{"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":"/task/object-detection/papers/5","list_of":"/task/object-detection","task":"Object Detection","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_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'","n_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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":5,"pages_in_order":110,"rows_per_page":100,"rows":[401,500],"of":10957,"counts":{"archive_papers_tagged":10957,"with_a_code_link":4657,"where_syntology_ran_a_sample":1183,"not_listed_spam_title":0,"listed":10957,"listed_where_code_ran":1183,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1038,"every_run_a_failure_of_syntologys_instrument":145,"listed_with_a_run_with_no_instrument_failure":1038,"listed_every_run_a_failure_of_syntologys_instrument":145,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object-detection","prev":"/task/object-detection/papers/4","next":"/task/object-detection/papers/6","papers":[{"url":"/paper/wave-vit-unifying-wavelet-and-transformers","slug":"wave-vit-unifying-wavelet-and-transformers","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","date":"2022-07-11","arxiv_id":"2207.04978","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wave-vit-unifying-wavelet-and-transformers#ran","syntology_url":"https://syntology.ai/paper/2207.04978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04978"}},"official":{"repos":["yehli/imagenetmodel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/k-means-mask-transformer","slug":"k-means-mask-transformer","title":"kMaX-DeepLab: k-means Mask Transformer","date":"2022-07-08","arxiv_id":"2207.04044","repositories_listed":3,"syntology":null},{"url":"/paper/small-object-detection-via-pixel-level","slug":"small-object-detection-via-pixel-level","title":"Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection","date":"2022-06-17","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/label-matching-semi-supervised-object-1","slug":"label-matching-semi-supervised-object-1","title":"Label Matching Semi-Supervised Object Detection","date":"2022-06-14","arxiv_id":"2206.06608","repositories_listed":3,"syntology":null},{"url":"/paper/transfuser-imitation-with-transformer-based","slug":"transfuser-imitation-with-transformer-based","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","date":"2022-05-31","arxiv_id":"2205.15997","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfuser-imitation-with-transformer-based#ran","syntology_url":"https://syntology.ai/paper/2205.15997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15997"}},"official":{"repos":["autonomousvision/transfuser"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gconet-a-stronger-group-collaborative-co","slug":"gconet-a-stronger-group-collaborative-co","title":"GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector","date":"2022-05-30","arxiv_id":"2205.15469","repositories_listed":3,"syntology":null},{"url":"/paper/point-m2ae-multi-scale-masked-autoencoders","slug":"point-m2ae-multi-scale-masked-autoencoders","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","date":"2022-05-28","arxiv_id":"2205.14401","repositories_listed":3,"syntology":null},{"url":"/paper/architecture-agnostic-masked-image-modeling","slug":"architecture-agnostic-masked-image-modeling","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","date":"2022-05-27","arxiv_id":"2205.13943","repositories_listed":3,"syntology":null},{"url":"/paper/knowledge-distillation-from-a-stronger","slug":"knowledge-distillation-from-a-stronger","title":"Knowledge Distillation from A Stronger Teacher","date":"2022-05-21","arxiv_id":"2205.10536","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":1,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":4,"n_violates":4,"n_no_contract":2,"n_pointer_only":0,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 4 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knowledge-distillation-from-a-stronger#ran","syntology_url":"https://syntology.ai/paper/2205.10536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10536"}},"official":{"repos":["hunto/dist_kd"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/integral-migrating-pre-trained-transformer","slug":"integral-migrating-pre-trained-transformer","title":"Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection","date":"2022-05-19","arxiv_id":"2205.09613","repositories_listed":3,"syntology":null},{"url":"/paper/masked-generative-distillation","slug":"masked-generative-distillation","title":"Masked Generative Distillation","date":"2022-05-03","arxiv_id":"2205.01529","repositories_listed":3,"syntology":null},{"url":"/paper/centernet-for-object-detection","slug":"centernet-for-object-detection","title":"CenterNet++ for Object