{"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/transformer/papers/111","list_of":"/method/transformer","method":"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":111,"pages_in_order":140,"rows_per_page":100,"rows":[11001,11100],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/110","next":"/method/transformer/papers/112","papers":[{"paper":null,"slug":"vitbis-vision-transformer-for-biomedical","title":"ViTBIS: Vision Transformer for Biomedical Image Segmentation","date":"2022-01-15","arxiv_id":"2201.05920","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-over-self-attention-intention-aware","title":"Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation","date":"2022-01-14","arxiv_id":"2201.05333","n_code_links":0,"syntology":null},{"paper":"/paper/accurate-identification-of-bacteriophages","slug":"accurate-identification-of-bacteriophages","title":"Accurate identification of bacteriophages from metagenomic data using Transformer","date":"2022-01-13","arxiv_id":"2201.04778","n_code_links":1,"syntology":null},{"paper":null,"slug":"hand-object-interaction-reasoning","title":"Hand-Object Interaction Reasoning","date":"2022-01-13","arxiv_id":"2201.04906","n_code_links":0,"syntology":null},{"paper":null,"slug":"technical-report-for-iccv-2021-challenge","title":"Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners","date":"2022-01-13","arxiv_id":"2201.04924","n_code_links":0,"syntology":null},{"paper":"/paper/transvod-end-to-end-video-object-detection","slug":"transvod-end-to-end-video-object-detection","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2022-01-13","arxiv_id":"2201.05047","n_code_links":3,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qianyuzqy/TransVOD_Lite"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"paper":"/paper/hypertransformer-model-generation-for","slug":"hypertransformer-model-generation-for","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","date":"2022-01-11","arxiv_id":"2201.04182","n_code_links":2,"syntology":null},{"paper":null,"slug":"model-less-robust-voltage-control-in-active","title":"Model-less Robust Voltage Control in Active Distribution Networks using Sensitivity Coefficients Estimated from Measurements","date":"2022-01-11","arxiv_id":"2201.04192","n_code_links":0,"syntology":null},{"paper":null,"slug":"pyramid-fusion-transformer-for-semantic","title":"Pyramid Fusion Transformer for Semantic Segmentation","date":"2022-01-11","arxiv_id":"2201.04019","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ginco-training-dataset-for-web-genre","title":"The GINCO Training Dataset for Web Genre Identification of Documents Out in the Wild","date":"2022-01-11","arxiv_id":"2201.03857","n_code_links":0,"syntology":null},{"paper":null,"slug":"uni-eden-universal-encoder-decoder-network-by","title":"Uni-EDEN: Universal Encoder-Decoder Network by Multi-Granular Vision-Language Pre-training","date":"2022-01-11","arxiv_id":"2201.04026","n_code_links":0,"syntology":null},{"paper":"/paper/local-information-assisted-attention-free","slug":"local-information-assisted-attention-free","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","date":"2022-01-10","arxiv_id":"2201.03217","n_code_links":1,"syntology":null},{"paper":null,"slug":"swin-transformers-make-strong-contextual","title":"Swin Transformer coupling CNNs Makes Strong Contextual Encoders for VHR Image Road Extraction","date":"2022-01-10","arxiv_id":"2201.03178","n_code_links":0,"syntology":null},{"paper":null,"slug":"tiltedbert-resource-adjustable-version-of","title":"Latency Adjustable Transformer Encoder for Language Understanding","date":"2022-01-10","arxiv_id":"2201.03327","n_code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-tuples-transformer-for","slug":"spatio-temporal-tuples-transformer-for","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","date":"2022-01-08","arxiv_id":"2201.02849","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":3,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["heleiqiu/sttformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-speech-recognition-datasets-in","slug":"automatic-speech-recognition-datasets-in","title":"Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset","date":"2022-01-07","arxiv_id":"2201.02419","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-target-aware-representation-for","title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","date":"2022-01-07","arxiv_id":"2201.02526","n_code_links":0,"syntology":null},{"paper":"/paper/compact-bidirectional-transformer-for-image","slug":"compact-bidirectional-transformer-for-image","title":"Compact Bidirectional Transformer for Image Captioning","date":"2022-01-06","arxiv_id":"2201.01984","n_code_links":1,"syntology":null},{"paper":"/paper/flow-guided-sparse-transformer-for-video","slug":"flow-guided-sparse-transformer-for-video","title":"Flow-Guided