{"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/deep-attention","name":"Deep Attention","slug":"deep-attention","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":109,"papers_with_code":45,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/google-refexp","name":"Google Refexp","full_name":"","num_papers_in_archive":46},{"url":"/dataset/metu-viref-dataset","name":"METU-VIREF Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":109,"of_with_code":45,"tagged_in_all":109,"counts":{"archive_papers_tagged":109,"with_a_code_link":45,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":109,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"items":[{"url":"/paper/predator-registration-of-3d-point-clouds-with","slug":"predator-registration-of-3d-point-clouds-with","title":"PREDATOR: Registration of 3D Point Clouds with Low Overlap","date":"2020-11-25","arxiv_id":"2011.13005","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/predator-registration-of-3d-point-clouds-with#ran","syntology_url":"https://syntology.ai/paper/2011.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13005"}},"official":{"repos":["ShengyuH/OverlapPredator"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/weakly-supervised-segmentation-with-multi","slug":"weakly-supervised-segmentation-with-multi","title":"Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates","date":"2020-07-02","arxiv_id":"2007.01152","repositories_listed":3,"syntology":null},{"url":"/paper/deep-attention-recurrent-q-network","slug":"deep-attention-recurrent-q-network","title":"Deep Attention Recurrent Q-Network","date":"2015-12-05","arxiv_id":"1512.01693","repositories_listed":3,"syntology":null},{"url":"/paper/restoring-snow-degraded-single-images-with","slug":"restoring-snow-degraded-single-images-with","title":"Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer","date":"2023-09-11","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","repositories_listed":2,"syntology":null},{"url":"/paper/deep-multi-stations-weather-forecasting","slug":"deep-multi-stations-weather-forecasting","title":"Deep multi-stations weather forecasting: explainable recurrent convolutional neural networks","date":"2020-09-23","arxiv_id":"2009.11239","repositories_listed":2,"syntology":null},{"url":"/paper/deep-attention-aware-feature-learning-for","slug":"deep-attention-aware-feature-learning-for","title":"Deep Attention Aware Feature Learning for Person Re-Identification","date":"2020-03-01","arxiv_id":"2003.00517","repositories_listed":2,"syntology":null},{"url":"/paper/your-local-gan-designing-two-dimensional","slug":"your-local-gan-designing-two-dimensional","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","date":"2019-11-27","arxiv_id":"1911.12287","repositories_listed":2,"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/your-local-gan-designing-two-dimensional#ran","syntology_url":"https://syntology.ai/paper/1911.12287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12287"}},"official":{"repos":["giannisdaras/ylg"],"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/190503711","slug":"190503711","title":"Processing Megapixel Images with Deep Attention-Sampling Models","date":"2019-05-03","arxiv_id":"1905.03711","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/190503711#ran","syntology_url":"https://syntology.ai/paper/1905.03711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.03711"}},"official":{"repos":["idiap/attention-sampling"],"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/bayes-optimal-learning-of-attention-indexed","slug":"bayes-optimal-learning-of-attention-indexed","title":"Bayes optimal learning of attention-indexed models","date":"2025-06-02","arxiv_id":"2506.01582","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-collaborative-optimization-and","slug":"multi-modal-collaborative-optimization-and","title":"Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition","date":"2025-05-17","arxiv_id":"2505.12007","repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-framework-for-probabilistic-short","slug":"an-ensemble-framework-for-probabilistic-short","title":"An Ensemble Framework for Probabilistic Short-Term Load Forecasting Based on BiTCN and Deep Attention Networks","date":"2025-02-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fundamental-limits-of-learning-in-sequence","slug":"fundamental-limits-of-learning-in-sequence","title":"Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds","date":"2025-02-02","arxiv_id":"2502.00901","repositories_listed":1,"syntology":null},{"url":"/paper/sgformer-single-layer-graph-transformers-with","slug":"sgformer-single-layer-graph-transformers-with","title":"SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity","date":"2024-09-13","arxiv_id":"2409.09007","repositories_listed":1,"syntology":null},{"url":"/paper/allweathernet-unified-image-enhancement-for","slug":"allweathernet-unified-image-enhancement-for","title":"AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditions","date":"2024-09-03","arxiv_id":"2409.02045","repositories_listed":1,"syntology":null},{"url":"/paper/geometry-of-lightning-self-attention","slug":"geometry-of-lightning-self-attention","title":"Geometry