Detection","date":"2022-04-18","arxiv_id":"2204.08394","repositories_listed":3,"syntology":null},{"url":"/paper/collaborative-transformers-for-grounded","slug":"collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","arxiv_id":"2203.16518","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/collaborative-transformers-for-grounded#ran","syntology_url":"https://syntology.ai/paper/2203.16518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16518"}},"official":{"repos":["jhcho99/coformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/simcrosstrans-a-simple-cross-modality","slug":"simcrosstrans-a-simple-cross-modality","title":"simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers","date":"2022-03-20","arxiv_id":"2203.10456","repositories_listed":3,"syntology":null},{"url":"/paper/hybridnets-end-to-end-perception-network-1","slug":"hybridnets-end-to-end-perception-network-1","title":"HybridNets: End-to-End Perception Network","date":"2022-03-17","arxiv_id":"2203.09035","repositories_listed":3,"syntology":null},{"url":"/paper/edgeformer-improving-light-weight-convnets-by","slug":"edgeformer-improving-light-weight-convnets-by","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","date":"2022-03-08","arxiv_id":"2203.03952","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/edgeformer-improving-light-weight-convnets-by#ran","syntology_url":"https://syntology.ai/paper/2203.03952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03952"}},"official":{"repos":["hkzhang91/edgeformer","hkzhang91/pacc-net","hkzhang91/parc-net"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/muad-multiple-uncertainties-for-autonomous","slug":"muad-multiple-uncertainties-for-autonomous","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","date":"2022-03-02","arxiv_id":"2203.01437","repositories_listed":3,"syntology":null},{"url":"/paper/tableformer-table-structure-understanding","slug":"tableformer-table-structure-understanding","title":"TableFormer: Table Structure Understanding with Transformers","date":"2022-03-02","arxiv_id":"2203.01017","repositories_listed":3,"syntology":null},{"url":"/paper/bed-a-real-time-object-detection-system-for","slug":"bed-a-real-time-object-detection-system-for","title":"BED: A Real-Time Object Detection System for Edge Devices","date":"2022-02-14","arxiv_id":"2202.07503","repositories_listed":3,"syntology":null},{"url":"/paper/the-kfiou-loss-for-rotated-object-detection-1","slug":"the-kfiou-loss-for-rotated-object-detection-1","title":"The KFIoU Loss for Rotated Object Detection","date":"2022-01-29","arxiv_id":"2201.12558","repositories_listed":3,"syntology":{"n":7,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-kfiou-loss-for-rotated-object-detection-1#ran","syntology_url":"https://syntology.ai/paper/2201.12558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12558"}},"official":{"repos":["Jittor/JDet","yangxue0827/RotationDetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/transvod-end-to-end-video-object-detection","slug":"transvod-end-to-end-video-object-detection","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2022-01-13","arxiv_id":"2201.05047","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transvod-end-to-end-video-object-detection#ran","syntology_url":"https://syntology.ai/paper/2201.05047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05047"}},"official":{"repos":["qianyuzqy/TransVOD_Lite"],"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":["named_in_paper","official"]}}},{"url":"/paper/mpvit-multi-path-vision-transformer-for-dense","slug":"mpvit-multi-path-vision-transformer-for-dense","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","date":"2021-12-21","arxiv_id":"2112.11010","repositories_listed":3,"syntology":null},{"url":"/paper/a-simple-single-scale-vision-transformer-for","slug":"a-simple-single-scale-vision-transformer-for","title":"A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation","date":"2021-12-17","arxiv_id":"2112.09747","repositories_listed":3,"syntology":null},{"url":"/paper/dilated-convolution-with-learnable-spacings","slug":"dilated-convolution-with-learnable-spacings","title":"Dilated convolution with learnable spacings","date":"2021-12-07","arxiv_id":"2112.03740","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/dilated-convolution-with-learnable-spacings#ran","syntology_url":"https://syntology.ai/paper/2112.03740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03740"}},"official":{"repos":["k-h-ismail/convnext-dcls","k-h-ismail/dilated-convolution-with-learnable-spacings-pytorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/grounded-language-image-pre-training","slug":"grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","date":"2021-12-07","arxiv_id":"2112.03857","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2112.