Sparse Transformer for Video Deblurring","date":"2022-01-06","arxiv_id":"2201.01893","n_code_links":1,"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":["linjing7/VR-Baseline"],"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":"transvpr-transformer-based-place-recognition","title":"TransVPR: Transformer-based place recognition with multi-level attention aggregation","date":"2022-01-06","arxiv_id":"2201.02001","n_code_links":0,"syntology":null},{"paper":"/paper/lawin-transformer-improving-semantic","slug":"lawin-transformer-improving-semantic","title":"Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention","date":"2022-01-05","arxiv_id":"2201.01615","n_code_links":3,"syntology":null},{"paper":null,"slug":"efficient-dyn-dynamic-graph-representation","title":"Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network","date":"2022-01-04","arxiv_id":"2201.01384","n_code_links":0,"syntology":null},{"paper":"/paper/pyramidtnt-improved-transformer-in","slug":"pyramidtnt-improved-transformer-in","title":"PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture","date":"2022-01-04","arxiv_id":"2201.00978","n_code_links":1,"syntology":null},{"paper":"/paper/sign-pose-based-transformer-for-word-level","slug":"sign-pose-based-transformer-for-word-level","title":"Sign Pose-Based Transformer for Word-Level Sign Language Recognition","date":"2022-01-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"caft-clustering-and-filter-on-tokens-of","title":"CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization","date":"2022-01-03","arxiv_id":"2201.00475","n_code_links":0,"syntology":null},{"paper":"/paper/d-former-a-u-shaped-dilated-transformer-for","slug":"d-former-a-u-shaped-dilated-transformer-for","title":"D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation","date":"2022-01-03","arxiv_id":"2201.00462","n_code_links":1,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-transformer-with-deformable-attention","slug":"vision-transformer-with-deformable-attention","title":"Vision Transformer with Deformable Attention","date":"2022-01-03","arxiv_id":"2201.00520","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":4,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"8 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; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/detail-preserving-transformer-for-light-field","slug":"detail-preserving-transformer-for-light-field","title":"Detail-Preserving Transformer for Light Field Image Super-Resolution","date":"2022-01-02","arxiv_id":"2201.00346","n_code_links":1,"syntology":{"ran":10,"of":21,"n_ran_checked":6,"n_instrument":4,"unverified":11,"pointer_only":21,"phrase":"10 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; 4 where Syntology's instrument failed) · 11 unverified","official":{"repos":["bitszwang/dpt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/informed-multi-context-entity-alignment","slug":"informed-multi-context-entity-alignment","title":"Informed Multi-context Entity Alignment","date":"2022-01-02","arxiv_id":"2201.00304","n_code_links":1,"syntology":null},{"paper":"/paper/splicing-vit-features-for-semantic-appearance","slug":"splicing-vit-features-for-semantic-appearance","title":"Splicing ViT Features for Semantic Appearance Transfer","date":"2022-01-02","arxiv_id":"2201.00424","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["omerbt/Splice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-brand-new-dance-partner-music-conditioned","slug":"a-brand-new-dance-partner-music-conditioned","title":"A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-graph-matching-perspective-with","title":"A Graph Matching Perspective With Transformers on Video Instance Segmentation","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"continual-learning-with-lifelong-vision","title":"Continual Learning With Lifelong Vision Transformer","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"destr-object-detection-with-split-transformer","title":"DESTR: Object Detection With Split Transformer","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dlformer-discrete-latent-transformer-for","title":"DLFormer: Discrete Latent Transformer for Video Inpainting","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-scene-graph-generation-via","title":"Dynamic Scene Graph Generation via Anticipatory Pre-Training","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hivt-hierarchical-vector-transformer-for","slug":"hivt-hierarchical-vector-transformer-for","title":"HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction","date":"2022-01-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/image-dehazing-transformer-with-transmission","slug":"image-dehazing-transformer-with-transmission","title":"Image