{"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/3","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":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"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/papers/2","next":"/method/swin-transformer/papers/4","papers":[{"paper":"/paper/revolutionizing-space-health-swin-fsr","slug":"revolutionizing-space-health-swin-fsr","title":"Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology","date":"2023-08-11","arxiv_id":"2308.06332","n_code_links":1,"syntology":null},{"paper":null,"slug":"breast-ultrasound-tumor-classification-using","title":"Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network","date":"2023-08-04","arxiv_id":"2308.02101","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-for-human-behavior-analysis","title":"Data Augmentation for Human Behavior Analysis in Multi-Person Conversations","date":"2023-08-03","arxiv_id":"2308.01526","n_code_links":0,"syntology":null},{"paper":"/paper/indoherb-indonesia-medicinal-plants","slug":"indoherb-indonesia-medicinal-plants","title":"IndoHerb: Indonesia Medicinal Plants Recognition using Transfer Learning and Deep Learning","date":"2023-08-03","arxiv_id":"2308.01604","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-swin-vision","title":"Performance Evaluation of Swin Vision Transformer Model using Gradient Accumulation Optimization Technique","date":"2023-07-31","arxiv_id":"2308.00197","n_code_links":0,"syntology":null},{"paper":"/paper/tuning-pre-trained-model-via-moment-probing","slug":"tuning-pre-trained-model-via-moment-probing","title":"Tuning Pre-trained Model via Moment Probing","date":"2023-07-21","arxiv_id":"2307.11342","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":3,"n_instrument":5,"unverified":5,"pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mingzeg/moment-probing"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hierarchical-spatiotemporal-transformers-for","title":"Hierarchical Spatiotemporal Transformers for Video Object Segmentation","date":"2023-07-17","arxiv_id":"2307.08263","n_code_links":0,"syntology":null},{"paper":"/paper/scale-aware-modulation-meet-transformer","slug":"scale-aware-modulation-meet-transformer","title":"Scale-Aware Modulation Meet Transformer","date":"2023-07-17","arxiv_id":"2307.08579","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["afeng-x/smt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tall-thumbnail-layout-for-deepfake-video","slug":"tall-thumbnail-layout-for-deepfake-video","title":"TALL: Thumbnail Layout for Deepfake Video Detection","date":"2023-07-14","arxiv_id":"2307.07494","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["rainy-xu/tall4deepfake"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/deepfake-video-detection-using-generative","slug":"deepfake-video-detection-using-generative","title":"Deepfake Video Detection Using Generative Convolutional Vision Transformer","date":"2023-07-13","arxiv_id":"2307.07036","n_code_links":1,"syntology":null},{"paper":null,"slug":"convnext-charm-convnext-based-transform-for","title":"ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression","date":"2023-07-12","arxiv_id":"2307.06342","n_code_links":0,"syntology":null},{"paper":"/paper/swift-swin-4d-fmri-transformer-1","slug":"swift-swin-4d-fmri-transformer-1","title":"SwiFT: Swin 4D fMRI Transformer","date":"2023-07-12","arxiv_id":"2307.05916","n_code_links":1,"syntology":{"ran":25,"of":42,"n_ran_checked":21,"n_instrument":4,"unverified":17,"pointer_only":16,"phrase":"25 ran (of which 4 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 17 unverified","official":{"repos":["transconnectome/swift"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"automatic-diagnosis-of-knee-osteoarthritis","title":"Automatic diagnosis of knee osteoarthritis severity using Swin transformer","date":"2023-07-10","arxiv_id":"2307.04442","n_code_links":0,"syntology":null},{"paper":null,"slug":"art-authentication-with-vision-transformers","title":"Art Authentication with Vision Transformers","date":"2023-07-06","arxiv_id":"2307.03039","n_code_links":0,"syntology":null},{"paper":"/paper/maskbev-joint-object-detection-and-footprint","slug":"maskbev-joint-object-detection-and-footprint","title":"MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds","date":"2023-07-04","arxiv_id":"2307.01864","n_code_links":1,"syntology":null},{"paper":null,"slug":"selffed-self-supervised-federated-learning","title":"SelfFed: Self-supervised Federated Learning for Data Heterogeneity and Label Scarcity in IoMT","date":"2023-07-04","arxiv_id":"2307.01514","n_code_links":0,"syntology":null},{"paper":null,"slug":"cutting-edge-techniques-for-depth-map-super","title":"Cutting-Edge Techniques for Depth Map Super-Resolution","date":"2023-06-27","arxiv_id":"2306.15244","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameternet-parameters-are-all-you-need-for","title":"ParameterNet: Parameters Are All You