{"total":358,"rows":[{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305,"area":"diffusion"},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658,"area":"wm"},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2102.10662","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","created":"2021-02-21","cited_by_count":320,"area":null},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319,"area":null},{"id":"2104.00954","title":"Skillful Precipitation Nowcasting using Deep Generative Models of Radar","created":"2021-04-02","cited_by_count":311,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289,"area":null},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280,"area":"wm"},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2412.07236","title":"CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding","created":"2024-12-10","cited_by_count":199,"area":null},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2211.14830","title":"Medical Image Segmentation Review: The success of U-Net","created":"2022-11-27","cited_by_count":191,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165,"area":"wm"},{"id":"2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","created":"2022-07-12","cited_by_count":152,"area":null},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2303.17599","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","created":"2023-03-30","cited_by_count":137,"area":"diffusion"},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136,"area":"wm"},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118,"area":null},{"id":"2401.11605","title":"Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers","created":"2024-01-21","cited_by_count":118,"area":"diffusion"},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102,"area":null},{"id":"2110.13711","title":"Hierarchical Transformers Are More Efficient Language Models","created":"2021-10-26","cited_by_count":102,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98,"area":null},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98,"area":null},{"id":"2111.04734","title":"Mixed Transformer U-Net For Medical Image Segmentation","created":"2021-11-08","cited_by_count":95,"area":null},{"id":"2104.13897","title":"Inpainting Transformer for Anomaly Detection","created":"2021-04-28","cited_by_count":91,"area":null},{"id":"2102.04432","title":"Colorization Transformer","created":"2021-02-08","cited_by_count":89,"area":null},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88,"area":null},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84,"area":null},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84,"area":"ssm"},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83,"area":null},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71,"area":null},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2107.02368","title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","created":"2021-07-06","cited_by_count":61,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2106.07631","title":"Improved Transformer for High-Resolution GANs","created":"2021-06-14","cited_by_count":59,"area":null},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51,"area":null},{"id":"2102.13645","title":"Convolution-Free Medical Image Segmentation using Transformers","created":"2021-02-26","cited_by_count":49,"area":null},{"id":"2305.18415","title":"Geometric Algebra Transformer","created":"2023-05-28","cited_by_count":48,"area":null},{"id":"2107.11906","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","created":"2021-07-25","cited_by_count":47,"area":null},{"id":"2210.01820","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2301.13366","title":"CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects","created":"2023-01-31","cited_by_count":43,"area":null},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42,"area":null},{"id":"2310.05900","title":"Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network","created":"2023-10-09","cited_by_count":42,"area":null},{"id":"2212.08710","title":"JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving","created":"2022-12-16","cited_by_count":40,"area":"driving"},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2112.04653","title":"Extending nn-UNet for brain tumor segmentation","created":"2021-12-09","cited_by_count":36,"area":null},{"id":"2205.05076","title":"Reduce Information Loss in Transformers for Pluralistic Image Inpainting","created":"2022-05-10","cited_by_count":36,"area":null},{"id":"2209.09475","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","created":"2022-09-20","cited_by_count":36,"area":null},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2402.14396","title":"Quantum Circuit Optimization with AlphaTensor","created":"2024-02-22","cited_by_count":36,"area":null},{"id":"2511.15684","title":"Walrus: A Cross-Domain Foundation Model for Continuum Dynamics","created":"2025-11-19","cited_by_count":36,"area":null},{"id":"2208.14876","title":"NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation","created":"2022-08-31","cited_by_count":34,"area":null},{"id":"2305.17431","title":"Towards Consistent Video Editing with Text-to-Image Diffusion Models","created":"2023-05-27","cited_by_count":34,"area":"diffusion"},{"id":"2409.09811","title":"PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics","created":"2024-09-15","cited_by_count":34,"area":null},{"id":"2103.00879","title":"DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection","created":"2021-03-01","cited_by_count":32,"area":null},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32,"area":null},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32,"area":null},{"id":"2505.24717","title":"PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations","created":"2025-05-30","cited_by_count":32,"area":null},{"id":"2109.15142","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","created":"2021-09-30","cited_by_count":31,"area":null},{"id":"2404.09178","title":"HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images","created":"2024-04-14","cited_by_count":30,"area":null},{"id":"2308.05731","title":"The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2205.08473","title":"ColonFormer: An Efficient Transformer based Method for Colon Polyp Segmentation","created":"2022-05-17","cited_by_count":28,"area":null},{"id":"2207.09840","title":"EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer","created":"2022-07-20","cited_by_count":28,"area":null},{"id":"2304.03834","title":"WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting","created":"2023-04-07","cited_by_count":28,"area":null},{"id":"2306.14066","title":"SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models","created":"2023-06-24","cited_by_count":28,"area":"diffusion"},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27,"area":null},{"id":"2403.07187","title":"UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation","created":"2024-03-11","cited_by_count":27,"area":null},{"id":"2106.10637","title":"More than Encoder: Introducing Transformer Decoder to Upsample","created":"2021-06-20","cited_by_count":26,"area":null}],"next_cursor":"100"}