Dehazing Transformer With Transmission-Aware 3D Position Embedding","date":"2022-01-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"instance-segmentation-with-mask-supervised","title":"Instance Segmentation With Mask-Supervised Polygonal Boundary Transformers","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knn-local-attention-for-image-restoration","title":"KNN Local Attention for Image Restoration","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-transferable-human-object","slug":"learning-transferable-human-object","title":"Learning Transferable Human-Object Interaction Detector With Natural Language Supervision","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"lift-learning-4d-lidar-image-fusion","title":"LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/likert-scoring-with-grade-decoupling-for-long","slug":"likert-scoring-with-grade-decoupling-for-long","title":"Likert Scoring With Grade Decoupling for Long-Term Action Assessment","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ltp-lane-based-trajectory-prediction-for","title":"LTP: Lane-Based Trajectory Prediction for Autonomous Driving","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/m3t-three-dimensional-medical-image","slug":"m3t-three-dimensional-medical-image","title":"M3T: Three-Dimensional Medical Image Classifier Using Multi-Plane and Multi-Slice Transformer","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mr-biq-post-training-non-uniform-quantization","title":"Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-dynamic-graph-transformer-for","slug":"multi-modal-dynamic-graph-transformer-for","title":"Multi-Modal Dynamic Graph Transformer for Visual Grounding","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"patchtrack-multiple-object-tracking-using","title":"PatchTrack: Multiple Object Tracking Using Frame Patches","date":"2022-01-01","arxiv_id":"2201.00080","n_code_links":0,"syntology":null},{"paper":null,"slug":"recurring-the-transformer-for-video-action","title":"Recurring the Transformer for Video Action Recognition","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tencent-mvse-a-large-scale-benchmark-dataset","title":"Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-line-segment-classifier","title":"Transformer Based Line Segment Classifier With Image Context for Real-Time Vanishing Point Detection in Manhattan World","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-guided-probabilistic-transformer","title":"Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/csformer-bridging-convolution-and-transformer","slug":"csformer-bridging-convolution-and-transformer","title":"CSformer: Bridging Convolution and Transformer for Compressive Sensing","date":"2021-12-31","arxiv_id":"2112.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"openqa-hybrid-qa-system-relying-on-structured","title":"OpenQA: Hybrid QA System Relying on Structured Knowledge Base as well as Non-structured Data","date":"2021-12-31","arxiv_id":"2112.15356","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-adaptive-attention-network-for-crowd","title":"Scene-Adaptive Attention Network for Crowd Counting","date":"2021-12-31","arxiv_id":"2112.15509","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-embeddings-of-irregularly-spaced-1","slug":"transformer-embeddings-of-irregularly-spaced-1","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","date":"2021-12-31","arxiv_id":"2201.00044","n_code_links":2,"syntology":null},{"paper":"/paper/vinmt-neural-machine-translation-tookit","slug":"vinmt-neural-machine-translation-tookit","title":"ViNMT: Neural Machine Translation Toolkit","date":"2021-12-31","arxiv_id":"2112.15272","n_code_links":1,"syntology":null},{"paper":"/paper/a-lightweight-and-accurate-spatial-temporal","slug":"a-lightweight-and-accurate-spatial-temporal","title":"A Lightweight and Accurate Spatial-Temporal Transformer for Traffic Forecasting","date":"2021-12-30","arxiv_id":"2201.00008","n_code_links":1,"syntology":null},{"paper":null,"slug":"chunkformer-learning-long-time-series-with","title":"ChunkFormer: Learning Long Time Series with Multi-stage Chunked Transformer","date":"2021-12-30","arxiv_id":"2112.15087","n_code_links":0,"syntology":null},{"paper":"/paper/persformer-a-transformer-architecture-for","slug":"persformer-a-transformer-architecture-for","title":"Persformer: A Transformer Architecture for Topological Machine Learning","date":"2021-12-30","arxiv_id":"2112.15210","n_code_links":1,"syntology":null},{"paper":"/paper/the-benchmark-transferable-representation","slug":"the-benchmark-transferable-representation","title":"THE Benchmark: Transferable Representation Learning for Monocular Height