{"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/swin-transformer/papers/2","list_of":"/method/swin-transformer","method":"Swin Transformer","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":2,"pages_in_order":5,"rows_per_page":100,"rows":[101,200],"of":416,"counts":{"archive_papers_tagged":416,"with_a_code_link":207,"where_syntology_ran_a_sample":58,"not_listed_spam_title":0,"listed":416,"listed_where_code_ran":58,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":50,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":50,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/swin-transformer","prev":"/method/swin-transformer","next":"/method/swin-transformer/papers/3","papers":[{"paper":"/paper/image-to-latex-converter-for-mathematical","slug":"image-to-latex-converter-for-mathematical","title":"Image-to-LaTeX Converter for Mathematical Formulas and Text","date":"2024-08-07","arxiv_id":"2408.04015","n_code_links":1,"syntology":null},{"paper":"/paper/swinshadow-shifted-window-for-ambiguous","slug":"swinshadow-shifted-window-for-ambiguous","title":"SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection","date":"2024-08-07","arxiv_id":"2408.03521","n_code_links":1,"syntology":null},{"paper":"/paper/2408-01031","slug":"2408-01031","title":"POA: Pre-training Once for Models of All Sizes","date":"2024-08-02","arxiv_id":"2408.01031","n_code_links":1,"syntology":null},{"paper":null,"slug":"2407-21507","title":"FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication","date":"2024-07-31","arxiv_id":"2407.21507","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-successive-refinement-a-generative","title":"Semantic Successive Refinement: A Generative AI-aided Semantic Communication Framework","date":"2024-07-31","arxiv_id":"2408.05112","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-generalized-recaptured-screen-image","title":"Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer","date":"2024-07-24","arxiv_id":"2407.17170","n_code_links":0,"syntology":null},{"paper":"/paper/improving-representation-of-high-frequency","slug":"improving-representation-of-high-frequency","title":"Improving Representation of High-frequency Components for Medical Visual Foundation Models","date":"2024-07-19","arxiv_id":"2407.14651","n_code_links":1,"syntology":{"ran":15,"of":17,"n_ran_checked":13,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Arturia-Pendragon-Iris/Frepa"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-er-reconstruction-of-imaging-cherenkov","slug":"deep-er-reconstruction-of-imaging-cherenkov","title":"Deep(er) Reconstruction of Imaging Cherenkov Detectors with Swin Transformers and Normalizing Flow Models","date":"2024-07-10","arxiv_id":"2407.07376","n_code_links":1,"syntology":null},{"paper":"/paper/cross-modal-spherical-aggregation-for-weakly","slug":"cross-modal-spherical-aggregation-for-weakly","title":"Cross-Modal Spherical Aggregation for Weakly Supervised Remote Sensing Shadow Removal","date":"2024-06-25","arxiv_id":"2406.17469","n_code_links":1,"syntology":null},{"paper":"/paper/sum-saliency-unification-through-mamba-for","slug":"sum-saliency-unification-through-mamba-for","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","date":"2024-06-25","arxiv_id":"2406.17815","n_code_links":1,"syntology":{"ran":14,"of":14,"n_ran_checked":14,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Arhosseini77/SUM"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unambiguous-recognition-should-not-rely","slug":"unambiguous-recognition-should-not-rely","title":"MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data","date":"2024-06-24","arxiv_id":"2406.17148","n_code_links":1,"syntology":null},{"paper":null,"slug":"swinstyleformer-is-a-favorable-choice-for","title":"SwinStyleformer is a favorable choice for image inversion","date":"2024-06-19","arxiv_id":"2406.13153","n_code_links":0,"syntology":null},{"paper":"/paper/diffusion-based-adaptation-for-classification","slug":"diffusion-based-adaptation-for-classification","title":"Diffusion-Based Adaptation for Classification of Unknown Degraded Images","date":"2024-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/q-mamba-on-first-exploration-of-vision-mamba","slug":"q-mamba-on-first-exploration-of-vision-mamba","title":"QMamba: On First Exploration of Vision Mamba for Image Quality Assessment","date":"2024-06-13","arxiv_id":"2406.09546","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-robust-pipeline-for-classification-and","title":"A Robust Pipeline for Classification and Detection of Bleeding Frames in Wireless Capsule Endoscopy using Swin Transformer and RT-DETR","date":"2024-06-12","arxiv_id":"2406.08046","n_code_links":0,"syntology":null},{"paper":"/paper/superformer-volumetric-transformer","slug":"superformer-volumetric-transformer","title":"SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution","date":"2024-06-05","arxiv_id":"2406.03359","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-image-semantic-coding-with-learnable","title":"Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channels","date":"2024-05-30","arxiv_id":"2406.07389","n_code_links":0,"syntology":null},{"paper":null,"slug":"yotor-you-only-transform-one-representation","title":"YotoR-You Only Transform One Representation","date":"2024-05-30","arxiv_id":"2405.19629","n_code_links":0,"syntology":null},{"paper":"/paper/mds-vitnet-improving-saliency-prediction-for","slug":"mds-vitnet-improving-saliency-prediction-for","title":"MDS-ViTNet: Improving saliency prediction for Eye-Tracking with Vision Transformer","date":"2024-05-29","arxiv_id":"2405.19501","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-modality-agnostic-pre","slug":"self-supervised-modality-agnostic-pre","title":"Self-Supervised Modality-Agnostic Pre-Training of Swin Transformers","date":"2024-05-21","arxiv_id":"2405.12781","n_code_links":1,"syntology":null},{"paper":null,"slug":"ground-based-image-deconvolution-with-swin","title":"Ground-based image deconvolution with Swin Transformer UNet","date":"2024-05-13","arxiv_id":"2405.07842","n_code_links":0,"syntology":null},{"paper":null,"slug":"super-resolving-blurry-images-with-events","title":"Super-Resolving Blurry Images with Events","date":"2024-05-11","arxiv_id":"2405.06918","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatio-temporal-swinmae-a-swin-transformer","title":"SatSwinMAE: Efficient Autoencoding for Multiscale Time-series Satellite Imagery","date":"2024-05-03","arxiv_id":"2405.02512","n_code_links":0,"syntology":null},{"paper":null,"slug":"technical-report-on-target-classification-in","title":"Technical report on target classification in SAR track","date":"2024-05-03","arxiv_id":"2405.02361","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-fusion-across-disjoint-samples","title":"Transformers Fusion across Disjoint Samples for Hyperspectral Image Classification","date":"2024-05-02","arxiv_id":"2405.01095","n_code_links":0,"syntology":null},{"paper":null,"slug":"stridenet-swin-transformer-for-terrain","title":"StrideNET: Swin Transformer for Terrain Recognition with Dynamic Roughness Extraction","date":"2024-04-20","arxiv_id":"2404.13270","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-ferrous-scrap-material","title":"Towards Robust Ferrous Scrap Material Classification with Deep Learning and Conformal Prediction","date":"2024-04-19","arxiv_id":"2404.13002","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-and-llm-based-methods-applied","slug":"deep-learning-and-llm-based-methods-applied","title":"Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification","date":"2024-04-16","arxiv_id":"2404.10757","n_code_links":1,"syntology":null},{"paper":null,"slug":"odformer-semantic-fundus-image-segmentation","title":"ODFormer: Semantic Fundus Image Segmentation Using Transformer for Optic Nerve Head Detection","date":"2024-04-15","arxiv_id":"2405.09552","n_code_links":0,"syntology":null},{"paper":null,"slug":"heat-head-level-parameter-efficient","title":"Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness across Diverse Tasks","date":"2024-04-13","arxiv_id":"2404.08894","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalability-in-building-component-data","title":"Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data","date":"2024-04-12","arxiv_id":"2404.08557","n_code_links":0,"syntology":null},{"paper":null,"slug":"post-hurricane-building-damage-assessment","title":"Post-hurricane building damage assessment using street-view imagery and