of Lightning Self-Attention: Identifiability and Dimension","date":"2024-08-30","arxiv_id":"2408.17221","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-driven-reinforcement-learning","slug":"deep-attention-driven-reinforcement-learning","title":"Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment","date":"2024-07-12","arxiv_id":"2407.08932","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-q-network-for-personalized","slug":"deep-attention-q-network-for-personalized","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","date":"2023-07-04","arxiv_id":"2307.01519","repositories_listed":1,"syntology":null},{"url":"/paper/towards-deep-attention-in-graph-neural","slug":"towards-deep-attention-in-graph-neural","title":"Towards Deep Attention in Graph Neural Networks: Problems and Remedies","date":"2023-06-04","arxiv_id":"2306.02376","repositories_listed":1,"syntology":null},{"url":"/paper/aia-attention-in-attention-within-collaborate","slug":"aia-attention-in-attention-within-collaborate","title":"AIA: Attention in Attention Within Collaborate Domains","date":"2022-10-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/open-cykg-an-open-cyber-threat-intelligence","slug":"open-cykg-an-open-cyber-threat-intelligence","title":"Open-CyKG: An Open Cyber Threat Intelligence Knowledge Graph","date":"2021-12-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-guided-graph-clustering-with","slug":"deep-attention-guided-graph-clustering-with","title":"Deep Attention-guided Graph Clustering with Dual Self-supervision","date":"2021-11-10","arxiv_id":"2111.05548","repositories_listed":1,"syntology":null},{"url":"/paper/label-cleaning-multiple-instance-learning","slug":"label-cleaning-multiple-instance-learning","title":"Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images","date":"2021-09-22","arxiv_id":"2109.10778","repositories_listed":1,"syntology":null},{"url":"/paper/hit-a-hierarchically-fused-deep-attention-1","slug":"hit-a-hierarchically-fused-deep-attention-1","title":"HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/thermal-image-super-resolution-using-second","slug":"thermal-image-super-resolution-using-second","title":"Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive Fields","date":"2021-07-30","arxiv_id":"2108.00094","repositories_listed":1,"syntology":null},{"url":"/paper/grid-partitioned-attention-efficient","slug":"grid-partitioned-attention-efficient","title":"Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation","date":"2021-07-08","arxiv_id":"2107.03742","repositories_listed":1,"syntology":null},{"url":"/paper/hit-a-hierarchically-fused-deep-attention","slug":"hit-a-hierarchically-fused-deep-attention","title":"HIT: A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation","date":"2021-05-30","arxiv_id":"2105.14600","repositories_listed":1,"syntology":null},{"url":"/paper/lipschitz-normalization-for-self-attention","slug":"lipschitz-normalization-for-self-attention","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","date":"2021-03-08","arxiv_id":"2103.04886","repositories_listed":1,"syntology":null},{"url":"/paper/hard-attention-for-scalable-image","slug":"hard-attention-for-scalable-image","title":"Hard-Attention for Scalable Image Classification","date":"2021-02-20","arxiv_id":"2102.10212","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-prostate-cancer-detection-in-bpmri","slug":"end-to-end-prostate-cancer-detection-in-bpmri","title":"End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction","date":"2021-01-08","arxiv_id":"2101.03244","repositories_listed":1,"syntology":null},{"url":"/paper/whole-slide-images-based-cancer-survival","slug":"whole-slide-images-based-cancer-survival","title":"Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks","date":"2020-09-23","arxiv_id":"2009.11169","repositories_listed":1,"syntology":null},{"url":"/paper/weight-excitation-built-in-attention","slug":"weight-excitation-built-in-attention","title":"Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/do-transformers-need-deep-long-range-memory-1","slug":"do-transformers-need-deep-long-range-memory-1","title":"Do Transformers Need Deep Long-Range Memory","date":"2020-07-07","arxiv_id":"2007.03356","repositories_listed":1,"syntology":null},{"url":"/paper/infinite-attention-nngp-and-ntk-for-deep","slug":"infinite-attention-nngp-and-ntk-for-deep","title":"Infinite attention: NNGP and NTK for deep attention networks","date":"2020-06-18","arxiv_id":"2006.10540","repositories_listed":1,"syntology":null},{"url":"/paper/image-search-with-text-feedback-by","slug":"image-search-with-text-feedback-by","title":"Image Search With Text Feedback by Visiolinguistic