Need","date":"2023-06-26","arxiv_id":"2306.14525","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-sequence-models-for-sequential-decision","title":"Large Sequence Models for Sequential Decision-Making: A Survey","date":"2023-06-24","arxiv_id":"2306.13945","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-free-achieving-better-cross-window","title":"Swin-Free: Achieving Better Cross-Window Attention and Efficiency with Size-varying Window","date":"2023-06-23","arxiv_id":"2306.13776","n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-sub-model-to-improve-main-model","slug":"augmenting-sub-model-to-improve-main-model","title":"Masking meets Supervision: A Strong Learning Alliance","date":"2023-06-20","arxiv_id":"2306.11339","n_code_links":1,"syntology":null},{"paper":"/paper/slamb-accelerated-large-batch-training-with","slug":"slamb-accelerated-large-batch-training-with","title":"SLAMB: Accelerated Large Batch Training with Sparse Communication","date":"2023-06-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"npvforensics-jointing-non-critical-phonemes","title":"NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection","date":"2023-06-12","arxiv_id":"2306.06885","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-dataset-pruning-with-dynamic","slug":"large-scale-dataset-pruning-with-dynamic","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","date":"2023-06-08","arxiv_id":"2306.05175","n_code_links":2,"syntology":{"ran":11,"of":11,"n_ran_checked":8,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"11 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["baai-dcai/dataset-pruning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformer-based-unet-with-multi-headed","title":"Transformer-Based UNet with Multi-Headed Cross-Attention Skip Connections to Eliminate Artifacts in Scanned Documents","date":"2023-06-05","arxiv_id":"2306.02815","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-low-light-image-enhancement","title":"Unsupervised Low Light Image Enhancement Using SNR-Aware Swin Transformer","date":"2023-06-03","arxiv_id":"2306.02082","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-driver-distraction-behavior-detection","slug":"a-novel-driver-distraction-behavior-detection","title":"A Novel Driver Distraction Behavior Detection Method Based on Self-supervised Learning with Masked Image Modeling","date":"2023-06-01","arxiv_id":"2306.00543","n_code_links":1,"syntology":null},{"paper":"/paper/swinia-self-supervised-blind-spot-image","slug":"swinia-self-supervised-blind-spot-image","title":"SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions","date":"2023-05-09","arxiv_id":"2305.05651","n_code_links":0,"syntology":null},{"paper":"/paper/rfr-wwanet-weighted-window-attention-based","slug":"rfr-wwanet-weighted-window-attention-based","title":"RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration","date":"2023-05-07","arxiv_id":"2305.04236","n_code_links":1,"syntology":null},{"paper":null,"slug":"updexplainer-an-interpretable-transformer","title":"UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagery","date":"2023-05-04","arxiv_id":"2305.02911","n_code_links":0,"syntology":null},{"paper":null,"slug":"lemart-label-efficient-masked-region","title":"LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization","date":"2023-04-25","arxiv_id":"2304.13166","n_code_links":0,"syntology":null},{"paper":"/paper/sdsc-unet-dual-skip-connection-vit-based-u","slug":"sdsc-unet-dual-skip-connection-vit-based-u","title":"SDSC-UNet: Dual Skip Connection ViT-based U-shaped Model for Building Extraction","date":"2023-04-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stm-unet-an-efficient-u-shaped-architecture","title":"STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation","date":"2023-04-25","arxiv_id":"2304.12615","n_code_links":0,"syntology":null},{"paper":null,"slug":"swinfsr-stereo-image-super-resolution-using","title":"SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge","date":"2023-04-25","arxiv_id":"2304.12556","n_code_links":0,"syntology":null},{"paper":null,"slug":"darswin-distortion-aware-radial-swin","title":"DarSwin: Distortion Aware Radial Swin Transformer","date":"2023-04-19","arxiv_id":"2304.09691","n_code_links":0,"syntology":null},{"paper":"/paper/lipsformer-introducing-lipschitz-continuity","slug":"lipsformer-introducing-lipschitz-continuity","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","date":"2023-04-19","arxiv_id":"2304.09856","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["idea-research/lipsformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swin3d-a-pretrained-transformer-backbone-for","slug":"swin3d-a-pretrained-transformer-backbone-for","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","date":"2023-04-14","arxiv_id":"2304.06906","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/swin3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"video-event-restoration-based-on-keyframes","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","date":"2023-04-11","arxiv_id":"2304