structured data: A multi-modal deep learning approach","date":"2024-04-11","arxiv_id":"2404.07399","n_code_links":0,"syntology":null},{"paper":"/paper/nerf-mae-masked-autoencoders-for-self","slug":"nerf-mae-masked-autoencoders-for-self","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","date":"2024-04-01","arxiv_id":"2404.01300","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zubair-irshad/NeRF-MAE"],"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"]}}},{"paper":"/paper/densenets-reloaded-paradigm-shift-beyond","slug":"densenets-reloaded-paradigm-shift-beyond","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","date":"2024-03-28","arxiv_id":"2403.19588","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huggingface/pytorch-image-models","naver-ai/rdnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/residual-dense-swin-transformer-for","slug":"residual-dense-swin-transformer-for","title":"Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging","date":"2024-03-25","arxiv_id":"2403.16384","n_code_links":1,"syntology":null},{"paper":null,"slug":"parformer-vision-transformer-baseline-with","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","date":"2024-03-22","arxiv_id":"2403.15004","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-confidence-pseudo-labels-for-domain","title":"High-confidence pseudo-labels for domain adaptation in COVID-19 detection","date":"2024-03-20","arxiv_id":"2403.13509","n_code_links":0,"syntology":null},{"paper":"/paper/attention-enhanced-hybrid-feature-aggregation","slug":"attention-enhanced-hybrid-feature-aggregation","title":"Attention-Enhanced Hybrid Feature Aggregation Network for 3D Brain Tumor Segmentation","date":"2024-03-15","arxiv_id":"2403.09942","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-spatio-temporal-aligned-sunet-model-for-low","title":"A Spatio-temporal Aligned SUNet Model for Low-light Video Enhancement","date":"2024-03-04","arxiv_id":"2403.02408","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-retinal-vascular-structure","slug":"enhancing-retinal-vascular-structure","title":"Enhancing Retinal Vascular Structure Segmentation in Images With a Novel Design Two-Path Interactive Fusion Module Model","date":"2024-03-03","arxiv_id":"2403.01362","n_code_links":1,"syntology":null},{"paper":"/paper/automated-segmentation-of-lesions-and-organs","slug":"automated-segmentation-of-lesions-and-organs","title":"Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR","date":"2024-02-29","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/befunet-a-hybrid-cnn-transformer-architecture","slug":"befunet-a-hybrid-cnn-transformer-architecture","title":"BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation","date":"2024-02-13","arxiv_id":"2402.08793","n_code_links":1,"syntology":null},{"paper":null,"slug":"faster-inference-of-integer-swin-transformer","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","date":"2024-02-02","arxiv_id":"2402.01169","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-swin-transformer-for-local-to","slug":"leveraging-swin-transformer-for-local-to","title":"Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation","date":"2024-01-31","arxiv_id":"2401.17828","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-method-for-vehicle-logo-recognition","title":"A New Method for Vehicle Logo Recognition Based on Swin Transformer","date":"2024-01-27","arxiv_id":"2401.15458","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-augmentation-training-makes","slug":"adversarial-augmentation-training-makes","title":"Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts","date":"2024-01-21","arxiv_id":"2401.11406","n_code_links":1,"syntology":null},{"paper":null,"slug":"lrp-qvit-mixed-precision-vision-transformer","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","date":"2024-01-20","arxiv_id":"2401.11243","n_code_links":0,"syntology":null},{"paper":"/paper/trapped-in-texture-bias-a-large-scale","slug":"trapped-in-texture-bias-a-large-scale","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","date":"2024-01-17","arxiv_id":"2401.09109","n_code_links":1,"syntology":null},{"paper":null,"slug":"b-cos-aligned-transformers-learn-human","title":"B-Cos Aligned Transformers Learn