Attention Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-attended-visual-targets-in-video","slug":"detecting-attended-visual-targets-in-video","title":"Detecting Attended Visual Targets in Video","date":"2020-03-05","arxiv_id":"2003.02501","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/detecting-attended-visual-targets-in-video#ran","syntology_url":"https://syntology.ai/paper/2003.02501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02501"}},"official":null}},{"url":"/paper/deep-attention-based-semi-supervised-2d-pose","slug":"deep-attention-based-semi-supervised-2d-pose","title":"Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments","date":"2019-12-10","arxiv_id":"1912.04618","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-networks-reveal-the-rules-of","slug":"deep-attention-networks-reveal-the-rules-of","title":"Deep attention networks reveal the rules of collective motion in zebrafish","date":"2019-09-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pdanet-polarity-consistent-deep-attention","slug":"pdanet-polarity-consistent-deep-attention","title":"PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression","date":"2019-09-11","arxiv_id":"1909.05693","repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-ambiguous-objects-in-videos","slug":"searching-for-ambiguous-objects-in-videos","title":"Searching for Ambiguous Objects in Videos using Relational Referring Expressions","date":"2019-08-03","arxiv_id":"1908.01189","repositories_listed":1,"syntology":null},{"url":"/paper/compact-global-descriptor-for-neural-networks","slug":"compact-global-descriptor-for-neural-networks","title":"Compact Global Descriptor for Neural Networks","date":"2019-07-23","arxiv_id":"1907.09665","repositories_listed":1,"syntology":null},{"url":"/paper/dan-deep-attention-neural-network-for-news","slug":"dan-deep-attention-neural-network-for-news","title":"Dan: Deep attention neural network for news recommendation","date":"2019-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-scale-guided-attention-for-medical","slug":"multi-scale-guided-attention-for-medical","title":"Multi-scale self-guided attention for medical image segmentation","date":"2019-06-07","arxiv_id":"1906.02849","repositories_listed":1,"syntology":null},{"url":"/paper/ra-unet-a-hybrid-deep-attention-aware-network","slug":"ra-unet-a-hybrid-deep-attention-aware-network","title":"RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans","date":"2018-11-04","arxiv_id":"1811.01328","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-based-classification-network","slug":"deep-attention-based-classification-network","title":"Deep attention-based classification network for robust depth prediction","date":"2018-07-11","arxiv_id":"1807.03959","repositories_listed":1,"syntology":null},{"url":null,"slug":"neuropapyri-a-deep-attention-embedding","title":"NeuroPapyri: A Deep Attention Embedding Network for Handwritten Papyri Retrieval","date":"2024-08-14","arxiv_id":"2408.07785","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-deep-attention-recurrent","title":"Uncertainty-Aware Deep Attention Recurrent Neural Network for Heterogeneous Time Series Imputation","date":"2024-01-04","arxiv_id":"2401.02258","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-riemannian-geometric-features","title":"Learning with Geometry: Including Riemannian Geometric Features in Coefficient of Pressure Prediction on Aircraft Wings","date":"2023-12-22","arxiv_id":"2401.09452","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-shaped-transformer-attention-models-in","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","date":"2023-06-30","arxiv_id":"2306.17759","repositories_listed":0,"syntology":null},{"url":null,"slug":"between-sample-relationship-in-learning","title":"Between-Sample Relationship in Learning Tabular Data Using Graph and Attention Networks","date":"2023-06-11","arxiv_id":"2306.06772","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsity-and-coefficient-permutation-based","title":"Sparsity and Coefficient Permutation Based Two-Domain AMP for Image Block Compressed Sensing","date":"2023-05-22","arxiv_id":"2305.12986","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-diaphragm-excursion-prediction-deep","title":"Speaker Diaphragm Excursion Prediction: deep attention and online adaptation","date":"2023-05-11","arxiv_id":"2305.06640","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-unet-a-network-model-with","title":"Deep Attention Unet: A Network Model with Global Feature Perception Ability","date":"2023-04-21","arxiv_id":"2304.10829","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-network-for-enhanced-hand","title":"Deep Attention Network for Enhanced Hand Gesture Recognition System","date":"2023-04-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"relate-auditory-speech-to-eeg-by-shallow-deep","title":"Relate auditory speech to EEG by shallow-deep attention-based