{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/coco/papers/4","list_of":"/dataset/coco","dataset":"COCO (Common Objects in Context)","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"order":"archive","order_definition":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":4,"pages_in_order":6,"rows_per_page":100,"rows":[301,400],"of":579,"counts":{"papers_with_a_benchmark_row":579,"with_a_code_link":504,"where_syntology_ran_a_sample":256,"not_listed_spam_title":0,"listed":579,"listed_where_code_ran":256,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":226,"every_run_a_failure_of_syntologys_instrument":30,"listed_with_a_run_with_no_instrument_failure":226,"listed_every_run_a_failure_of_syntologys_instrument":30,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/coco","prev":"/dataset/coco/papers/3","next":"/dataset/coco/papers/5","papers":[{"paper":"/paper/recursively-refined-r-cnn-instance","slug":"recursively-refined-r-cnn-instance","title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","date":"2021-04-03","arxiv_id":"2104.01329","rows_on_this_dataset":9,"code_links":1,"syntology":null},{"paper":"/paper/2103-15320","slug":"2103-15320","title":"TFPose: Direct Human Pose Estimation with Transformers","date":"2021-03-29","arxiv_id":"2103.15320","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/2103-15358","slug":"2103-15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","date":"2021-03-29","arxiv_id":"2103.15358","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["microsoft/vision-longformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2103-15358#ran","syntology_url":"https://syntology.ai/paper/2103.15358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15358"}}}},{"paper":"/paper/ota-optimal-transport-assignment-for-object","slug":"ota-optimal-transport-assignment-for-object","title":"OTA: Optimal Transport Assignment for Object Detection","date":"2021-03-26","arxiv_id":"2103.14259","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Megvii-BaseDetection/OTA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ota-optimal-transport-assignment-for-object#ran","syntology_url":"https://syntology.ai/paper/2103.14259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14259"}}}},{"paper":"/paper/swin-transformer-hierarchical-vision","slug":"swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","rows_on_this_dataset":8,"code_links":80,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":207,"samples_ran":123,"samples_constructed":45,"samples_ran_checked":82,"samples_ran_instrument_failed":41,"samples_unverified":84,"pointer_only_for_licence":45,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"paper":"/paper/usb-universal-scale-object-detection","slug":"usb-universal-scale-object-detection","title":"USB: Universal-Scale Object Detection Benchmark","date":"2021-03-25","arxiv_id":"2103.14027","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/deep-occlusion-aware-instance-segmentation","slug":"deep-occlusion-aware-instance-segmentation","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","date":"2021-03-23","arxiv_id":"2103.12340","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["lkeab/BCNet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-occlusion-aware-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12340"}}}},{"paper":"/paper/meta-detr-few-shot-object-detection-via","slug":"meta-detr-few-shot-object-detection-via","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","date":"2021-03-22","arxiv_id":"2103.11731","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ZhangGongjie/Meta-DETR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/meta-detr-few-shot-object-detection-via#ran","syntology_url":"https://syntology.ai/paper/2103.11731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11731"}}}},{"paper":"/paper/omnipose-a-multi-scale-framework-for-multi","slug":"omnipose-a-multi-scale-framework-for-multi","title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","date":"2021-03-18","arxiv_id":"2103.10180","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/you-only-look-one-level-feature","slug":"you-only-look-one-level-feature","title":"You Only Look One-level Feature","date":"2021-03-17","arxiv_id":"2103.09460","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/bbam-bounding-box-attribution-map-for-weakly","slug":"bbam-bounding-box-attribution-map-for-weakly","title":"BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation","date":"2021-03-16","arxiv_id":"2103.08907","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/probabilistic-two-stage-detection","slug":"probabilistic-two-stage-detection","title":"Probabilistic two-stage