.05112","n_code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-intracranial-hemorrhage","slug":"weakly-supervised-intracranial-hemorrhage","title":"Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning","date":"2023-04-11","arxiv_id":"2304.04902","n_code_links":1,"syntology":null},{"paper":null,"slug":"hst-mrf-heterogeneous-swin-transformer-with","title":"HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation","date":"2023-04-10","arxiv_id":"2304.04614","n_code_links":0,"syntology":null},{"paper":null,"slug":"surrogate-lagrangian-relaxation-a-path-to","title":"Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning","date":"2023-04-08","arxiv_id":"2304.04120","n_code_links":0,"syntology":null},{"paper":null,"slug":"pft-ssr-parallax-fusion-transformer-for","title":"PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution","date":"2023-03-24","arxiv_id":"2303.13807","n_code_links":0,"syntology":null},{"paper":"/paper/ff-former-swin-fourier-transformer-for","slug":"ff-former-swin-fourier-transformer-for","title":"FF-Former: Swin Fourier Transformer for Nighttime Flare Removal","date":"2023-03-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/lswinsr-uav-imagery-super-resolution-based-on","slug":"lswinsr-uav-imagery-super-resolution-based-on","title":"LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer","date":"2023-03-17","arxiv_id":"2303.10232","n_code_links":1,"syntology":null},{"paper":"/paper/a-framework-for-real-time-object-detection","slug":"a-framework-for-real-time-object-detection","title":"Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy","date":"2023-03-16","arxiv_id":"2303.09190","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-exposure-hdr-composition-by-gated-swin","title":"Multi-Exposure HDR Composition by Gated Swin Transformer","date":"2023-03-15","arxiv_id":"2303.08704","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-facial-expression-recognition","title":"Multi Modal Facial Expression Recognition with Transformer-Based Fusion Networks and Dynamic Sampling","date":"2023-03-15","arxiv_id":"2303.08419","n_code_links":0,"syntology":null},{"paper":null,"slug":"endoscopy-classification-model-using-swin","title":"Endoscopy Classification Model Using Swin Transformer and Saliency Map","date":"2023-03-12","arxiv_id":"2303.06736","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-facial-action-unit-detection","title":"Self-supervised Facial Action Unit Detection with Region and Relation Learning","date":"2023-03-10","arxiv_id":"2303.05708","n_code_links":0,"syntology":null},{"paper":"/paper/x-pruner-explainable-pruning-for-vision","slug":"x-pruner-explainable-pruning-for-vision","title":"X-Pruner: eXplainable Pruning for Vision Transformers","date":"2023-03-08","arxiv_id":"2303.04935","n_code_links":1,"syntology":null},{"paper":"/paper/extended-agriculture-vision-an-extension-of-a","slug":"extended-agriculture-vision-an-extension-of-a","title":"Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis","date":"2023-03-04","arxiv_id":"2303.02460","n_code_links":1,"syntology":null},{"paper":"/paper/depth-based-6dof-object-pose-estimation-using","slug":"depth-based-6dof-object-pose-estimation-using","title":"Depth-based 6DoF Object Pose Estimation using Swin Transformer","date":"2023-03-03","arxiv_id":"2303.02133","n_code_links":1,"syntology":null},{"paper":null,"slug":"patch-network-for-medical-image-segmentation","title":"Patch Network for medical image Segmentation","date":"2023-02-23","arxiv_id":"2302.11802","n_code_links":0,"syntology":null},{"paper":"/paper/video-swinunet-spatio-temporal-deep-learning","slug":"video-swinunet-spatio-temporal-deep-learning","title":"Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation","date":"2023-02-22","arxiv_id":"2302.11325","n_code_links":2,"syntology":null},{"paper":"/paper/memory-augmented-online-video-anomaly","slug":"memory-augmented-online-video-anomaly","title":"Memory-augmented Online Video Anomaly Detection","date":"2023-02-21","arxiv_id":"2302.10719","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-to-embrace-natural-language-processing","title":"Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines","date":"2023-02-21","arxiv_id":"2302.10406","n_code_links":0,"syntology":null},{"paper":"/paper/stb-vmm-swin-transformer-based-video-motion","slug":"stb-vmm-swin-transformer-based-video-motion","title":"STB-VMM: Swin Transformer Based Video Motion Magnification","date":"2023-02-20","arxiv_id":"2302.10001","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-transformer-based-networks-with","title":"Improving Transformer-based Networks With Locality For Automatic Speaker Verification","date":"2023-02-17","arxiv_id":"2302.08639","n_code_links":0,"syntology":null},{"paper":null,"slug":"vita-a-vision-transformer-inference","title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","date":"2023-02-17","arxiv_id":"2302.09108","n_code_links":0,"syntology":null},{"paper":"/paper/cholectriplet2022-show-me-a-tool-and-tell-me","slug":"cholectriplet2022-show-me-a-tool-and-tell-me","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","date":"2023-02-13","arxiv_id":"2302.06294","n_code_links":2,"syntology":null},{"paper":null,"slug":"swincross-cross-modal-swin-transformer-for","title":"SwinCross: