{"url":"/task/zero-shot-image-retrieval","name":"Zero-shot Image Retrieval","slug":"zero-shot-image-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":17,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/imagenet-r","name":"ImageNet-R","full_name":"ImageNet-Rendition","num_papers_in_archive":481},{"url":"/dataset/coco-cn","name":"COCO-CN","full_name":"","num_papers_in_archive":21},{"url":"/dataset/quilt-1m","name":"QUILT-1M","full_name":"","num_papers_in_archive":17},{"url":"/dataset/flickr30k-cna","name":"Flickr30k-CNA","full_name":"Flickr30k-Chinese All","num_papers_in_archive":7},{"url":"/dataset/xtd10","name":"XTD10","full_name":"","num_papers_in_archive":4},{"url":"/dataset/simco-comco","name":"simco-comco","full_name":"","num_papers_in_archive":1},{"url":"/dataset/webli","name":"WebLI","full_name":"Web Language Image","num_papers_in_archive":1},{"url":"/dataset/x-transferbench","name":"X-TransferBench","full_name":"X-TransferBench","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":17,"of":17,"tagged_in_all":29,"items":[{"url":"/paper/flava-a-foundational-language-and-vision","title":"FLAVA: A Foundational Language And Vision Alignment Model","date":"2021-12-08","arxiv_id":"2112.04482","repositories_listed":4,"syntology":null},{"url":"/paper/internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","repositories_listed":2,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/revisiting-clip-efficient-alignment-of-3d-mri","title":"Revisiting CLIP: Efficient Alignment of 3D MRI and Tabular Data using Domain-Specific Foundation Models","date":"2025-01-23","arxiv_id":"2501.14051","repositories_listed":1,"syntology":null},{"url":"/paper/boldsymbol-m-2-encoder-advancing-bilingual","title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","date":"2024-01-29","arxiv_id":"2401.15896","repositories_listed":1,"syntology":null},{"url":"/paper/context-i2w-mapping-images-to-context","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","date":"2023-09-28","arxiv_id":"2309.16137","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/factual-a-benchmark-for-faithful-and","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","date":"2023-05-27","arxiv_id":"2305.17497","repositories_listed":1,"syntology":null},{"url":"/paper/pic2word-mapping-pictures-to-words-for-zero","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","date":"2023-02-06","arxiv_id":"2302.03084","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/chinese-clip-contrastive-vision-language","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","date":"2022-11-02","arxiv_id":"2211.01335","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/ernie-vil-2-0-multi-view-contrastive-learning","title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","date":"2022-09-30","arxiv_id":"2209.15270","repositories_listed":1,"syntology":null},{"url":"/paper/feta-towards-specializing-foundation-models","title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","date":"2022-09-08","arxiv_id":"2209.03648","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-and-multilingual-clip","title":"Cross-lingual and Multilingual CLIP","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","arxiv_id":"2205.03860","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","date":"2022-02-14","arxiv_id":"2202.06767","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/visual-representation-learning-with-self","title":"Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime","date":"2022-01-22","arxiv_id":"2201.08951","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-the-role-of-data-attention-and","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","date":"2021-01-31","arxiv_id":"2102.00529","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}