{"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":"/method/layer-normalization/papers/250","list_of":"/method/layer-normalization","method":"Layer Normalization","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":250,"pages_in_order":250,"rows_per_page":100,"rows":[24901,24980],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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":"/method/layer-normalization","prev":"/method/layer-normalization/papers/249","next":null,"papers":[{"paper":"/paper/character-level-language-modeling-with-deeper","slug":"character-level-language-modeling-with-deeper","title":"Character-Level Language Modeling with Deeper Self-Attention","date":"2018-08-09","arxiv_id":"1808.04444","n_code_links":1,"syntology":null},{"paper":"/paper/design-challenges-in-named-entity","slug":"design-challenges-in-named-entity","title":"Design Challenges in Named Entity Transliteration","date":"2018-08-07","arxiv_id":"1808.02563","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-decoding","title":"Neural Machine Translation with Decoding History Enhanced Attention","date":"2018-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"doubly-attentive-transformer-machine","title":"Doubly Attentive Transformer Machine Translation","date":"2018-07-30","arxiv_id":"1807.11605","n_code_links":0,"syntology":null},{"paper":"/paper/reenactgan-learning-to-reenact-faces-via","slug":"reenactgan-learning-to-reenact-faces-via","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","date":"2018-07-29","arxiv_id":"1807.11079","n_code_links":1,"syntology":null},{"paper":null,"slug":"recurrent-neural-networks-for-long-and-short","title":"Recurrent Neural Networks for Long and Short-Term Sequential Recommendation","date":"2018-07-23","arxiv_id":"1807.09142","n_code_links":0,"syntology":null},{"paper":null,"slug":"destnet-densely-fused-spatial-transformer","title":"DeSTNet: Densely Fused Spatial Transformer Networks","date":"2018-07-11","arxiv_id":"1807.04050","n_code_links":0,"syntology":null},{"paper":"/paper/universal-transformers","slug":"universal-transformers","title":"Universal Transformers","date":"2018-07-10","arxiv_id":"1807.03819","n_code_links":8,"syntology":{"ran":17,"of":25,"n_ran_checked":17,"n_instrument":0,"unverified":8,"pointer_only":24,"phrase":"17 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"model-based-hand-pose-estimation-for","title":"Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization","date":"2018-07-02","arxiv_id":"1807.00898","n_code_links":0,"syntology":null},{"paper":"/paper/conceptual-captions-a-cleaned-hypernymed","slug":"conceptual-captions-a-cleaned-hypernymed","title":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning","date":"2018-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/how-much-attention-do-you-need-a-granular","slug":"how-much-attention-do-you-need-a-granular","title":"How Much Attention Do You Need? A Granular Analysis of Neural Machine Translation Architectures","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-longer-term-dependencies-in-rnns-1","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","date":"2018-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-turn-response-selection-for-chatbots","slug":"multi-turn-response-selection-for-chatbots","title":"Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"nict-self-training-approach-to-neural-machine","title":"NICT Self-Training Approach to Neural Machine Translation at NMT-2018","date":"2018-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-annotated-transformer","slug":"the-annotated-transformer","title":"The Annotated Transformer","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/differentiable-learning-to-normalize-via","slug":"differentiable-learning-to-normalize-via","title":"Differentiable Learning-to-Normalize via Switchable Normalization","date":"2018-06-28","arxiv_id":"1806.10779","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"a-comparison-of-transformer-and-recurrent","title":"A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation","date":"2018-06-18","arxiv_id":"1806.06957","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-lip-reading-a-comparison-of-models-and","title":"Deep Lip Reading: a comparison of models and an online application","date":"2018-06-15","arxiv_id":"1806.06053","n_code_links":0,"syntology":null},{"paper":"/paper/an-evaluation-of-neural-machine-translation","slug":"an-evaluation-of-neural-machine-translation","title":"An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization","date":"2018-06-13","arxiv_id":"1806.05210","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-end-to-end-speech-recognition","title":"Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages","date":"2018-06-12","arxiv_id":"1806.05059","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"n_code_links":13,"syntology":null},{"paper":null,"slug":"meta-learner-with-linear-nulling","title":"Meta-Learner with Linear