Estimation","date":"2021-12-30","arxiv_id":"2112.14985","n_code_links":0,"syntology":null},{"paper":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["codecaution/evomoe"],"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"]}}},{"paper":"/paper/learning-inception-attention-for-image","slug":"learning-inception-attention-for-image","title":"Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognition","date":"2021-12-29","arxiv_id":"2112.14804","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-attention-augmented-transformer","title":"Temporal Attention Augmented Transformer Hawkes Process","date":"2021-12-29","arxiv_id":"2112.14472","n_code_links":0,"syntology":null},{"paper":"/paper/april-finding-the-achilles-heel-on-privacy","slug":"april-finding-the-achilles-heel-on-privacy","title":"APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers","date":"2021-12-28","arxiv_id":"2112.14087","n_code_links":1,"syntology":null},{"paper":null,"slug":"extended-self-critical-pipeline-for","title":"Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg","date":"2021-12-28","arxiv_id":"2112.14100","n_code_links":0,"syntology":null},{"paper":"/paper/pale-transformer-a-general-vision-transformer","slug":"pale-transformer-a-general-vision-transformer","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","date":"2021-12-28","arxiv_id":"2112.14000","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BR-IDL/PaddleViT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"synchronized-audio-visual-frames-with","title":"Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation","date":"2021-12-28","arxiv_id":"2112.14088","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-sentence-analysis-for-the","title":"Contextual Sentence Analysis for the Sentiment Prediction on Financial Data","date":"2021-12-27","arxiv_id":"2112.13790","n_code_links":0,"syntology":null},{"paper":"/paper/heteroqa-learning-towards-question-and","slug":"heteroqa-learning-towards-question-and","title":"HeteroQA: Learning towards Question-and-Answering through Multiple Information Sources via Heterogeneous Graph Modeling","date":"2021-12-27","arxiv_id":"2112.13597","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-robust-and-lightweight-model-through","title":"Learning Robust and Lightweight Model through Separable Structured Transformations","date":"2021-12-27","arxiv_id":"2112.13551","n_code_links":0,"syntology":null},{"paper":"/paper/msht-multi-stage-hybrid-transformer-for-the","slug":"msht-multi-stage-hybrid-transformer-for-the","title":"MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer","date":"2021-12-27","arxiv_id":"2112.13513","n_code_links":1,"syntology":null},{"paper":"/paper/spvit-enabling-faster-vision-transformers-via","slug":"spvit-enabling-faster-vision-transformers-via","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","date":"2021-12-27","arxiv_id":"2112.13890","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peiyanflying/spvit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/video-joint-modelling-based-on-hierarchical","slug":"video-joint-modelling-based-on-hierarchical","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","date":"2021-12-27","arxiv_id":"2112.13478","n_code_links":2,"syntology":null},{"paper":null,"slug":"vir-the-vision-reservoir","title":"ViR:the Vision Reservoir","date":"2021-12-27","arxiv_id":"2112.13545","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-for-small-size-datasets","slug":"vision-transformer-for-small-size-datasets","title":"Vision Transformer for Small-Size Datasets","date":"2021-12-27","arxiv_id":"2112.13492","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["aanna0701/SPT_LSA_ViT"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/an-ensemble-of-pre-trained-transformer-models","slug":"an-ensemble-of-pre-trained-transformer-models","title":"An Ensemble of Pre-trained Transformer Models For Imbalanced Multiclass Malware Classification","date":"2021-12-25","arxiv_id":"2112.13236","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-improvements-for-exploiting","title":"Combining Improvements for Exploiting Dependency Trees in Neural Semantic Parsing","date":"2021-12-25","arxiv_id":"2112.13179","n_code_links":0,"syntology":null},{"paper":null,"slug":"raw-produce-quality-detection-with-shifted","title":"Raw Produce Quality Detection with Shifted Window Self-Attention","date":"2021-12-24","arxiv_id":"2112.13845","n_code_links":0,"syntology":null},{"paper":"/paper/simvit-exploring-a-simple-vision-transformer","slug":"simvit-exploring-a-simple-vision-transformer","title":"SimViT: Exploring a Simple Vision Transformer with sliding