detection","date":"2021-03-12","arxiv_id":"2103.07461","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/fsce-few-shot-object-detection-via","slug":"fsce-few-shot-object-detection-via","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","date":"2021-03-10","arxiv_id":"2103.05950","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["MegviiDetection/FSCE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fsce-few-shot-object-detection-via#ran","syntology_url":"https://syntology.ai/paper/2103.05950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05950"}}}},{"paper":"/paper/beyond-max-margin-class-margin-equilibrium","slug":"beyond-max-margin-class-margin-equilibrium","title":"Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection","date":"2021-03-08","arxiv_id":"2103.04612","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["Bohao-Lee/CME"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beyond-max-margin-class-margin-equilibrium#ran","syntology_url":"https://syntology.ai/paper/2103.04612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.04612"}}}},{"paper":"/paper/openpifpaf-composite-fields-for-semantic","slug":"openpifpaf-composite-fields-for-semantic","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","date":"2021-03-03","arxiv_id":"2103.02440","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/towards-open-world-object-detection","slug":"towards-open-world-object-detection","title":"Towards Open World Object Detection","date":"2021-03-03","arxiv_id":"2103.02603","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["JosephKJ/OWOD"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-open-world-object-detection#ran","syntology_url":"https://syntology.ai/paper/2103.02603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.02603"}}}},{"paper":"/paper/semantic-relation-reasoning-for-shot-stable","slug":"semantic-relation-reasoning-for-shot-stable","title":"Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection","date":"2021-03-02","arxiv_id":"2103.01903","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/universal-prototype-augmentation-for-few-shot","slug":"universal-prototype-augmentation-for-few-shot","title":"Universal-Prototype Enhancing for Few-Shot Object Detection","date":"2021-03-01","arxiv_id":"2103.01077","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":2,"code_links":82,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/paper/pyramid-vision-transformer-a-versatile","slug":"pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","arxiv_id":"2102.12122","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":30,"samples_ran":22,"samples_constructed":16,"samples_ran_checked":18,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":1,"official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pyramid-vision-transformer-a-versatile#ran","syntology_url":"https://syntology.ai/paper/2102.12122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12122"}}}},{"paper":"/paper/should-i-look-at-the-head-or-the-tail-dual","slug":"should-i-look-at-the-head-or-the-tail-dual","title":"Dual-Awareness Attention for Few-Shot Object Detection","date":"2021-02-24","arxiv_id":"2102.12152","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}}}},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}}}},{"paper":"/paper/bottleneck-transformers-for-visual","slug":"bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","rows_on_this_dataset":6,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":49,"samples_ran":26,"samples_constructed":9,"samples_ran_checked":19,"samples_ran_instrument_failed":7,"samples_unverified":23,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottleneck-transformers-for-visual#ran","syntology_url":"https://syntology.ai/paper/2101.11605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11605"}}}},{"paper":"/paper/multi-hypothesis-pose-networks-rethinking-top","slug":"multi-hypothesis-pose-networks-rethinking-top","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","date":"2021-01-27","arxiv_id":"2101.11223","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["rawalkhirodkar/MIPNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-hypothesis-pose-networks-rethinking-top#ran","syntology_url":"https://syntology.ai/paper/2101.11223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11223"}}}},{"paper":"/paper/cross-modal-contrastive-learning-for-text-to","slug":"cross-modal-contrastive-learning-for-text-to","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","date":"2021-01-12","arxiv_id":"2101.04702","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["google-research/xmcgan_image_generation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-modal-contrastive-learning-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2101.04702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04702"}}}},{"paper":"/paper/similarity-reasoning-and-filtration-for-image","slug":"similarity-reasoning-and-filtration-for-image","title":"Similarity Reasoning and Filtration for Image-Text