Nulling","date":"2018-06-04","arxiv_id":"1806.01010","n_code_links":0,"syntology":null},{"paper":"/paper/deep-diffeomorphic-transformer-networks","slug":"deep-diffeomorphic-transformer-networks","title":"Deep Diffeomorphic Transformer Networks","date":"2018-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"weakly-supervised-phrase-localization-with","title":"Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network","date":"2018-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/theory-and-experiments-on-vector-quantized","slug":"theory-and-experiments-on-vector-quantized","title":"Theory and Experiments on Vector Quantized Autoencoders","date":"2018-05-28","arxiv_id":"1805.11063","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","n_code_links":0,"syntology":null},{"paper":"/paper/deep-neural-machine-translation-with-weakly","slug":"deep-neural-machine-translation-with-weakly","title":"Deep Neural Machine Translation with Weakly-Recurrent Units","date":"2018-05-10","arxiv_id":"1805.04185","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-data-driven-residential-transformer","title":"A Data-Driven Residential Transformer Overloading Risk Assessment Method","date":"2018-05-02","arxiv_id":"1805.00630","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-neural-transformer-via-an","slug":"accelerating-neural-transformer-via-an","title":"Accelerating Neural Transformer via an Average Attention Network","date":"2018-05-02","arxiv_id":"1805.00631","n_code_links":1,"syntology":{"ran":7,"of":19,"n_ran_checked":7,"n_instrument":0,"unverified":12,"pointer_only":0,"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) · 12 unverified","official":{"repos":["bzhangXMU/transformer-aan"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":12,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"localization-a-missing-link-in-the-pipeline","title":"Localization: A Missing Link in the Pipeline of Object Matching and Registration","date":"2018-05-01","arxiv_id":"1805.00223","n_code_links":0,"syntology":null},{"paper":null,"slug":"craft-complementary-recommendations-using","title":"CRAFT: Complementary Recommendations Using Adversarial Feature Transformer","date":"2018-04-29","arxiv_id":"1804.10871","n_code_links":0,"syntology":null},{"paper":null,"slug":"cram-clued-recurrent-attention-model","title":"CRAM: Clued Recurrent Attention Model","date":"2018-04-28","arxiv_id":"1804.10844","n_code_links":0,"syntology":null},{"paper":"/paper/syllable-based-sequence-to-sequence-speech","slug":"syllable-based-sequence-to-sequence-speech","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","date":"2018-04-28","arxiv_id":"1804.10752","n_code_links":1,"syntology":null},{"paper":"/paper/the-best-of-both-worlds-combining-recent","slug":"the-best-of-both-worlds-combining-recent","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","date":"2018-04-26","arxiv_id":"1804.09849","n_code_links":3,"syntology":null},{"paper":"/paper/convolutional-generative-adversarial-networks","slug":"convolutional-generative-adversarial-networks","title":"Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation","date":"2018-04-25","arxiv_id":"1804.09399","n_code_links":3,"syntology":{"ran":19,"of":35,"n_ran_checked":19,"n_instrument":0,"unverified":16,"pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified","official":{"repos":["salu133445/musegan"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":12,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformation-on-computer-generated-facial","title":"Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector","date":"2018-04-12","arxiv_id":"1804.04418","n_code_links":0,"syntology":null},{"paper":"/paper/adafactor-adaptive-learning-rates-with","slug":"adafactor-adaptive-learning-rates-with","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","date":"2018-04-11","arxiv_id":"1804.04235","n_code_links":5,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 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) · 0 unverified","official":null}},{"paper":null,"slug":"language-modeling-with-generative","title":"Language Modeling with Generative AdversarialNetworks","date":"2018-04-08","arxiv_id":"1804.02617","n_code_links":0,"syntology":null},{"paper":null,"slug":"statistical-transformer-networks-learning","title":"Statistical transformer networks: learning shape and appearance models via self supervision","date":"2018-04-07","arxiv_id":"1804.02541","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","n_code_links":1,"syntology":null},{"paper":"/paper/training-tips-for-the-transformer-model","slug":"training-tips-for-the-transformer-model","title":"Training Tips for the Transformer Model","date":"2018-04-01","arxiv_id":"1804.00247","n_code_links":4,"syntology":null},{"paper":null,"slug":"efficient-and-deep-person-re-identification","title":"Efficient and Deep Person Re-Identification using Multi-Level Similarity","date":"2018-03-30","arxiv_id":"1803.11353","n_code_links":0,"syntology":null},{"paper":"/paper/tensor2tensor-for-neural-machine-translation","slug":"tensor2tensor-for-neural-machine-translation","title":"Tensor2Tensor for