{"url":"/task/text-matching","name":"Text Matching","slug":"text-matching","description_markdown":"Matching a target text to a source text based on their meaning.","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":364,"papers_with_code":161,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":7,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/medicat","name":"MedICaT","full_name":null,"num_papers_in_archive":28},{"url":"/dataset/snopes","name":"Snopes","full_name":"","num_papers_in_archive":22},{"url":"/dataset/politifact","name":"PolitiFact","full_name":"","num_papers_in_archive":20},{"url":"/dataset/delemon","name":"DuLeMon","full_name":"Baidu Long-term Memory Conversation","num_papers_in_archive":14},{"url":"/dataset/covid-19-twitter-chatter-dataset","name":"COVID-19 Twitter Chatter Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/composed-quora","name":"Composed Quora","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/psm","name":"PSM","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":30,"of":161,"tagged_in_all":364,"items":[{"url":"/paper/attngan-fine-grained-text-to-image-generation","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","date":"2017-11-28","arxiv_id":"1711.10485","repositories_listed":20,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/text-matching-as-image-recognition","title":"Text Matching as Image Recognition","date":"2016-02-20","arxiv_id":"1602.06359","repositories_listed":7,"syntology":null},{"url":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":7,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/colpali-efficient-document-retrieval-with","title":"ColPali: Efficient Document Retrieval with Vision Language Models","date":"2024-06-27","arxiv_id":"2407.01449","repositories_listed":5,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fine-grained-video-text-retrieval-with","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","date":"2020-03-01","arxiv_id":"2003.00392","repositories_listed":4,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/structure-clip-enhance-multi-modal-language","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","date":"2023-05-06","arxiv_id":"2305.06152","repositories_listed":3,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/df-gan-deep-fusion-generative-adversarial","title":"DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis","date":"2020-08-13","arxiv_id":"2008.05865","repositories_listed":3,"syntology":null},{"url":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/a-systematic-survey-of-prompt-engineering-on","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","date":"2023-07-24","arxiv_id":"2307.12980","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","arxiv_id":"2211.13594","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/dissecting-deep-metric-learning-losses-for","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","date":"2022-10-21","arxiv_id":"2210.13188","repositories_listed":2,"syntology":null},{"url":"/paper/eccv-caption-correcting-false-negatives-by","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","date":"2022-04-07","arxiv_id":"2204.03359","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/identifying-machine-paraphrased-plagiarism","title":"Identifying Machine-Paraphrased Plagiarism","date":"2021-03-22","arxiv_id":"2103.11909","repositories_listed":2,"syntology":null},{"url":"/paper/universal-weighting-metric-learning-for-cross-1","title":"Universal Weighting Metric Learning for Cross-Modal Matching","date":"2020-10-07","arxiv_id":"2010.03403","repositories_listed":2,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/extractive-summarization-as-text-matching","title":"Extractive Summarization as Text Matching","date":"2020-04-19","arxiv_id":"2004.08795","repositories_listed":2,"syntology":null},{"url":"/paper/visual-semantic-reasoning-for-image-text","title":"Visual Semantic Reasoning for Image-Text Matching","date":"2019-09-06","arxiv_id":"1909.02701","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/matching-images-and-text-with-multi-modal","title":"Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking","date":"2019-08-12","arxiv_id":"1908.04011","repositories_listed":2,"syntology":null},{"url":"/paper/dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","date":"2016-11-02","arxiv_id":"1611.00471","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-medical-vision-language-alignment","title":"Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models","date":"2025-06-10","arxiv_id":"2506.08990","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-information-capacity-between-vision","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","date":"2025-03-19","arxiv_id":"2503.14953","repositories_listed":1,"syntology":null},{"url":"/paper/clip-is-strong-enough-to-fight-back-test-time","title":"CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP","date":"2025-03-05","arxiv_id":"2503.03613","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/iterprime-zero-shot-referring-image","title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","date":"2025-03-02","arxiv_id":"2503.00936","repositories_listed":1,"syntology":null},{"url":"/paper/clip-under-the-microscope-a-fine-grained","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","date":"2025-02-27","arxiv_id":"2502.19842","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/filo-zero-few-shot-anomaly-detection-by-fused","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","date":"2025-01-17","arxiv_id":"2501.10067","repositories_listed":1,"syntology":null},{"url":"/paper/vulnerability-of-text-matching-in-ml-ai","title":"Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments to Collusions","date":"2024-12-09","arxiv_id":"2412.06606","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/tdsm-triplet-diffusion-for-skeleton-text","title":"TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition","date":"2024-11-16","arxiv_id":"2411.10745","repositories_listed":1,"syntology":null},{"url":"/paper/disco-a-hierarchical-disentangled-cognitive","title":"DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job Recommendation","date":"2024-10-10","arxiv_id":"2410.07671","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":7}}],"syntology_records":17,"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"}}