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03857"}},"official":{"repos":["microsoft/GLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dancetrack-multi-object-tracking-in-uniform","slug":"dancetrack-multi-object-tracking-in-uniform","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","date":"2021-11-29","arxiv_id":"2111.14690","repositories_listed":3,"syntology":null},{"url":"/paper/a-normalized-gaussian-wasserstein-distance","slug":"a-normalized-gaussian-wasserstein-distance","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","date":"2021-10-26","arxiv_id":"2110.13389","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-normalized-gaussian-wasserstein-distance#ran","syntology_url":"https://syntology.ai/paper/2110.13389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13389"}},"official":{"repos":["jwwangchn/NWD"],"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"]}}},{"url":"/paper/parsing-table-structures-in-the-wild","slug":"parsing-table-structures-in-the-wild","title":"Parsing Table Structures in the Wild","date":"2021-09-06","arxiv_id":"2109.02199","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/parsing-table-structures-in-the-wild#ran","syntology_url":"https://syntology.ai/paper/2109.02199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02199"}},"official":{"repos":["wangwen-whu/wtw-dataset"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tph-yolov5-improved-yolov5-based-on","slug":"tph-yolov5-improved-yolov5-based-on","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","date":"2021-08-26","arxiv_id":"2108.11539","repositories_listed":3,"syntology":null},{"url":"/paper/exploring-simple-3d-multi-object-tracking-for","slug":"exploring-simple-3d-multi-object-tracking-for","title":"Exploring Simple 3D Multi-Object Tracking for Autonomous Driving","date":"2021-08-23","arxiv_id":"2108.10312","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/exploring-simple-3d-multi-object-tracking-for#ran","syntology_url":"https://syntology.ai/paper/2108.10312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10312"}},"official":{"repos":["qcraftai/simtrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/specificity-preserving-rgb-d-saliency","slug":"specificity-preserving-rgb-d-saliency","title":"Specificity-preserving RGB-D Saliency Detection","date":"2021-08-18","arxiv_id":"2108.08162","repositories_listed":3,"syntology":{"n":14,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/specificity-preserving-rgb-d-saliency#ran","syntology_url":"https://syntology.ai/paper/2108.08162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08162"}},"official":{"repos":["taozh2017/RGBD-SODsurvey","taozh2017/spnet","nnizhang/SMAC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/rank-sort-loss-for-object-detection-and","slug":"rank-sort-loss-for-object-detection-and","title":"Rank & Sort Loss for Object Detection and Instance Segmentation","date":"2021-07-24","arxiv_id":"2107.11669","repositories_listed":3,"syntology":null},{"url":"/paper/real-time-pear-fruit-detection-and-counting","slug":"real-time-pear-fruit-detection-and-counting","title":"Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT","date":"2021-07-14","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/locally-enhanced-self-attention-rethinking","slug":"locally-enhanced-self-attention-rethinking","title":"Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms","date":"2021-07-12","arxiv_id":"2107.05637","repositories_listed":3,"syntology":null},{"url":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/focal-self-attention-for-local-global#ran","syntology_url":"https://syntology.ai/paper/2107.00641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00641"}},"official":{"repos":["microsoft/Focal-Transformer"],"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":["official","unlocated"]}}},{"url":"/paper/dynamic-head-unifying-object-detection-heads","slug":"dynamic-head-unifying-object-detection-heads","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","date":"2021-06-15","arxiv_id":"2106.08322","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}},"official":{"repos":["microsoft/DynamicHead"],"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"]}}},{"url":"/paper/sparse-pointpillars-exploiting-sparsity-in","slug":"sparse-pointpillars-exploiting-sparsity-in","title":"Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems","date":"2021-06-12","arxiv_id":"2106.06882","repositories_listed":3,"syntology":null},{"url":"/paper/icdar-2021-competition-on-scientific","slug":"icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","date":"2021-06-08","arxiv_id":"2106.14616","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/icdar-2021-competition-on-scientific#ran","syntology_url":"https://syntology.ai/paper/2106.14616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14616"}},"official":{"repos":["ibm-aur-nlp/PubLayNet","ibm-aur-nlp/PubTabNet","wenwenyu/MASTER-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transformer-in-convolutional-neural-networks","slug":"transformer-in-convolutional-neural-networks","title":"Vision Transformers with Hierarchical Attention","date":"2021-06-06","arxiv_id":"2106.03180","repositories_listed":3,"syntology":null},{"url":"/paper/msg-transformer-exchanging-local-spatial","slug":"msg-transformer-exchanging-local-spatial","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","date":"2021-05-31","arxiv_id":"2105.15168","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/msg-transformer-exchanging-local-spatial#ran","syntology_url":"https://syntology.ai/paper/2105.15168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15168"}},"official":{"repos":["hustvl/MSG-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/yolo5face-why-reinventing-a-face-detector","slug":"yolo5face-why-reinventing-a-face-detector","title":"YOLO5Face: Why Reinventing a Face Detector","date":"2021-05-27","arxiv_id":"2105.12931","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/yolo5face-why-reinventing-a-face-detector#ran","syntology_url":"https://syntology.ai/paper/2105.12931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12931"}},"official":{"repos":["deepcam-cn/yolov5-face"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/houghnet-integrating-near-and-long-range-1","slug":"houghnet-integrating-near-and-long-range-1","title":"HoughNet: Integrating near and long-range evidence for visual detection","date":"2021-04-14","arxiv_id":"2104.06773","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-object-detection-via-bayesian","slug":"multimodal-object-detection-via-bayesian","title":"Multimodal Object Detection via Probabilistic Ensembling","date":"2021-04-07","arxiv_id":"2104.02904","repositories_listed":3,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multimodal-object-detection-via-bayesian#ran","syntology_url":"https://syntology.ai/paper/2104.02904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02904"}},"official":{"repos":["Jamie725/RGBT-detection"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/objects-are-different-flexible-monocular-3d","slug":"objects-are-different-flexible-monocular-3d","title":"Objects are Different: Flexible Monocular 3D Object Detection","date":"2021-04-06","arxiv_id":"2104.02323","repositories_listed":3,"syntology":{"n":20,"n_ran":14,"n_constructed":1,"n_ran_checked":6,"n_instrument":8,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"14 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/objects-are-different-flexible-monocular-3d#ran","syntology_url":"https://syntology.ai/paper/2104.02323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02323"}},"official":{"repos":["zhangyp15/MonoFlex"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2103-15358#ran","syntology_url":"https://syntology.ai/paper/2103.15358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15358"}},"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"]}}},{"url":"/paper/diverse-branch-block-building-a-convolution","slug":"diverse-branch-block-building-a-convolution","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","date":"2021-03-24","arxiv_id":"2103.13425","repositories_listed":3,"syntology":{"n":20,"n_ran":11,"n_constructed":3,"n_ran_checked":4,"n_instrument":7,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/diverse-branch-block-building-a-convolution#ran","syntology_url":"https://syntology.ai/paper/2103.13425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13425"}},"official":{"repos":["DingXiaoH/DiverseBranchBlock"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/robust-and-accurate-object-detection-via","slug":"robust-and-accurate-object-detection-via","title":"Robust and Accurate Object Detection via Adversarial Learning","date":"2021-03-23","arxiv_id":"2103.13886","repositories_listed":3,"syntology":null},{"url":"/paper/3d-human-pose-estimation-with-spatial-and","slug":"3d-human-pose-estimation-with-spatial-and","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","date":"2021-03-18","arxiv_id":"2103.10455","repositories_listed":3,"syntology":{"n":8,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/3d-human-pose-estimation-with-spatial-and#ran","syntology_url":"https://syntology.ai/paper/2103.10455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10455"}},"official":{"repos":["zczcwh/PoseFormer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/probabilistic-two-stage-detection","slug":"probabilistic-two-stage-detection","title":"Probabilistic two-stage detection","date":"2021-03-12","arxiv_id":"2103.07461","repositories_listed":3,"syntology":null},{"url":"/paper/uncertainty-aware-unsupervised-domain","slug":"uncertainty-aware-unsupervised-domain","title":"Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection","date":"2021-02-27","arxiv_id":"2103.00236","repositories_listed":3,"syntology":null},{"url":"/paper/brecq-pushing-the-limit-of-post-training-1","slug":"brecq-pushing-the-limit-of-post-training-1","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","date":"2021-02-10","arxiv_id":"2102.05426","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brecq-pushing-the-limit-of-post-training-1#ran","syntology_url":"https://syntology.ai/paper/2102.05426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05426"}},"official":{"repos":["yhhhli/BRECQ"],"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","unlocated"]}}},{"url":"/paper/sa-net-shuffle-attention-for-deep","slug":"sa-net-shuffle-attention-for-deep","title":"SA-Net: Shuffle Attention for Deep Convolutional Neural