Neural Machine Translation","date":"2018-03-16","arxiv_id":"1803.07416","n_code_links":15,"syntology":{"ran":30,"of":48,"n_ran_checked":29,"n_instrument":1,"unverified":18,"pointer_only":0,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 0 honoured, 0 violated, 29 with no contract checked; 1 where Syntology's instrument failed) · 18 unverified","official":{"repos":["tensorflow/tensor2tensor"],"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"]}}},{"paper":null,"slug":"studying-invariances-of-trained-convolutional","title":"Studying Invariances of Trained Convolutional Neural Networks","date":"2018-03-15","arxiv_id":"1803.05963","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-decoding-in-sequence-models-using","title":"Fast Decoding in Sequence Models using Discrete Latent Variables","date":"2018-03-09","arxiv_id":"1803.03382","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-with-relative-position","slug":"self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","arxiv_id":"1803.02155","n_code_links":13,"syntology":{"ran":13,"of":23,"n_ran_checked":8,"n_instrument":5,"unverified":10,"pointer_only":3,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/st-gan-spatial-transformer-generative","slug":"st-gan-spatial-transformer-generative","title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","date":"2018-03-05","arxiv_id":"1803.01837","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chenhsuanlin/spatial-transformer-GAN"],"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"]}}},{"paper":null,"slug":"classification-based-grasp-detection-using","title":"Classification based Grasp Detection using Spatial Transformer Network","date":"2018-03-04","arxiv_id":"1803.01356","n_code_links":0,"syntology":null},{"paper":"/paper/learning-longer-term-dependencies-in-rnns","slug":"learning-longer-term-dependencies-in-rnns","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","date":"2018-03-01","arxiv_id":"1803.00144","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-person-re-identification-by-temporal","title":"Video Person Re-identification by Temporal Residual Learning","date":"2018-02-22","arxiv_id":"1802.07918","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-spatial-transformer-network","title":"Hierarchical Spatial Transformer Network","date":"2018-01-29","arxiv_id":"1801.09467","n_code_links":0,"syntology":null},{"paper":null,"slug":"identity-preserving-face-recovery-from","title":"Identity-preserving Face Recovery from Portraits","date":"2018-01-08","arxiv_id":"1801.02279","n_code_links":0,"syntology":null},{"paper":"/paper/sockeye-a-toolkit-for-neural-machine","slug":"sockeye-a-toolkit-for-neural-machine","title":"Sockeye: A Toolkit for Neural Machine Translation","date":"2017-12-15","arxiv_id":"1712.05690","n_code_links":16,"syntology":null},{"paper":"/paper/see-towards-semi-supervised-end-to-end-scene","slug":"see-towards-semi-supervised-end-to-end-scene","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":"1712.05404","n_code_links":2,"syntology":null},{"paper":"/paper/see-towards-semi-supervisedend-to-end-scene","slug":"see-towards-semi-supervisedend-to-end-scene","title":"SEE: Towards Semi-SupervisedEnd-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-top-down-feature-transformer","title":"Controllable Top-down Feature Transformer","date":"2017-12-06","arxiv_id":"1712.02400","n_code_links":0,"syntology":null},{"paper":"/paper/distance-based-self-attention-network-for","slug":"distance-based-self-attention-network-for","title":"Distance-based Self-Attention Network for Natural Language Inference","date":"2017-12-06","arxiv_id":"1712.02047","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-fusion-and-machine-learning-integration","title":"Data Fusion and Machine Learning Integration for Transformer Loss of Life Estimation","date":"2017-11-08","arxiv_id":"1711.03398","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-label-image-recognition-by-recurrently","title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","date":"2017-11-08","arxiv_id":"1711.02816","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-neural-machine-translation-1","slug":"non-autoregressive-neural-machine-translation-1","title":"Non-Autoregressive Neural Machine Translation","date":"2017-11-07","arxiv_id":"1711.02281","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"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","official":{"repos":["salesforce/nonauto-nmt"],"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"]}}},{"paper":"/paper/weighted-transformer-network-for-machine","slug":"weighted-transformer-network-for-machine","title":"Weighted Transformer Network for Machine Translation","date":"2017-11-06","arxiv_id":"1711.02132","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"image-patch-matching-using-convolutional","title":"Image Patch Matching Using Convolutional Descriptors with Euclidean