windows","date":"2021-12-24","arxiv_id":"2112.13085","n_code_links":2,"syntology":null},{"paper":"/paper/elsa-enhanced-local-self-attention-for-vision","slug":"elsa-enhanced-local-self-attention-for-vision","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","date":"2021-12-23","arxiv_id":"2112.12786","n_code_links":1,"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":["damo-cv/elsa"],"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":"/paper/latr-layout-aware-transformer-for-scene-text","slug":"latr-layout-aware-transformer-for-scene-text","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","date":"2021-12-23","arxiv_id":"2112.12494","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/s-page-a-speaker-and-position-aware-graph","slug":"s-page-a-speaker-and-position-aware-graph","title":"S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation","date":"2021-12-23","arxiv_id":"2112.12389","n_code_links":0,"syntology":null},{"paper":"/paper/semask-semantically-masked-transformers-for-1","slug":"semask-semantically-masked-transformers-for-1","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","date":"2021-12-23","arxiv_id":"2112.12782","n_code_links":1,"syntology":null},{"paper":"/paper/clevr3d-compositional-language-and-elementary","slug":"clevr3d-compositional-language-and-elementary","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","date":"2021-12-22","arxiv_id":"2112.11691","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yanx27/clevr3d"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"da-fdftnet-dual-attention-fake-detection-fine","title":"DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images","date":"2021-12-22","arxiv_id":"2112.12001","n_code_links":0,"syntology":null},{"paper":null,"slug":"diformer-directional-transformer-for-neural","title":"Diformer: Directional Transformer for Neural Machine Translation","date":"2021-12-22","arxiv_id":"2112.11632","n_code_links":0,"syntology":null},{"paper":null,"slug":"mia-former-efficient-and-robust-vision","title":"MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation","date":"2021-12-21","arxiv_id":"2112.11542","n_code_links":0,"syntology":null},{"paper":"/paper/mpvit-multi-path-vision-transformer-for-dense","slug":"mpvit-multi-path-vision-transformer-for-dense","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","date":"2021-12-21","arxiv_id":"2112.11010","n_code_links":3,"syntology":null},{"paper":"/paper/soit-segmenting-objects-with-instance-aware","slug":"soit-segmenting-objects-with-instance-aware","title":"SOIT: Segmenting Objects with Instance-Aware Transformers","date":"2021-12-21","arxiv_id":"2112.11037","n_code_links":1,"syntology":null},{"paper":"/paper/article-reranking-by-memory-enhanced-key-1","slug":"article-reranking-by-memory-enhanced-key-1","title":"Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims","date":"2021-12-20","arxiv_id":"2112.10322","n_code_links":1,"syntology":null},{"paper":"/paper/diaformer-automatic-diagnosis-via-symptoms","slug":"diaformer-automatic-diagnosis-via-symptoms","title":"Diaformer: Automatic Diagnosis via Symptoms Sequence Generation","date":"2021-12-20","arxiv_id":"2112.10433","n_code_links":1,"syntology":null},{"paper":"/paper/lite-vision-transformer-with-enhanced-self","slug":"lite-vision-transformer-with-enhanced-self","title":"Lite Vision Transformer with Enhanced Self-Attention","date":"2021-12-20","arxiv_id":"2112.10809","n_code_links":1,"syntology":null},{"paper":"/paper/self-attention-presents-low-dimensional","slug":"self-attention-presents-low-dimensional","title":"Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction","date":"2021-12-20","arxiv_id":"2112.10644","n_code_links":1,"syntology":null},{"paper":"/paper/ssdnet-state-space-decomposition-neural","slug":"ssdnet-state-space-decomposition-neural","title":"SSDNet: State Space Decomposition Neural Network for Time Series Forecasting","date":"2021-12-19","arxiv_id":"2112.10251","n_code_links":1,"syntology":null},{"paper":null,"slug":"task-oriented-multi-user-semantic-1","title":"Task-Oriented Multi-User Semantic Communications","date":"2021-12-19","arxiv_id":"2112.10255","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-long-term-dependencies-for","slug":"exploiting-long-term-dependencies-for","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","date":"2021-12-18","arxiv_id":"2112.09828","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-single-scale-vision-transformer-for","slug":"a-simple-single-scale-vision-transformer-for","title":"A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation","date":"2021-12-17","arxiv_id":"2112.09747","n_code_links":3,"syntology":null},{"paper":null,"slug":"challenging-america-modeling-language-in","title":"Challenging America: Modeling language in longer time scales","date":"2021-12-17","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"91c48da8ee90eef66aff3f4191dec28adc0ba02e64e759802aac3bbe415d975c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}