{"total":207,"rows":[{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"area":null},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294,"area":"diffusion"},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236,"area":null},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2301.04558","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","created":"2023-01-11","cited_by_count":211,"area":null},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169,"area":null},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167,"area":"inference"},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136,"area":null},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113,"area":null},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2211.15979","title":"AirFormer: Predicting Nationwide Air Quality in China with Transformers","created":"2022-11-29","cited_by_count":73,"area":null},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2203.04845","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","created":"2022-03-09","cited_by_count":67,"area":null},{"id":"2402.17228","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","created":"2024-02-27","cited_by_count":67,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63,"area":null},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56,"area":null},{"id":"2302.03548","title":"PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer","created":"2023-02-07","cited_by_count":48,"area":null},{"id":"2311.15153","title":"Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture","created":"2023-11-26","cited_by_count":46,"area":null},{"id":"2305.16642","title":"Improving Position Encoding of Transformers for Multivariate Time Series Classification","created":"2023-05-26","cited_by_count":45,"area":null},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42,"area":null},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2211.14462","title":"Meta Architecture for Point Cloud Analysis","created":"2022-11-26","cited_by_count":40,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38,"area":null},{"id":"2308.05493","title":"Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation","created":"2023-08-10","cited_by_count":38,"area":null},{"id":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36,"area":null},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34,"area":null},{"id":"2302.01791","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","created":"2023-02-03","cited_by_count":34,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2310.12970","title":"Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding","created":"2023-10-19","cited_by_count":33,"area":"wm"},{"id":"2203.01252","title":"A Unified Query-based Paradigm for Point Cloud Understanding","created":"2022-03-02","cited_by_count":32,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2303.08891","title":"ViTO: Vision Transformer-Operator","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2206.00790","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","created":"2022-06-01","cited_by_count":27,"area":null},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27,"area":null},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26,"area":null},{"id":"2307.13363","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","created":"2023-07-25","cited_by_count":25,"area":null},{"id":"2112.14087","title":"APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers","created":"2021-12-28","cited_by_count":24,"area":null},{"id":"2301.04648","title":"Head-Free Lightweight Semantic Segmentation with Linear Transformer","created":"2023-01-11","cited_by_count":22,"area":null},{"id":"2308.10133","title":"TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security","created":"2023-08-20","cited_by_count":22,"area":null},{"id":"2203.01536","title":"Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2305.06621","title":"PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer","created":"2023-05-11","cited_by_count":21,"area":null},{"id":"2301.05372","title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","created":"2023-01-13","cited_by_count":20,"area":null},{"id":"2112.12786","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","created":"2021-12-23","cited_by_count":18,"area":null},{"id":"2311.05613","title":"Window Attention is Bugged: How not to Interpolate Position Embeddings","created":"2023-11-09","cited_by_count":18,"area":null},{"id":"2506.03737","title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","created":"2025-06-04","cited_by_count":18,"area":null},{"id":"2309.06891","title":"Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?","created":"2023-09-13","cited_by_count":16,"area":null},{"id":"2212.03690","title":"Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data","created":"2022-12-07","cited_by_count":15,"area":null},{"id":"2408.11567","title":"Positional Prompt Tuning for Efficient 3D Representation Learning","created":"2024-08-21","cited_by_count":15,"area":null},{"id":"2409.00353","title":"RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning","created":"2024-08-31","cited_by_count":15,"area":null},{"id":"2206.08194","title":"Online Segmentation of LiDAR Sequences: Dataset and Algorithm","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2306.17373","title":"HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image","created":"2023-06-30","cited_by_count":14,"area":null},{"id":"2308.11568","title":"SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation","created":"2023-08-22","cited_by_count":14,"area":null},{"id":"2407.02894","title":"Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2505.04616","title":"Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait","created":"2025-05-07","cited_by_count":14,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2112.15509","title":"Scene-Adaptive Attention Network for Crowd Counting","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2206.07662","title":"SP-ViT: Learning 2D Spatial Priors for Vision Transformers","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2309.14660","title":"CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2410.14195","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2403.02871","title":"Quantum Mixed-State Self-Attention Network","created":"2024-03-05","cited_by_count":11,"area":null},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2203.01587","title":"Multi-Tailed Vision Transformer for Efficient Inference","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2311.18307","title":"Categorical Traffic Transformer: Interpretable and Diverse Behavior Prediction with Tokenized Latent","created":"2023-11-30","cited_by_count":10,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2410.06405","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","created":"2024-10-08","cited_by_count":10,"area":"lr"},{"id":"2303.08438","title":"Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement","created":"2023-03-15","cited_by_count":9,"area":null},{"id":"2306.14662","title":"Cross Architecture Distillation for Face Recognition","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2305.11468","title":"Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2404.18043","title":"Utilizing Large Language Models for Information Extraction from Real Estate Transactions","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2405.00251","title":"Semantically Consistent Video Inpainting with Conditional Diffusion Models","created":"2024-04-30","cited_by_count":8,"area":"diffusion"},{"id":"2502.20371","title":"Constrained Generative Modeling with Manually Bridged Diffusion Models","created":"2025-02-27","cited_by_count":8,"area":"diffusion"},{"id":"2211.01484","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2212.00975","title":"Relation-Aware Language-Graph Transformer for Question Answering","created":"2022-12-02","cited_by_count":7,"area":null},{"id":"2302.03038","title":"Single Cells Are Spatial Tokens: Transformers for Spatial Transcriptomic Data Imputation","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2509.01250","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2202.06510","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","created":"2022-02-14","cited_by_count":6,"area":null}],"next_cursor":"100"}