Networks","date":"2021-01-30","arxiv_id":"2102.00240","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sa-net-shuffle-attention-for-deep#ran","syntology_url":"https://syntology.ai/paper/2102.00240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.00240"}},"official":{"repos":["wofmanaf/SA-Net"],"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"]}}},{"url":"/paper/a-comparative-analysis-of-object-detection","slug":"a-comparative-analysis-of-object-detection","title":"A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit","date":"2021-01-25","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/salient-object-detection-via-integrity","slug":"salient-object-detection-via-integrity","title":"Salient Object Detection via Integrity Learning","date":"2021-01-19","arxiv_id":"2101.07663","repositories_listed":3,"syntology":null},{"url":"/paper/estimating-and-evaluating-regression","slug":"estimating-and-evaluating-regression","title":"Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors","date":"2021-01-13","arxiv_id":"2101.05036","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/estimating-and-evaluating-regression#ran","syntology_url":"https://syntology.ai/paper/2101.05036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05036"}},"official":{"repos":["asharakeh/probdet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/global-context-networks","slug":"global-context-networks","title":"Global Context Networks","date":"2020-12-24","arxiv_id":"2012.13375","repositories_listed":3,"syntology":null},{"url":"/paper/online-bag-of-visual-words-generation-for","slug":"online-bag-of-visual-words-generation-for","title":"OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning","date":"2020-12-21","arxiv_id":"2012.11552","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/online-bag-of-visual-words-generation-for#ran","syntology_url":"https://syntology.ai/paper/2012.11552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.11552"}},"official":{"repos":["valeoai/obow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/confluence-a-robust-non-iou-alternative-to","slug":"confluence-a-robust-non-iou-alternative-to","title":"Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection","date":"2020-12-01","arxiv_id":"2012.00257","repositories_listed":3,"syntology":null},{"url":"/paper/dense-attention-fluid-network-for-salient","slug":"dense-attention-fluid-network-for-salient","title":"Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images","date":"2020-11-26","arxiv_id":"2011.13144","repositories_listed":3,"syntology":null},{"url":"/paper/ramp-cnn-a-novel-neural-network-for-enhanced","slug":"ramp-cnn-a-novel-neural-network-for-enhanced","title":"RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition","date":"2020-11-13","arxiv_id":"2011.08981","repositories_listed":3,"syntology":null},{"url":"/paper/centerfusion-center-based-radar-and-camera","slug":"centerfusion-center-based-radar-and-camera","title":"CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection","date":"2020-11-10","arxiv_id":"2011.04841","repositories_listed":3,"syntology":null},{"url":"/paper/efficientpose-an-efficient-accurate-and","slug":"efficientpose-an-efficient-accurate-and","title":"EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach","date":"2020-11-09","arxiv_id":"2011.04307","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/paper/yolobile-real-time-object-detection-on-mobile","slug":"yolobile-real-time-object-detection-on-mobile","title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","date":"2020-09-12","arxiv_id":"2009.05697","repositories_listed":3,"syntology":null},{"url":"/paper/align-deep-features-for-oriented-object","slug":"align-deep-features-for-oriented-object","title":"Align Deep Features for Oriented Object Detection","date":"2020-08-21","arxiv_id":"2008.09397","repositories_listed":3,"syntology":null},{"url":"/paper/suppress-and-balance-a-simple-gated-network","slug":"suppress-and-balance-a-simple-gated-network","title":"Suppress and Balance: A Simple Gated Network for Salient Object Detection","date":"2020-07-16","arxiv_id":"2007.08074","repositories_listed":3,"syntology":null},{"url":"/paper/pyramidal-convolution-rethinking","slug":"pyramidal-convolution-rethinking","title":"Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition","date":"2020-06-20","arxiv_id":"2006.11538","repositories_listed":3,"syntology":null},{"url":"/paper/quasi-dense-instance-similarity-learning","slug":"quasi-dense-instance-similarity-learning","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","date":"2020-06-11","arxiv_id":"2006.06664","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/object-detection-in-the-dct-domain-is","slug":"object-detection-in-the-dct-domain-is","title":"Object Detection in the DCT Domain: is Luminance the Solution?","date":"2020-06-10","arxiv_id":"2006.05732","repositories_listed":3,"syntology":null},{"url":"/paper/improving-convolutional-networks-with-self","slug":"improving-convolutional-networks-with-self","title":"Improving Convolutional Networks With Self-Calibrated Convolutions","date":"2020-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","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"}},"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"]}}},{"url":"/paper/tresnet-high-performance-gpu-dedicated","slug":"tresnet-high-performance-gpu-dedicated","title":"TResNet: High Performance GPU-Dedicated Architecture","date":"2020-03-30","arxiv_id":"2003.13630","repositories_listed":3,"syntology":null},{"url":"/paper/detection-in-crowded-scenes-one-proposal","slug":"detection-in-crowded-scenes-one-proposal","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","date":"2020-03-20","arxiv_id":"2003.09163","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/detection-in-crowded-scenes-one-proposal#ran","syntology_url":"https://syntology.ai/paper/2003.09163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.09163"}},"official":{"repos":["megvii-model/CrowdDetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/smoke-single-stage-monocular-3d-object","slug":"smoke-single-stage-monocular-3d-object","title":"SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation","date":"2020-02-24","arxiv_id":"2002.10111","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/smoke-single-stage-monocular-3d-object#ran","syntology_url":"https://syntology.ai/paper/2002.10111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10111"}},"official":{"repos":["lzccccc/SMOKE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/near-lossless-post-training-quantization-of","slug":"near-lossless-post-training-quantization-of","title":"Post-Training Piecewise Linear Quantization for Deep Neural Networks","date":"2020-01-31","arxiv_id":"2002.00104","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/near-lossless-post-training-quantization-of#ran","syntology_url":"https://syntology.ai/paper/2002.00104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00104"}},"official":null}},{"url":"/paper/deep-learning-for-3d-point-clouds-a-survey","slug":"deep-learning-for-3d-point-clouds-a-survey","title":"Deep Learning for 3D Point Clouds: A Survey","date":"2019-12-27","arxiv_id":"1912.12033","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-object-detection-in-large-images","slug":"efficient-object-detection-in-large-images","title":"Efficient Object Detection in Large Images using Deep Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.03966","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-object-detection-in-large-images#ran","syntology_url":"https://syntology.ai/paper/1912.03966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.03966"}},"official":{"repos":["uzkent/EfficientObjectDetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/side-aware-boundary-localization-for-more","slug":"side-aware-boundary-localization-for-more","title":"Side-Aware Boundary Localization for More Precise Object Detection","date":"2019-12-09","arxiv_id":"1912.04260","repositories_listed":3,"syntology":null},{"url":"/paper/long-term-temporal-context-for-per-camera","slug":"long-term-temporal-context-for-per-camera","title":"Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection","date":"2019-12-07","arxiv_id":"1912.03538","repositories_listed":3,"syntology":null},{"url":"/paper/multiple-anchor-learning-for-visual-object","slug":"multiple-anchor-learning-for-visual-object","title":"Multiple Anchor Learning for Visual Object Detection","date":"2019-12-04","arxiv_id":"1912.02252","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-anchor-learning-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/1912.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02252"}},"official":null}},{"url":"/paper/cagnet-content-aware-guidance-for-salient","slug":"cagnet-content-aware-guidance-for-salient","title":"CAGNet: Content-Aware Guidance for Salient Object Detection","date":"2019-11-29","arxiv_id":"1911.13168","repositories_listed":3,"syntology":null},{"url":"/paper/mixture-model-based-bounding-box-density","slug":"mixture-model-based-bounding-box-density","title":"Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Image","date":"2019-11-28","arxiv_id":"1911.12721","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mixture-model-based-bounding-box-density#ran","syntology_url":"https://syntology.ai/paper/1911.12721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12721"}},"official":{"repos":["yoojy31/mdod"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gated-channel-transformation-for-visual","slug":"gated-channel-transformation-for-visual","title":"Gated Channel Transformation for Visual Recognition","date":"2019-09-25","arxiv_id":"1909.11519","repositories_listed":3,"syntology":null},{"url":"/paper/class-balanced-grouping-and-sampling-for","slug":"class-balanced-grouping-and-sampling-for","title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","date":"2019-08-26","arxiv_id":"1908.09492","repositories_listed":3,"syntology":{"n":22,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/class-balanced-grouping-and-sampling-for#ran","syntology_url":"https://syntology.ai/paper/1908.