{"url":"/task/image-cropping","name":"Image Cropping","slug":"image-cropping","description_markdown":"**Image Cropping** is a common photo manipulation process, which improves the overall composition by removing unwanted regions. Image Cropping is widely used in photographic, film processing, graphic design, and printing businesses.\n\n\n<span class=\"description-source\">Source: [Listwise View Ranking for Image Cropping ](https://arxiv.org/abs/1905.05352)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":83,"papers_with_code":39,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-cropping-on-flms","slug":"image-cropping-on-flms","dataset":"FLMS","dataset_url":null,"rows_in_archive":1,"metrics":["BDE","IoU"],"first_row_in_archive_order":{"model":"CACNet","paper_title":"Composing Photos Like a Photographer","paper_url":"/paper/composing-photos-like-a-photographer","paper_date":"2021-06-19","arxiv_id":null,"code_links":[{"title":"bo-zhang-cs/CACNet-Pytorch","url":"https://github.com/bo-zhang-cs/CACNet-Pytorch"}],"syntology":null}}],"datasets":[{"url":"/dataset/aadb","name":"AADB","full_name":"","num_papers_in_archive":44},{"url":"/dataset/flickr-cropping-dataset","name":"Flickr Cropping Dataset","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/cuhk-image-cropping","name":"CUHK Image Cropping","full_name":"CUHK Image Cropping","num_papers_in_archive":3},{"url":"/dataset/gnmc","name":"GNMC","full_name":"Gracenote Multi-Crop Dataset","num_papers_in_archive":0}],"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":39,"tagged_in_all":83,"items":[{"url":"/paper/kornia-an-open-source-differentiable-computer","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2019-10-05","arxiv_id":"1910.02190","repositories_listed":5,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/see-better-before-looking-closer-weakly","title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","date":"2019-01-26","arxiv_id":"1901.09891","repositories_listed":4,"syntology":null},{"url":"/paper/a2-rl-aesthetics-aware-reinforcement-learning","title":"A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping","date":"2017-09-14","arxiv_id":"1709.04595","repositories_listed":3,"syntology":null},{"url":"/paper/fit-flexible-vision-transformer-for-diffusion","title":"FiT: Flexible Vision Transformer for Diffusion Model","date":"2024-02-19","arxiv_id":"2402.12376","repositories_listed":2,"syntology":{"n":17,"n_ran":15,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/a-framework-for-real-time-object-detection","title":"Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy","date":"2023-03-16","arxiv_id":"2303.09190","repositories_listed":2,"syntology":null},{"url":"/paper/deep-pcb-to-coco-convertor","title":"Deep PCB To COCO Convertor","date":"2022-05-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/image-cropping-on-twitter-fairness-metrics","title":"Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency","date":"2021-05-18","arxiv_id":"2105.08667","repositories_listed":2,"syntology":null},{"url":"/paper/an-end-to-end-neural-network-for-image","title":"An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos","date":"2019-07-02","arxiv_id":"1907.01432","repositories_listed":2,"syntology":null},{"url":"/paper/ace-anatomically-consistent-embeddings-in","title":"ACE: Anatomically Consistent Embeddings in Composition and Decomposition","date":"2025-01-17","arxiv_id":"2501.10131","repositories_listed":1,"syntology":null},{"url":"/paper/fitv2-scalable-and-improved-flexible-vision","title":"FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model","date":"2024-10-17","arxiv_id":"2410.13925","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01355","title":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","date":"2024-08-02","arxiv_id":"2408.01355","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-dependence-of-perception","title":"Understanding the Dependence of Perception Model Competency on Regions in an Image","date":"2024-07-15","arxiv_id":"2407.10543","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-semantic-collaborative-cropping-for","title":"Spatial-Semantic Collaborative Cropping for User Generated Content","date":"2024-01-16","arxiv_id":"2401.08086","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-image-borders-learning-feature","title":"Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition","date":"2023-09-21","arxiv_id":"2309.12042","repositories_listed":1,"syntology":null},{"url":"/paper/tame-a-wild-camera-in-the-wild-monocular-1","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","date":"2023-06-19","arxiv_id":"2306.10988","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/mixpro-data-augmentation-with-maskmix-and","title":"MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer","date":"2023-04-24","arxiv_id":"2304.12043","repositories_listed":1,"syntology":{"n":18,"n_ran":10,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/human-centric-image-cropping-with-partition","title":"Human-centric Image Cropping with Partition-aware and Content-preserving Features","date":"2022-07-21","arxiv_id":"2207.10269","repositories_listed":1,"syntology":null},{"url":"/paper/augstatic-a-light-weight-image-augmentation","title":"AugStatic - A Light-Weight Image Augmentation Library","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/augmented-balanced-image-dataset-generator","title":"Augmented Balanced Image Dataset Generator Using AugStatic Library","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/from-image-to-imuge-immunized-image","title":"From Image to Imuge: Immunized Image Generation","date":"2021-10-27","arxiv_id":"2110.14196","repositories_listed":1,"syntology":null},{"url":"/paper/looking-outside-the-window-wider-context","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","date":"2021-06-29","arxiv_id":"2106.15754","repositories_listed":1,"syntology":null},{"url":"/paper/composing-photos-like-a-photographer","title":"Composing Photos Like a Photographer","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/salient-object-ranking-with-position","title":"Salient Object Ranking with Position-Preserved Attention","date":"2021-06-09","arxiv_id":"2106.05047","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/dissecting-image-crops","title":"Dissecting Image Crops","date":"2020-11-24","arxiv_id":"2011.11831","repositories_listed":1,"syntology":null},{"url":"/paper/towards-resolving-the-challenge-of-long-tail","title":"Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection","date":"2020-11-07","arxiv_id":"2011.03822","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-kornia-an-open-source","title":"A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2020-09-21","arxiv_id":"2009.10521","repositories_listed":1,"syntology":null},{"url":"/paper/ida-improved-data-augmentation-applied-to","title":"IDA: Improved Data Augmentation Applied to Salient Object Detection","date":"2020-09-18","arxiv_id":"2009.08845","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-learn-cropping-models-for","title":"Learning to Learn Cropping Models for Different Aspect Ratio Requirements","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/density-map-guided-object-detection-in-aerial","title":"Density Map Guided Object Detection in Aerial Images","date":"2020-04-12","arxiv_id":"2004.05520","repositories_listed":1,"syntology":null},{"url":"/paper/anda-a-novel-data-augmentation-technique","title":"ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection","date":"2019-10-03","arxiv_id":"1910.01256","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}