Matching","date":"2021-01-05","arxiv_id":"2101.01368","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["Paranioar/SGRAF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/similarity-reasoning-and-filtration-for-image#ran","syntology_url":"https://syntology.ai/paper/2101.01368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01368"}}}},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unimo-towards-unified-modal-understanding-and","slug":"unimo-towards-unified-modal-understanding-and","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","date":"2020-12-31","arxiv_id":"2012.15409","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/transpose-towards-explainable-human-pose","slug":"transpose-towards-explainable-human-pose","title":"TransPose: Keypoint Localization via Transformer","date":"2020-12-28","arxiv_id":"2012.14214","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/global-context-networks","slug":"global-context-networks","title":"Global Context Networks","date":"2020-12-24","arxiv_id":"2012.13375","rows_on_this_dataset":4,"code_links":3,"syntology":null},{"paper":"/paper/refine-prediction-fusion-network-for-panoptic","slug":"refine-prediction-fusion-network-for-panoptic","title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","date":"2020-12-15","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/simple-copy-paste-is-a-strong-data","slug":"simple-copy-paste-is-a-strong-data","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","date":"2020-12-13","arxiv_id":"2012.07177","rows_on_this_dataset":8,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-copy-paste-is-a-strong-data#ran","syntology_url":"https://syntology.ai/paper/2012.07177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.07177"}}}},{"paper":"/paper/ada-segment-automated-multi-loss-adaptation","slug":"ada-segment-automated-multi-loss-adaptation","title":"Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation","date":"2020-12-07","arxiv_id":"2012.03603","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/attention-driven-dynamic-graph-convolutional-1","slug":"attention-driven-dynamic-graph-convolutional-1","title":"Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition","date":"2020-12-05","arxiv_id":"2012.02994","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boxinst-high-performance-instance","slug":"boxinst-high-performance-instance","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","date":"2020-12-03","arxiv_id":"2012.02310","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/parallel-residual-bi-fusion-feature-pyramid","slug":"parallel-residual-bi-fusion-feature-pyramid","title":"Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection","date":"2020-12-03","arxiv_id":"2012.01724","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/fully-convolutional-networks-for-panoptic","slug":"fully-convolutional-networks-for-panoptic","title":"Fully Convolutional Networks for Panoptic Segmentation","date":"2020-12-01","arxiv_id":"2012.00720","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/max-deeplab-end-to-end-panoptic-segmentation","slug":"max-deeplab-end-to-end-panoptic-segmentation","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","date":"2020-12-01","arxiv_id":"2012.00759","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/scalenas-one-shot-learning-of-scale-aware","slug":"scalenas-one-shot-learning-of-scale-aware","title":"ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition","date":"2020-11-30","arxiv_id":"2011.14584","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/generalized-focal-loss-v2-learning-reliable","slug":"generalized-focal-loss-v2-learning-reliable","title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","date":"2020-11-25","arxiv_id":"2011.12885","rows_on_this_dataset":6,"code_links":5,"syntology":null},{"paper":"/paper/sparse-r-cnn-end-to-end-object-detection-with","slug":"sparse-r-cnn-end-to-end-object-detection-with","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","date":"2020-11-25","arxiv_id":"2011.12450","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/torchdistill-a-modular-configuration-driven","slug":"torchdistill-a-modular-configuration-driven","title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","date":"2020-11-25","arxiv_id":"2011.12913","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":10,"samples_unverified":16,"pointer_only_for_licence":0,"official":{"repos":["yoshitomo-matsubara/torchdistill"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/torchdistill-a-modular-configuration-driven#ran","syntology_url":"https://syntology.ai/paper/2011.12913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12913"}}}},{"paper":"/paper/scaling-wide-residual-networks-for-panoptic","slug":"scaling-wide-residual-networks-for-panoptic","title":"Scaling Wide Residual Networks for Panoptic Segmentation","date":"2020-11-23","arxiv_id":"2011.11675","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/evopose2d-pushing-the-boundaries-of-2d-human","slug":"evopose2d-pushing-the-boundaries-of-2d-human","title":"EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer","date":"2020-11-17","arxiv_id":"2011.08446","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wmcnally/evopose2d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evopose2d-pushing-the-boundaries-of-2d-human#ran","syntology_url":"https://syntology.ai/paper/2011.08446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08446"}}}},{"paper":"/paper/slender-object-detection-diagnoses-and","slug":"slender-object-detection-diagnoses-and","title":"Slender