Cross-modal Swin Transformer for Head-and-Neck Tumor Segmentation in PET/CT Images","date":"2023-02-08","arxiv_id":"2302.03861","n_code_links":0,"syntology":null},{"paper":"/paper/local-window-attention-transformer-for","slug":"local-window-attention-transformer-for","title":"Local Window Attention Transformer for Polarimetric SAR Image Classification","date":"2023-01-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/swindepth-unsupervised-depth-estimation-using","slug":"swindepth-unsupervised-depth-estimation-using","title":"SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network","date":"2023-01-17","arxiv_id":"2301.06715","n_code_links":1,"syntology":null},{"paper":"/paper/swinlstm-improving-spatiotemporal-prediction-1","slug":"swinlstm-improving-spatiotemporal-prediction-1","title":"SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/swin-mae-masked-autoencoders-for-small","slug":"swin-mae-masked-autoencoders-for-small","title":"Swin MAE: Masked Autoencoders for Small Datasets","date":"2022-12-28","arxiv_id":"2212.13805","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-approaches-to-building-rooftop","slug":"deep-learning-approaches-to-building-rooftop","title":"Deep learning approaches to building rooftop thermal bridge detection from aerial images","date":"2022-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"abhe-all-attention-based-homography","title":"AbHE: All Attention-based Homography Estimation","date":"2022-12-06","arxiv_id":"2212.03029","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-object-of-interest-segmentation","title":"Video Object of Interest Segmentation","date":"2022-12-06","arxiv_id":"2212.02871","n_code_links":0,"syntology":null},{"paper":"/paper/ghost-free-high-dynamic-range-imaging-via","slug":"ghost-free-high-dynamic-range-imaging-via","title":"Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor","date":"2022-12-01","arxiv_id":"2212.00595","n_code_links":1,"syntology":null},{"paper":"/paper/pattern-attention-transformer-with-doughnut","slug":"pattern-attention-transformer-with-doughnut","title":"Pattern Attention Transformer with Doughnut Kernel","date":"2022-11-30","arxiv_id":"2211.16961","n_code_links":0,"syntology":null},{"paper":"/paper/noisyquant-noisy-bias-enhanced-post-training","slug":"noisyquant-noisy-bias-enhanced-post-training","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","date":"2022-11-29","arxiv_id":"2211.16056","n_code_links":1,"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: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kriskrisliu/NoisyQuant"],"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/semantic-aware-local-global-vision","slug":"semantic-aware-local-global-vision","title":"Semantic-Aware Local-Global Vision Transformer","date":"2022-11-27","arxiv_id":"2211.14705","n_code_links":0,"syntology":null},{"paper":null,"slug":"degenerate-swin-to-win-plain-window-based","title":"Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations","date":"2022-11-25","arxiv_id":"2211.14255","n_code_links":0,"syntology":null},{"paper":"/paper/uperformer-a-multi-scale-transformer-based","slug":"uperformer-a-multi-scale-transformer-based","title":"MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation","date":"2022-11-25","arxiv_id":"2211.13928","n_code_links":2,"syntology":null},{"paper":"/paper/video-test-time-adaptation-for-action","slug":"video-test-time-adaptation-for-action","title":"Video Test-Time Adaptation for Action Recognition","date":"2022-11-24","arxiv_id":"2211.15393","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-and-mitigating-static-bias-of","slug":"evaluating-and-mitigating-static-bias-of","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","date":"2022-11-23","arxiv_id":"2211.12883","n_code_links":1,"syntology":null},{"paper":"/paper/conv2former-a-simple-transformer-style","slug":"conv2former-a-simple-transformer-style","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","date":"2022-11-22","arxiv_id":"2211.11943","n_code_links":2,"syntology":null},{"paper":"/paper/blur-interpolation-transformer-for-real-world","slug":"blur-interpolation-transformer-for-real-world","title":"Blur Interpolation Transformer for Real-World Motion from Blur","date":"2022-11-21","arxiv_id":"2211.11423","n_code_links":1,"syntology":null},{"paper":"/paper/n-gram-in-swin-transformers-for-efficient","slug":"n-gram-in-swin-transformers-for-efficient","title":"N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution","date":"2022-11-21","arxiv_id":"2211.11436","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rami0205/ngramswin"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"problem-behaviors-recognition-in-videos-using","title":"Language-Assisted