentence-alignment","description_markdown":"Predict the alignment (score) between an image and a sentence.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":2,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-sentence-alignment-on-valse","slug":"image-sentence-alignment-on-valse","dataset":"VALSE","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["average pairwise accuracy","Average Accuracy"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-actant-swap","slug":"image-sentence-alignment-on-valse-actant-swap","dataset":"VALSE actant swap","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"GPT2","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-action","slug":"image-sentence-alignment-on-valse-action","dataset":"VALSE action replacement","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-coreference","slug":"image-sentence-alignment-on-valse-coreference","dataset":"VALSE coreference standard","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-coreference-1","slug":"image-sentence-alignment-on-valse-coreference-1","dataset":"VALSE coreference clean","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting","slug":"image-sentence-alignment-on-valse-counting","dataset":"VALSE counting balanced","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting-1","slug":"image-sentence-alignment-on-valse-counting-1","dataset":"VALSE counting small numbers","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting-2","slug":"image-sentence-alignment-on-valse-counting-2","dataset":"VALSE counting adversarial","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-existence","slug":"image-sentence-alignment-on-valse-existence","dataset":"VALSE existence","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-foil-it","slug":"image-sentence-alignment-on-valse-foil-it","dataset":"VALSE foil-it (noun phrases)","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-plurality","slug":"image-sentence-alignment-on-valse-plurality","dataset":"VALSE plurality","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-sentence-alignment-on-valse-spatial","slug":"image-sentence-alignment-on-valse-spatial","dataset":"VALSE spatial relations","dataset_url":"/dataset/valse","rows_in_archive":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"GPT1","paper_title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","paper_url":"/paper/valse-a-task-independent-benchmark-for-vision-1","paper_date":"2021-12-14","arxiv_id":"2112.07566","code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/valse","name":"VALSE","full_name":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","num_papers_in_archive":26}],"subtasks":[],"parent_tasks":[{"url":"/task/multimodal-text-and-image-classification","name":"Multimodal Text and Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":3,"items":[{"url":"/paper/valse-a-task-independent-benchmark-for-vision-1","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","date":"2021-12-14","arxiv_id":"2112.07566","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/removing-word-level-spurious-alignment","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","date":"2021-04-28","arxiv_id":"2104.13872","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}