Object Detection: Diagnoses and Improvements","date":"2020-11-17","arxiv_id":"2011.08529","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","slug":"scaled-yolov4-scaling-cross-stage-partial","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","date":"2020-11-16","arxiv_id":"2011.08036","rows_on_this_dataset":6,"code_links":41,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"paper":"/paper/in-defense-of-feature-mimicking-for-knowledge","slug":"in-defense-of-feature-mimicking-for-knowledge","title":"Distilling Knowledge by Mimicking Features","date":"2020-11-03","arxiv_id":"2011.01424","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["DoctorKey/LSHFM.detection","DoctorKey/LSHFM.multiclassification","DoctorKey/LSHFM.singleclassification"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/in-defense-of-feature-mimicking-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2011.01424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01424"}}}},{"paper":"/paper/relationnet-bridging-visual-representations","slug":"relationnet-bridging-visual-representations","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","date":"2020-10-29","arxiv_id":"2010.15831","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["microsoft/RelationNet2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/relationnet-bridging-visual-representations#ran","syntology_url":"https://syntology.ai/paper/2010.15831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15831"}}}},{"paper":"/paper/activenet-a-computer-vision-based-approach-to","slug":"activenet-a-computer-vision-based-approach-to","title":"ActiveNet: A computer-vision based approach to determine lethargy","date":"2020-10-26","arxiv_id":"2010.13714","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/synthesizing-the-unseen-for-zero-shot-object","slug":"synthesizing-the-unseen-for-zero-shot-object","title":"Synthesizing the Unseen for Zero-shot Object Detection","date":"2020-10-19","arxiv_id":"2010.09425","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/background-learnable-cascade-for-zero-shot","slug":"background-learnable-cascade-for-zero-shot","title":"Background Learnable Cascade for Zero-Shot Object Detection","date":"2020-10-09","arxiv_id":"2010.04502","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deformable-detr-deformable-transformers-for-1","slug":"deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","arxiv_id":"2010.04159","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":55,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":24,"samples_ran_instrument_failed":13,"samples_unverified":18,"pointer_only_for_licence":21,"official":{"repos":["fundamentalvision/Deformable-DETR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deformable-detr-deformable-transformers-for-1#ran","syntology_url":"https://syntology.ai/paper/2010.04159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04159"}}}},{"paper":"/paper/victr-visual-information-captured-text","slug":"victr-visual-information-captured-text","title":"VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks","date":"2020-10-07","arxiv_id":"2010.03182","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/asymmetric-loss-for-multi-label","slug":"asymmetric-loss-for-multi-label","title":"Asymmetric Loss For Multi-Label Classification","date":"2020-09-29","arxiv_id":"2009.14119","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":9,"official":{"repos":["Alibaba-MIIL/ASL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/asymmetric-loss-for-multi-label#ran","syntology_url":"https://syntology.ai/paper/2009.14119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14119"}}}},{"paper":"/paper/a-ranking-based-balanced-loss-function","slug":"a-ranking-based-balanced-loss-function","title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","date":"2020-09-28","arxiv_id":"2009.13592","rows_on_this_dataset":7,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kemaloksuz/aLRPLoss"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-ranking-based-balanced-loss-function#ran","syntology_url":"https://syntology.ai/paper/2009.13592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13592"}}}},{"paper":"/paper/leveraging-instance-image-and-dataset-level","slug":"leveraging-instance-image-and-dataset-level","title":"Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation","date":"2020-09-10","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/how-to-train-your-robust-human-pose-estimator","slug":"how-to-train-your-robust-human-pose-estimator","title":"AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation","date":"2020-08-17","arxiv_id":"2008.07139","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/reducing-label-noise-in-anchor-free-object","slug":"reducing-label-noise-in-anchor-free-object","title":"Reducing