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09492"}},"official":{"repos":["poodarchu/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/egnetedge-guidance-network-for-salient-object","slug":"egnetedge-guidance-network-for-salient-object","title":"EGNet:Edge Guidance Network for Salient Object Detection","date":"2019-08-22","arxiv_id":"1908.08297","repositories_listed":3,"syntology":null},{"url":"/paper/instaboost-boosting-instance-segmentation-via","slug":"instaboost-boosting-instance-segmentation-via","title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","date":"2019-08-21","arxiv_id":"1908.07801","repositories_listed":3,"syntology":null},{"url":"/paper/lvis-a-dataset-for-large-vocabulary-instance-1","slug":"lvis-a-dataset-for-large-vocabulary-instance-1","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","date":"2019-08-08","arxiv_id":"1908.03195","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lvis-a-dataset-for-large-vocabulary-instance-1#ran","syntology_url":"https://syntology.ai/paper/1908.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03195"}},"official":null}},{"url":"/paper/few-shot-object-detection-with-attention-rpn","slug":"few-shot-object-detection-with-attention-rpn","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","date":"2019-08-06","arxiv_id":"1908.01998","repositories_listed":3,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/few-shot-object-detection-with-attention-rpn#ran","syntology_url":"https://syntology.ai/paper/1908.01998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01998"}},"official":{"repos":["fanq15/FewX"],"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"]}}},{"url":"/paper/nas-fcos-fast-neural-architecture-search-for","slug":"nas-fcos-fast-neural-architecture-search-for","title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","date":"2019-06-11","arxiv_id":"1906.04423","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nas-fcos-fast-neural-architecture-search-for#ran","syntology_url":"https://syntology.ai/paper/1906.04423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04423"}},"official":null}},{"url":"/paper/distilling-object-detectors-with-fine-grained-1","slug":"distilling-object-detectors-with-fine-grained-1","title":"Distilling Object Detectors with Fine-grained Feature Imitation","date":"2019-06-09","arxiv_id":"1906.03609","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/distilling-object-detectors-with-fine-grained-1#ran","syntology_url":"https://syntology.ai/paper/1906.03609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03609"}},"official":{"repos":["twangnh/Distilling-Object-Detectors"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/basnet-boundary-aware-salient-object","slug":"basnet-boundary-aware-salient-object","title":"BASNet: Boundary-Aware Salient Object Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/isaid-a-large-scale-dataset-for-instance","slug":"isaid-a-large-scale-dataset-for-instance","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","date":"2019-05-30","arxiv_id":"1905.12886","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/isaid-a-large-scale-dataset-for-instance#ran","syntology_url":"https://syntology.ai/paper/1905.12886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12886"}},"official":{"repos":["CAPTAIN-WHU/iSAID_Devkit"],"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"]}}},{"url":"/paper/spatial-group-wise-enhance-improving-semantic","slug":"spatial-group-wise-enhance-improving-semantic","title":"Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks","date":"2019-05-23","arxiv_id":"1905.09646","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spatial-group-wise-enhance-improving-semantic#ran","syntology_url":"https://syntology.ai/paper/1905.09646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09646"}},"official":{"repos":["implus/PytorchInsight"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-bi-directional-co-design-approach-to-enable","slug":"a-bi-directional-co-design-approach-to-enable","title":"A Bi-Directional Co-Design Approach to Enable Deep Learning on IoT Devices","date":"2019-05-20","arxiv_id":"1905.08369","repositories_listed":3,"syntology":null},{"url":"/paper/carafe-content-aware-reassembly-of-features","slug":"carafe-content-aware-reassembly-of-features","title":"CARAFE: Content-Aware ReAssembly of FEatures","date":"2019-05-06","arxiv_id":"1905.02188","repositories_listed":3,"syntology":null},{"url":"/paper/fpgadnn-co-design-an-efficient-design","slug":"fpgadnn-co-design-an-efficient-design","title":"FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge","date":"2019-04-09","arxiv_id":"1904.04421","repositories_listed":3,"syntology":null},{"url":"/paper/thundernet-towards-real-time-generic-object","slug":"thundernet-towards-real-time-generic-object","title":"ThunderNet: Towards Real-time Generic Object Detection","date":"2019-03-28","arxiv_id":"1903.11752","repositories_listed":3,"syntology":null},{"url":"/paper/fast-underwater-image-enhancement-for","slug":"fast-underwater-image-enhancement-for","title":"Fast Underwater Image Enhancement for Improved Visual Perception","date":"2019-03-23","arxiv_id":"1903.09766","repositories_listed":3,"syntology":null}],"record_sha256":"09117ef50d29f5aafbec1061500d9ef606c3d6235680260940db396e30da61a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}