network","date":"2023-03-20","arxiv_id":"2303.10897","repositories_listed":0,"syntology":null},{"url":null,"slug":"localeyenet-deep-attention-framework-for","title":"LocalEyenet: Deep Attention framework for Localization of Eyes","date":"2023-03-13","arxiv_id":"2303.12728","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-recognition-for-attack","title":"Deep Attention Recognition for Attack Identification in 5G UAV scenarios: Novel Architecture and End-to-End Evaluation","date":"2023-03-03","arxiv_id":"2303.12947","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-based-alignment-network-for","title":"Deep Attention-Based Alignment Network for Melody Generation from Incomplete Lyrics","date":"2023-01-23","arxiv_id":"2301.10015","repositories_listed":0,"syntology":null},{"url":null,"slug":"prostattention-net-a-deep-attention-model-for","title":"ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans","date":"2022-11-23","arxiv_id":"2211.13238","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-attention-weights-as-explanations","title":"Revisiting Attention Weights as Explanations from an Information Theoretic Perspective","date":"2022-10-31","arxiv_id":"2211.07714","repositories_listed":0,"syntology":null},{"url":null,"slug":"atttrack-online-deep-attention-transfer-for","title":"AttTrack: Online Deep Attention Transfer for Multi-object Tracking","date":"2022-10-16","arxiv_id":"2210.08648","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzy-attention-neural-network-to-tackle","title":"Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation","date":"2022-09-05","arxiv_id":"2209.02048","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-and-lightweight-deep-attention","title":"A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations","date":"2022-05-31","arxiv_id":"2206.00455","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-attention-methods-in-deep-learning-an","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","date":"2022-04-16","arxiv_id":"2204.07756","repositories_listed":0,"syntology":null},{"url":null,"slug":"webformer-the-web-page-transformer-for","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","date":"2022-02-01","arxiv_id":"2202.00217","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-based-supernovae","title":"Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves","date":"2022-01-20","arxiv_id":"2201.08482","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-diffusion-graph-neural","title":"Deep Attention Diffusion Graph Neural Networks for Text Classification","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-data-augmentation-and-deep-attention","title":"Hybrid Data Augmentation and Deep Attention-based Dilated Convolutional-Recurrent Neural Networks for Speech Emotion Recognition","date":"2021-09-18","arxiv_id":"2109.09026","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-models-improve-radiomics-1","title":"Generative Models Improve Radiomics Performance in Different Tasks and Different Datasets: An Experimental Study","date":"2021-09-06","arxiv_id":"2109.02252","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-recurrent-semi-supervised-eeg","title":"Deep Recurrent Semi-Supervised EEG Representation Learning for Emotion Recognition","date":"2021-07-28","arxiv_id":"2107.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-are-deep-infinite-dimensional-1","title":"Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines","date":"2021-06-02","arxiv_id":"2106.01506","repositories_listed":0,"syntology":null},{"url":null,"slug":"lung-cancer-diagnosis-using-deep-attention","title":"Lung Cancer Diagnosis Using Deep Attention Based on Multiple Instance Learning and Radiomics","date":"2021-04-29","arxiv_id":"2104.14655","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-ehr-spotlight-a-framework-and-mechanism","title":"Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions","date":"2021-03-25","arxiv_id":"2103.14161","repositories_listed":0,"syntology":null},{"url":null,"slug":"da2-deep-attention-adapter-for-memory","title":"$DA^3$:Dynamic Additive Attention Adaption for Memory-EfficientOn-Device Multi-Domain Learning","date":"2020-12-02","arxiv_id":"2012.01362","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-mechanism-transformers-bert-and-gpt","title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","date":"2020-11-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dualnet-locate-then-detect-effective-payload","title":"DualNet: Locate Then Detect Effective Payload with Deep Attention Network","date":"2020-10-23","arxiv_id":"2010.12171","repositories_listed":0,"syntology":null},{"url":null,"slug":"microscopic-fine-grained-instance","title":"Microscopic fine-grained instance classification through deep attention","date":"2020-10-06","arxiv_id":"2010.02818","repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-duo-tou-zhu-yi-li-he-bilstmgai-jin","title":"基于多头注意力和BiLSTM改进DAM模型的中文问答匹配方法(Chinese question answering method based on multi-head attention and BiLSTM improved DAM