Label Noise in Anchor-Free Object Detection","date":"2020-08-03","arxiv_id":"2008.01167","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/sipmask-spatial-information-preservation-for","slug":"sipmask-spatial-information-preservation-for","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","date":"2020-07-29","arxiv_id":"2007.14772","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/corner-proposal-network-for-anchor-free-two","slug":"corner-proposal-network-for-anchor-free-two","title":"Corner Proposal Network for Anchor-free, Two-stage Object Detection","date":"2020-07-27","arxiv_id":"2007.13816","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/commonality-parsing-network-across-shape-and","slug":"commonality-parsing-network-across-shape-and","title":"Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation","date":"2020-07-24","arxiv_id":"2007.12387","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/few-shot-object-detection-and-viewpoint","slug":"few-shot-object-detection-and-viewpoint","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","date":"2020-07-23","arxiv_id":"2007.12107","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/few-shot-object-detection-and-viewpoint#ran","syntology_url":"https://syntology.ai/paper/2007.12107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12107"}}}},{"paper":"/paper/multi-scale-positive-sample-refinement-for","slug":"multi-scale-positive-sample-refinement-for","title":"Multi-Scale Positive Sample Refinement for Few-Shot Object Detection","date":"2020-07-18","arxiv_id":"2007.09384","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["jiaxi-wu/MPSR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-scale-positive-sample-refinement-for#ran","syntology_url":"https://syntology.ai/paper/2007.09384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09384"}}}},{"paper":"/paper/autoregressive-unsupervised-image","slug":"autoregressive-unsupervised-image","title":"Autoregressive Unsupervised Image Segmentation","date":"2020-07-16","arxiv_id":"2007.08247","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/probabilistic-anchor-assignment-with-iou","slug":"probabilistic-anchor-assignment-with-iou","title":"Probabilistic Anchor Assignment with IoU Prediction for Object Detection","date":"2020-07-16","arxiv_id":"2007.08103","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/reppoints-v2-verification-meets-regression","slug":"reppoints-v2-verification-meets-regression","title":"RepPoints V2: Verification Meets Regression for Object Detection","date":"2020-07-16","arxiv_id":"2007.08508","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/toward-unsupervised-multi-object-discovery-in","slug":"toward-unsupervised-multi-object-discovery-in","title":"Toward unsupervised, multi-object discovery in large-scale image collections","date":"2020-07-06","arxiv_id":"2007.02662","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/houghnet-integrating-near-and-long-range","slug":"houghnet-integrating-near-and-long-range","title":"HoughNet: Integrating near and long-range evidence for bottom-up object detection","date":"2020-07-05","arxiv_id":"2007.02355","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/multi-label-image-recognition-with-multi","slug":"multi-label-image-recognition-with-multi","title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","date":"2020-07-03","arxiv_id":"2007.01755","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/localization-uncertainty-estimation-for","slug":"localization-uncertainty-estimation-for","title":"Localization Uncertainty Estimation for Anchor-Free Object Detection","date":"2020-06-28","arxiv_id":"2006.15607","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-person-pose-regression-via-pose","slug":"multi-person-pose-regression-via-pose","title":"SMPR: Single-Stage Multi-Person Pose Regression","date":"2020-06-28","arxiv_id":"2006.15576","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-pre-training-and-self-training","slug":"rethinking-pre-training-and-self-training","title":"Rethinking Pre-training and Self-training","date":"2020-06-11","arxiv_id":"2006.06882","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/virtex-learning-visual-representations-from","slug":"virtex-learning-visual-representations-from","title":"VirTex: Learning Visual Representations from Textual