Human-Interpretable Features","date":"2024-01-16","arxiv_id":"2401.08868","n_code_links":0,"syntology":null},{"paper":null,"slug":"importance-aware-image-segmentation-based","title":"Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving","date":"2024-01-16","arxiv_id":"2401.10153","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-quality-assessment-based-on-swin","title":"Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy","date":"2024-01-16","arxiv_id":"2401.08522","n_code_links":0,"syntology":null},{"paper":null,"slug":"dedustnet-a-frequency-dominated-swin","title":"DedustNet: A Frequency-dominated Swin Transformer-based Wavelet Network for Agricultural Dust Removal","date":"2024-01-09","arxiv_id":"2401.04750","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-method-to-enhance-pneumonia-detection","title":"A novel method to enhance pneumonia detection via a model-level ensembling of CNN and vision transformer","date":"2024-01-04","arxiv_id":"2401.02358","n_code_links":0,"syntology":null},{"paper":"/paper/moc-rvq-multilevel-codebook-assisted-digital","slug":"moc-rvq-multilevel-codebook-assisted-digital","title":"MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication","date":"2024-01-02","arxiv_id":"2401.01272","n_code_links":1,"syntology":null},{"paper":null,"slug":"parameternet-parameters-are-all-you-need-for-1","title":"ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"image-super-resolution-reconstruction-network","title":"Image Super-resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features","date":"2023-12-30","arxiv_id":"2401.00241","n_code_links":0,"syntology":null},{"paper":"/paper/c2t-net-channel-aware-cross-fused-transformer","slug":"c2t-net-channel-aware-cross-fused-transformer","title":"C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition","date":"2023-12-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/scunet-assessment-of-pulmonary-embolism-ct","slug":"scunet-assessment-of-pulmonary-embolism-ct","title":"SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation","date":"2023-12-22","arxiv_id":"2312.14705","n_code_links":1,"syntology":null},{"paper":null,"slug":"tptnet-a-data-driven-temperature-prediction","title":"TPTNet: A Data-Driven Temperature Prediction Model Based on Turbulent Potential Temperature","date":"2023-12-22","arxiv_id":"2312.14980","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-multilingual-natural-scene-text","title":"Research on Multilingual Natural Scene Text Detection Algorithm","date":"2023-12-18","arxiv_id":"2312.11153","n_code_links":0,"syntology":null},{"paper":"/paper/factorization-vision-transformer-modeling","slug":"factorization-vision-transformer-modeling","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","date":"2023-12-14","arxiv_id":"2312.08614","n_code_links":1,"syntology":null},{"paper":"/paper/polyper-boundary-sensitive-polyp-segmentation","slug":"polyper-boundary-sensitive-polyp-segmentation","title":"Polyper: Boundary Sensitive Polyp Segmentation","date":"2023-12-14","arxiv_id":"2312.08735","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-anomaly-detection-for-lane","title":"Intelligent Anomaly Detection for Lane Rendering Using Transformer with Self-Supervised Pre-Training and Customized Fine-Tuning","date":"2023-12-07","arxiv_id":"2312.04398","n_code_links":0,"syntology":null},{"paper":"/paper/self-training-solutions-for-the-iccv-2023","slug":"self-training-solutions-for-the-iccv-2023","title":"Self-training solutions for the ICCV 2023 GeoNet Challenge","date":"2023-11-28","arxiv_id":"2311.16843","n_code_links":1,"syntology":null},{"paper":null,"slug":"eafp-med-an-efficient-adaptive-feature","title":"EAFP-Med: An Efficient Adaptive Feature Processing Module Based on Prompts for Medical Image Detection","date":"2023-11-27","arxiv_id":"2311.15540","n_code_links":0,"syntology":null},{"paper":null,"slug":"progressive-learning-with-visual-prompt","title":"Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression","date":"2023-11-23","arxiv_id":"2311.