Deep Learning for Autistic Behaviors Recognition","date":"2022-11-17","arxiv_id":"2211.09310","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-sftnet-spatial-feature-expansion-and","title":"SWIN-SFTNet : Spatial Feature Expansion and Aggregation using Swin Transformer For Whole Breast micro-mass segmentation","date":"2022-11-16","arxiv_id":"2211.08717","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-machine-learning-framework-for","title":"End-to-End Machine Learning Framework for Facial AU Detection in Intensive Care Units","date":"2022-11-12","arxiv_id":"2211.06570","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multimodal-approach-for-dementia-detection","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","date":"2022-11-08","arxiv_id":"2211.04368","n_code_links":0,"syntology":null},{"paper":null,"slug":"osic-a-new-one-stage-image-captioner-coined","title":"OSIC: A New One-Stage Image Captioner Coined","date":"2022-11-04","arxiv_id":"2211.02321","n_code_links":0,"syntology":null},{"paper":"/paper/attention-swin-u-net-cross-contextual","slug":"attention-swin-u-net-cross-contextual","title":"Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation","date":"2022-10-30","arxiv_id":"2210.16898","n_code_links":1,"syntology":null},{"paper":null,"slug":"grafting-vision-transformers","title":"Grafting Vision Transformers","date":"2022-10-28","arxiv_id":"2210.15943","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-transformer-for-compressed-video","title":"End-to-end Transformer for Compressed Video Quality Enhancement","date":"2022-10-25","arxiv_id":"2210.13827","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-learning-with-masked-image","slug":"self-supervised-learning-with-masked-image","title":"Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs","date":"2022-10-20","arxiv_id":"2210.11404","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-image-super-resolution-using-2","title":"Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer","date":"2022-10-20","arxiv_id":"2210.11019","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-for-video-classification","title":"Transfer-learning for video classification: Video Swin Transformer on multiple domains","date":"2022-10-18","arxiv_id":"2210.09969","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-vision-transformers-for-medical","slug":"optimizing-vision-transformers-for-medical","title":"Optimizing Vision Transformers for Medical Image Segmentation","date":"2022-10-14","arxiv_id":"2210.08066","n_code_links":1,"syntology":null},{"paper":"/paper/a-perceptual-quality-metric-for-video-frame","slug":"a-perceptual-quality-metric-for-video-frame","title":"A Perceptual Quality Metric for Video Frame Interpolation","date":"2022-10-04","arxiv_id":"2210.01879","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hqqxyy/vfips"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/3d-ux-net-a-large-kernel-volumetric-convnet","slug":"3d-ux-net-a-large-kernel-volumetric-convnet","title":"3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation","date":"2022-09-29","arxiv_id":"2209.15076","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["masilab/3dux-net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/swin2sr-swinv2-transformer-for-compressed","slug":"swin2sr-swinv2-transformer-for-compressed","title":"Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration","date":"2022-09-22","arxiv_id":"2209.11345","n_code_links":5,"syntology":null},{"paper":"/paper/pict-a-slim-weakly-supervised-vision","slug":"pict-a-slim-weakly-supervised-vision","title":"PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification","date":"2022-09-21","arxiv_id":"2209.10074","n_code_links":1,"syntology":null},{"paper":null,"slug":"sar-ship-detection-based-on-swin-transformer","title":"Sar Ship Detection based on Swin Transformer and Feature Enhancement Feature Pyramid Network","date":"2022-09-21","arxiv_id":"2209.10421","n_code_links":0,"syntology":null},{"paper":"/paper/perceptual-quality-assessment-for-digital","slug":"perceptual-quality-assessment-for-digital","title":"Perceptual Quality Assessment for Digital Human Heads","date":"2022-09-20","arxiv_id":"2209.09489","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-outcome-of-the-2022-landslide4sense","title":"The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery","date":"2022-09-06","arxiv_id":"2209.02556","n_code_links":0,"syntology":null},{"paper":null,"slug":"viecap4h-vlsp-2021-vietnamese-image","title":"vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM","date":"2022-09-03","arxiv_id":"2209.01304","n_code_links":0,"syntology":null},{"paper":"/paper/gswin-gated-mlp-vision-model-with","slug":"gswin-gated-mlp-vision-model-with","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","date":"2022-08-24","arxiv_id":"2208.11718","n_code_links":0,"syntology":null}],"record_sha256":"c15b54a805536a07346bddeb6fd92858a1796cf8d733ecbc2f7cef1bbd949ef4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}