Annotations","date":"2020-06-11","arxiv_id":"2006.06666","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kdexd/virtex"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/virtex-learning-visual-representations-from#ran","syntology_url":"https://syntology.ai/paper/2006.06666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06666"}}}},{"paper":"/paper/generalized-focal-loss-learning-qualified-and","slug":"generalized-focal-loss-learning-qualified-and","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","date":"2020-06-08","arxiv_id":"2006.04388","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":22,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["implus/GFocal"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generalized-focal-loss-learning-qualified-and#ran","syntology_url":"https://syntology.ai/paper/2006.04388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04388"}}}},{"paper":"/paper/detectors-detecting-objects-with-recursive-1","slug":"detectors-detecting-objects-with-recursive-1","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","date":"2020-06-03","arxiv_id":"2006.02334","rows_on_this_dataset":6,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"paper":"/paper/d2det-towards-high-quality-object-detection","slug":"d2det-towards-high-quality-object-detection","title":"D2Det: Towards High Quality Object Detection and Instance Segmentation","date":"2020-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/interactive-object-segmentation-with-inside","slug":"interactive-object-segmentation-with-inside","title":"Interactive Object Segmentation With Inside-Outside Guidance","date":"2020-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-object-detection-with-transformers","slug":"end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","arxiv_id":"2005.12872","rows_on_this_dataset":5,"code_links":37,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":92,"samples_ran":70,"samples_constructed":45,"samples_ran_checked":62,"samples_ran_instrument_failed":8,"samples_unverified":22,"pointer_only_for_licence":19,"official":{"repos":["facebookresearch/detr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-object-detection-with-transformers#ran","syntology_url":"https://syntology.ai/paper/2005.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.12872"}}}},{"paper":"/paper/attention-guided-context-feature-pyramid","slug":"attention-guided-context-feature-pyramid","title":"Attention-guided Context Feature Pyramid Network for Object Detection","date":"2020-05-23","arxiv_id":"2005.11475","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/scale-equalizing-pyramid-convolution-for","slug":"scale-equalizing-pyramid-convolution-for","title":"Scale-Equalizing Pyramid Convolution for Object Detection","date":"2020-05-06","arxiv_id":"2005.03101","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-novel-region-of-interest-extraction-layer","slug":"a-novel-region-of-interest-extraction-layer","title":"A novel Region of Interest Extraction Layer for Instance Segmentation","date":"2020-04-28","arxiv_id":"2004.13665","rows_on_this_dataset":4,"code_links":5,"syntology":null},{"paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","slug":"yolov4-optimal-speed-and-accuracy-of-object","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","date":"2020-04-23","arxiv_id":"2004.10934","rows_on_this_dataset":4,"code_links":223,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":184,"samples_ran":142,"samples_constructed":0,"samples_ran_checked":133,"samples_ran_instrument_failed":9,"samples_unverified":42,"pointer_only_for_licence":21,"official":{"repos":["AlexeyAB/darknet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/yolov4-optimal-speed-and-accuracy-of-object#ran","syntology_url":"https://syntology.ai/paper/2004.10934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10934"}}}},{"paper":"/paper/resnest-split-attention-networks","slug":"resnest-split-attention-networks","title":"ResNeSt: Split-Attention Networks","date":"2020-04-19","arxiv_id":"2004.08955","rows_on_this_dataset":11,"code_links":36,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":48,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":25,"samples_ran_instrument_failed":3,"samples_unverified":20,"pointer_only_for_licence":23,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"paper":"/paper/dynamic-r-cnn-towards-high-quality-object","slug":"dynamic-r-cnn-towards-high-quality-object","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","date":"2020-04-13","arxiv_id":"2004.06002","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":1,"official":{"repos":["hkzhang95/DynamicRCNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dynamic-r-cnn-towards-high-quality-object#ran","syntology_url":"https://syntology.ai/paper/2004.06002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06002"}}}},{"paper":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":23,"samples_ran":13,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":1,"official":{"repos":["microsoft/Oscar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}}}},{"paper":"/paper/instance-aware-context-focused-and-memory","slug":"instance-aware-context-focused-and-memory","title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","date":"2020-04-09","arxiv_id":"2004.04725","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["NVlabs/wetectron"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/instance-aware-context-focused-and-memory#ran","syntology_url":"https://syntology.ai/paper/2004.04725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04725"}}}},{"paper":"/paper/pixel-consensus-voting-for-panoptic","slug":"pixel-consensus-voting-for-panoptic","title":"Pixel