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"benthiq-a-transformer-based-benthic","title":"BenthIQ: a Transformer-Based Benthic Classification Model for Coral Restoration","date":"2023-11-22","arxiv_id":"2311.13661","n_code_links":0,"syntology":null},{"paper":"/paper/importance-of-feature-extraction-in-the","slug":"importance-of-feature-extraction-in-the","title":"Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend","date":"2023-11-22","arxiv_id":"2311.13717","n_code_links":2,"syntology":null},{"paper":null,"slug":"pmp-swin-multi-scale-patch-message-passing","title":"PMP-Swin: Multi-Scale Patch Message Passing Swin Transformer for Retinal Disease Classification","date":"2023-11-20","arxiv_id":"2311.11669","n_code_links":0,"syntology":null},{"paper":null,"slug":"inspecting-explainability-of-transformer","title":"Inspecting Explainability of Transformer Models with Additional Statistical Information","date":"2023-11-19","arxiv_id":"2311.11378","n_code_links":0,"syntology":null},{"paper":"/paper/wildfire-smoke-detection-with-cross-contrast","slug":"wildfire-smoke-detection-with-cross-contrast","title":"Wildfire Smoke Detection with Cross Contrast Patch Embedding","date":"2023-11-16","arxiv_id":"2311.10116","n_code_links":1,"syntology":null},{"paper":null,"slug":"two-stream-scene-understanding-on-graph","title":"Two Stream Scene Understanding on Graph Embedding","date":"2023-11-12","arxiv_id":"2311.06746","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-knowledge-from-cnn-transformer","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","date":"2023-11-02","arxiv_id":"2311.01283","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-visual-cues-in-the-intensive-care","title":"Detecting Visual Cues in the Intensive Care Unit and Association with Patient Clinical Status","date":"2023-11-01","arxiv_id":"2311.00565","n_code_links":0,"syntology":null},{"paper":null,"slug":"faultseg-swin-unetr-transformer-based-self","title":"FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition","date":"2023-10-27","arxiv_id":"2310.17974","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-transformer-using-cross-channel","slug":"multimodal-transformer-using-cross-channel","title":"Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Images","date":"2023-10-21","arxiv_id":"2310.13876","n_code_links":1,"syntology":null},{"paper":null,"slug":"auxiliary-features-guided-super-resolution","title":"Auxiliary Features-Guided Super Resolution for Monte Carlo Rendering","date":"2023-10-20","arxiv_id":"2310.13235","n_code_links":0,"syntology":null},{"paper":null,"slug":"diar-deep-image-alignment-and-reconstruction","title":"DIAR: Deep Image Alignment and Reconstruction using Swin Transformers","date":"2023-10-17","arxiv_id":"2310.11605","n_code_links":0,"syntology":null},{"paper":null,"slug":"mask-wearing-object-detection-algorithm-based","title":"Mask wearing object detection algorithm based on improved YOLOv5","date":"2023-10-16","arxiv_id":"2310.10245","n_code_links":0,"syntology":null},{"paper":"/paper/covid-19-detection-using-swin-transformer","slug":"covid-19-detection-using-swin-transformer","title":"COVID-19 detection using ViT transformer-based approach from Computed Tomography Images","date":"2023-10-12","arxiv_id":"2310.08165","n_code_links":1,"syntology":null},{"paper":null,"slug":"selective-feature-adapter-for-dense-vision","title":"Selective Feature Adapter for Dense Vision Transformers","date":"2023-10-03","arxiv_id":"2310.01843","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-distilled-masked-attention-guided-masked","title":"Self-distilled Masked Attention guided masked image modeling with noise Regularized Teacher (SMART) for medical image analysis","date":"2023-10-02","arxiv_id":"2310.01209","n_code_links":0,"syntology":null},{"paper":"/paper/egocentric-rgb-depth-action-recognition-in","slug":"egocentric-rgb-depth-action-recognition-in","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","date":"2023-09-25","arxiv_id":"2309.13962","n_code_links":1,"syntology":null},{"paper":null,"slug":"osnet-mneto-two-types-of-general","title":"OSNet & MNetO: Two Types of General Reconstruction Architectures for Linear Computed Tomography in Multi-Scenarios","date":"2023-09-21","arxiv_id":"2309.11858","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-dynamic-mri-reconstruction-with","title":"Learning Dynamic MRI Reconstruction with Convolutional Network Assisted Reconstruction Swin