model)","date":"2020-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-flows-analyzing-and-comparing","title":"Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models","date":"2020-09-03","arxiv_id":"2009.07053","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-imitator-handwriting-calligraphy","title":"Deep imitator: Handwriting calligraphy imitation via deep attention networks","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"do-transformers-need-deep-long-range-memory","title":"Do Transformers Need Deep Long-Range Memory?","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ying-yong-duo-mo-shi-te-zheng-rong-he-de-shen","title":"應用多模式特徵融合的深度注意力網路進行謠言檢測 (Rumor Detection Using Deep Attention Networks With Multimodal Feature Fusion)","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-fusion-feature-for-speech","title":"Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method","date":"2020-03-17","arxiv_id":"2003.07544","repositories_listed":0,"syntology":null},{"url":null,"slug":"da4ad-end-to-end-deep-attention-aware","title":"DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving","date":"2020-03-06","arxiv_id":"2003.03026","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-spatio-temporal-point","title":"Deep Fourier Kernel for Self-Attentive Point Processes","date":"2020-02-17","arxiv_id":"2002.07281","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-and-spectral-deep-attention-fusion","title":"Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features","date":"2020-02-05","arxiv_id":"2002.01626","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-reinforcement-learning-with-deep","title":"Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks","date":"2020-01-02","arxiv_id":"2001.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-hand-movements-from-eeg","title":"Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network","date":"2019-08-06","arxiv_id":"1908.02252","repositories_listed":0,"syntology":null},{"url":null,"slug":"aiai-at-finsbd-task-sentence-boundary","title":"aiai at FinSBD task: Sentence Boundary Detection in Noisy Texts From Financial Documents Using Deep Attention Model","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alphastock-a-buying-winners-and-selling","title":"AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks","date":"2019-07-24","arxiv_id":"1908.02646","repositories_listed":0,"syntology":null},{"url":null,"slug":"microsoft-ai-challenge-india-2018-learning-to","title":"Microsoft AI Challenge India 2018: Learning to Rank Passages for Web Question Answering with Deep Attention Networks","date":"2019-06-14","arxiv_id":"1906.06056","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-shared-encoding-representation-for","title":"Learning Shared Encoding Representation for End-to-End Speech Recognition Models","date":"2019-03-31","arxiv_id":"1904.02147","repositories_listed":0,"syntology":null},{"url":null,"slug":"vmav-c-a-deep-attention-based-reinforcement","title":"VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm for Model-based Control","date":"2018-12-24","arxiv_id":"1812.09968","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-anomaly-detection-in-energy-time","title":"Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention","date":"2018-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantically-aware-attentive-neural","title":"Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization","date":"2018-12-08","arxiv_id":"1812.03402","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-guided-hashing","title":"Deep Attention-guided Hashing","date":"2018-12-04","arxiv_id":"1812.01404","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-attention-on-the-sun-what-do-existing","title":"Visual Attention on the Sun: What Do Existing Models Actually Predict?","date":"2018-11-25","arxiv_id":"1811.10004","repositories_listed":0,"syntology":null},{"url":null,"slug":"patient-risk-assessment-and-warning-symptom","title":"Patient Risk Assessment and Warning Symptom Detection Using Deep Attention-Based Neural Networks","date":"2018-09-28","arxiv_id":"1809.10804","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-neural-tensor-network-for","title":"Deep Attention Neural Tensor Network for Visual Question Answering","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attention-guided-fusion-network-for","title":"Deep attention-guided fusion network for lesion segmentation","date":"2018-07-23","arxiv_id":"1807.08471","repositories_listed":0,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/deep-attention/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/deep-attention/papers/2","json":"/task/deep-attention/papers/2.json","rows":9},{"order":"ran","page":1,"of":1,"url":"/task/deep-attention/papers/ran/1","json":"/task/deep-attention/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"0165b5500f0ad3be96456392f6dfb6616b381b25746b974d3f9398356ecfac69","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}