Consensus Voting for Panoptic Segmentation","date":"2020-04-04","arxiv_id":"2004.01849","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/saccadenet-a-fast-and-accurate-object","slug":"saccadenet-a-fast-and-accurate-object","title":"SaccadeNet: A Fast and Accurate Object Detector","date":"2020-03-26","arxiv_id":"2003.12125","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/epsnet-efficient-panoptic-segmentation","slug":"epsnet-efficient-panoptic-segmentation","title":"EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion","date":"2020-03-23","arxiv_id":"2003.10142","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/solov2-dynamic-faster-and-stronger","slug":"solov2-dynamic-faster-and-stronger","title":"SOLOv2: Dynamic and Fast Instance Segmentation","date":"2020-03-23","arxiv_id":"2003.10152","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":38,"samples_ran":23,"samples_constructed":4,"samples_ran_checked":15,"samples_ran_instrument_failed":8,"samples_unverified":15,"pointer_only_for_licence":24,"official":{"repos":["WXinlong/SOLO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/solov2-dynamic-faster-and-stronger#ran","syntology_url":"https://syntology.ai/paper/2003.10152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10152"}}}},{"paper":"/paper/axial-deeplab-stand-alone-axial-attention-for","slug":"axial-deeplab-stand-alone-axial-attention-for","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","date":"2020-03-17","arxiv_id":"2003.07853","rows_on_this_dataset":5,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["google-research/deeplab2"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/axial-deeplab-stand-alone-axial-attention-for#ran","syntology_url":"https://syntology.ai/paper/2003.07853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07853"}}}},{"paper":"/paper/revisiting-the-sibling-head-in-object","slug":"revisiting-the-sibling-head-in-object","title":"Revisiting the Sibling Head in Object Detector","date":"2020-03-17","arxiv_id":"2003.07540","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/frustratingly-simple-few-shot-object","slug":"frustratingly-simple-few-shot-object","title":"Frustratingly Simple Few-Shot Object Detection","date":"2020-03-16","arxiv_id":"2003.06957","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":11,"official":{"repos":["ucbdrive/few-shot-object-detection"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frustratingly-simple-few-shot-object#ran","syntology_url":"https://syntology.ai/paper/2003.06957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06957"}}}},{"paper":"/paper/object-centric-image-generation-from-layouts","slug":"object-centric-image-generation-from-layouts","title":"Object-Centric Image Generation from Layouts","date":"2020-03-16","arxiv_id":"2003.07449","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-delicate-local-representations-for","slug":"learning-delicate-local-representations-for","title":"Learning Delicate Local Representations for Multi-Person Pose Estimation","date":"2020-03-09","arxiv_id":"2003.04030","rows_on_this_dataset":5,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["caiyuanhao1998/RSN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-delicate-local-representations-for#ran","syntology_url":"https://syntology.ai/paper/2003.04030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04030"}}}},{"paper":"/paper/imram-iterative-matching-with-recurrent","slug":"imram-iterative-matching-with-recurrent","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","date":"2020-03-08","arxiv_id":"2003.03772","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["HuiChen24/IMRAM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imram-iterative-matching-with-recurrent#ran","syntology_url":"https://syntology.ai/paper/2003.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03772"}}}},{"paper":"/paper/a-u-net-based-discriminator-for-generative","slug":"a-u-net-based-discriminator-for-generative","title":"A U-Net Based Discriminator for Generative Adversarial Networks","date":"2020-02-28","arxiv_id":"2002.12655","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/cross-iteration-batch-normalization","slug":"cross-iteration-batch-normalization","title":"Cross-Iteration Batch Normalization","date":"2020-02-13","arxiv_id":"2002.05712","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["Howal/Cross-iterationBatchNorm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-iteration-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/2002.05712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05712"}}}},{"paper":"/paper/towards-high-performance-human-keypoint","slug":"towards-high-performance-human-keypoint","title":"Towards High Performance Human Keypoint Detection","date":"2020-02-03","arxiv_id":"2002.00537","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"record_sha256":"0bb293fb76b0e0145d74b212b0951c4d9037823dac36b851941b02c04813ef0a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}