Transformer","date":"2023-09-19","arxiv_id":"2309.10227","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-network-based-coronary-dominance","title":"Neural network-based coronary dominance classification of RCA angiograms","date":"2023-09-13","arxiv_id":"2309.06958","n_code_links":0,"syntology":null},{"paper":null,"slug":"ms-unet-v2-adaptive-denoising-method-and","title":"MS-UNet-v2: Adaptive Denoising Method and Training Strategy for Medical Image Segmentation with Small Training Data","date":"2023-09-07","arxiv_id":"2309.03686","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-diagnosis-and-prognosis-of-lung","title":"Improving diagnosis and prognosis of lung cancer using vision transformers: A scoping review","date":"2023-09-06","arxiv_id":"2309.02783","n_code_links":0,"syntology":null},{"paper":"/paper/dat-spatially-dynamic-vision-transformer-with","slug":"dat-spatially-dynamic-vision-transformer-with","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","date":"2023-09-04","arxiv_id":"2309.01430","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-dimension-unified-swin-transformer-for","title":"Multi-dimension unified Swin Transformer for 3D Lesion Segmentation in Multiple Anatomical Locations","date":"2023-09-04","arxiv_id":"2309.01823","n_code_links":0,"syntology":null},{"paper":"/paper/acc-unet-a-completely-convolutional-unet","slug":"acc-unet-a-completely-convolutional-unet","title":"ACC-UNet: A Completely Convolutional UNet model for the 2020s","date":"2023-08-25","arxiv_id":"2308.13680","n_code_links":1,"syntology":null},{"paper":"/paper/sg-former-self-guided-transformer-with","slug":"sg-former-self-guided-transformer-with","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","date":"2023-08-23","arxiv_id":"2308.12216","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 5 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) · 2 unverified","official":{"repos":["oliverrensu/sg-former"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/small-object-detection-for-birds-with-swin","slug":"small-object-detection-for-birds-with-swin","title":"Small Object Detection for Birds with Swin Transformer","date":"2023-08-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/swinface-a-multi-task-transformer-for-face","slug":"swinface-a-multi-task-transformer-for-face","title":"SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation","date":"2023-08-22","arxiv_id":"2308.11509","n_code_links":1,"syntology":null},{"paper":null,"slug":"swinv2dnet-pyramid-and-self-supervision","title":"SwinV2DNet: Pyramid and Self-Supervision Compounded Feature Learning for Remote Sensing Images Change Detection","date":"2023-08-22","arxiv_id":"2308.11159","n_code_links":0,"syntology":null},{"paper":null,"slug":"ldcsf-local-depth-convolution-based-swim","title":"LDCSF: Local depth convolution-based Swim framework for classifying multi-label histopathology images","date":"2023-08-21","arxiv_id":"2308.10446","n_code_links":0,"syntology":null},{"paper":"/paper/swinlstm-improving-spatiotemporal-prediction","slug":"swinlstm-improving-spatiotemporal-prediction","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-08-19","arxiv_id":"2308.09891","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 4 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) · 5 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["SongTang-x/SwinLSTM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/swinjscc-taming-swin-transformer-for-deep","slug":"swinjscc-taming-swin-transformer-for-deep","title":"SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding","date":"2023-08-18","arxiv_id":"2308.09361","n_code_links":2,"syntology":null},{"paper":null,"slug":"sst-a-simplified-swin-transformer-based-model","title":"SST: A Simplified Swin Transformer-based Model for Taxi Destination Prediction based on Existing Trajectory","date":"2023-08-15","arxiv_id":"2308.07555","n_code_links":0,"syntology":null},{"paper":null,"slug":"scsc-spatial-cross-scale-convolution-module","title":"SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers","date":"2023-08-14","arxiv_id":"2308.07110","n_code_links":0,"syntology":null}],"record_sha256":"3b7a9665a0537f9ea50194c24e968792e1dd2e15a302b391dfd9a7572192855e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}