Distance","date":"2017-10-31","arxiv_id":"1710.11359","n_code_links":0,"syntology":null},{"paper":"/paper/learning-deep-context-aware-features-over","slug":"learning-deep-context-aware-features-over","title":"Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification","date":"2017-10-18","arxiv_id":"1710.06555","n_code_links":0,"syntology":null},{"paper":"/paper/simple-recurrent-units-for-highly","slug":"simple-recurrent-units-for-highly","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","date":"2017-09-08","arxiv_id":"1709.02755","n_code_links":11,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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","official":{"repos":["asappresearch/sru"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/polar-transformer-networks","slug":"polar-transformer-networks","title":"Polar Transformer Networks","date":"2017-09-06","arxiv_id":"1709.01889","n_code_links":1,"syntology":null},{"paper":"/paper/3d-morphable-models-as-spatial-transformer","slug":"3d-morphable-models-as-spatial-transformer","title":"3D Morphable Models as Spatial Transformer Networks","date":"2017-08-23","arxiv_id":"1708.07199","n_code_links":1,"syntology":null},{"paper":"/paper/unconstrained-fashion-landmark-detection-via","slug":"unconstrained-fashion-landmark-detection-via","title":"Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks","date":"2017-08-07","arxiv_id":"1708.02044","n_code_links":2,"syntology":null},{"paper":"/paper/stn-ocr-a-single-neural-network-for-text","slug":"stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","date":"2017-07-27","arxiv_id":"1707.08831","n_code_links":3,"syntology":null},{"paper":null,"slug":"ssemnet-serial-section-electron-microscopy","title":"ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features","date":"2017-07-25","arxiv_id":"1707.07833","n_code_links":0,"syntology":null},{"paper":"/paper/learning-transferable-architectures-for","slug":"learning-transferable-architectures-for","title":"Learning Transferable Architectures for Scalable Image Recognition","date":"2017-07-21","arxiv_id":"1707.07012","n_code_links":17,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"dynamic-layer-normalization-for-adaptive","title":"Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition","date":"2017-07-19","arxiv_id":"1707.06065","n_code_links":0,"syntology":null},{"paper":"/paper/a-deep-regression-architecture-with-two-stage","slug":"a-deep-regression-architecture-with-two-stage","title":"A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection","date":"2017-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/gans-trained-by-a-two-time-scale-update-rule","slug":"gans-trained-by-a-two-time-scale-update-rule","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","date":"2017-06-26","arxiv_id":"1706.08500","n_code_links":71,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["bioinf-jku/TTUR"],"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"]}}},{"paper":null,"slug":"rotational-rectification-network-enabling","title":"Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision","date":"2017-06-19","arxiv_id":"1706.08917","n_code_links":0,"syntology":null},{"paper":"/paper/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","n_code_links":595,"syntology":{"ran":610,"of":946,"n_ran_checked":529,"n_instrument":81,"unverified":336,"pointer_only":451,"phrase":"610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified","official":{"repos":["tensorflow/tensor2tensor"],"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"]}}},{"paper":null,"slug":"enriched-deep-recurrent-visual-attention","title":"Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition","date":"2017-06-12","arxiv_id":"1706.03581","n_code_links":0,"syntology":null},{"paper":"/paper/continual-learning-with-deep-generative","slug":"continual-learning-with-deep-generative","title":"Continual Learning with Deep Generative Replay","date":"2017-05-24","arxiv_id":"1705.08690","n_code_links":5,"syntology":null},{"paper":"/paper/improved-training-of-wasserstein-gans","slug":"improved-training-of-wasserstein-gans","title":"Improved Training of Wasserstein GANs","date":"2017-03-31","arxiv_id":"1704.00028","n_code_links":110,"syntology":{"ran":27,"of":49,"n_ran_checked":19,"n_instrument":8,"unverified":22,"pointer_only":20,"phrase":"27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","official":{"repos":["igul222/improved_wgan_training"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"normalizing-the-normalizers-comparing-and","title":"Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes","date":"2016-11-14","arxiv_id":"1611.04520","n_code_links":0,"syntology":null},{"paper":"/paper/layer-normalization","slug":"layer-normalization","title":"Layer Normalization","date":"2016-07-21","arxiv_id":"1607.06450","n_code_links":34,"syntology":{"ran":7,"of":17,"n_ran_checked":7,"n_instrument":0,"unverified":10,"pointer_only":8,"phrase":"7 ran (of which 5 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) · 10 unverified","official":null}}],"record_sha256":"b8fbd8a7995ae496c438c72c00bd9191a2110e24ea4c95c665bbe806eab61ea0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}