{"total":567,"rows":[{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633,"area":null},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"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":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152,"area":null},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","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":"2209.13929","title":"Attention Spiking Neural Networks","created":"2022-09-28","cited_by_count":107,"area":null},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105,"area":null},{"id":"2404.03663","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","created":"2024-02-15","cited_by_count":103,"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":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95,"area":null},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89,"area":null},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89,"area":null},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80,"area":null},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2207.08132","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","created":"2022-07-17","cited_by_count":76,"area":null},{"id":"2305.03273","title":"Semantic Segmentation using Vision Transformers: A survey","created":"2023-05-05","cited_by_count":73,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2302.13485","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70,"area":null},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68,"area":null},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2203.03821","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","created":"2022-03-08","cited_by_count":63,"area":null},{"id":"2308.05659","title":"AD-CLIP: Adapting Domains in Prompt Space Using CLIP","created":"2023-08-10","cited_by_count":62,"area":null},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61,"area":null},{"id":"2201.09206","title":"A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization","created":"2022-01-23","cited_by_count":57,"area":null},{"id":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57,"area":null},{"id":"2406.05074","title":"Hibou: A Family of Foundational Vision Transformers for Pathology","created":"2024-06-07","cited_by_count":57,"area":null},{"id":"2311.16510","title":"Source-Free Domain Adaptation with Frozen Multimodal Foundation Model","created":"2023-11-27","cited_by_count":55,"area":null},{"id":"2206.04425","title":"Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential","created":"2022-06-09","cited_by_count":54,"area":null},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2310.08956","title":"LRRU: Long-short Range Recurrent Updating Networks for Depth Completion","created":"2023-10-13","cited_by_count":49,"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":"2206.07349","title":"XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention","created":"2022-06-15","cited_by_count":46,"area":null},{"id":"2404.08978","title":"Incremental Residual Concept Bottleneck Models","created":"2024-04-13","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":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41,"area":null},{"id":"2304.05340","title":"Unified Multi-Modal Image Synthesis for Missing Modality Imputation","created":"2023-04-11","cited_by_count":40,"area":null},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2302.09251","title":"StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization","created":"2023-02-18","cited_by_count":36,"area":null},{"id":"2302.11329","title":"HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer","created":"2023-02-22","cited_by_count":35,"area":null},{"id":"2311.12454","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","created":"2023-11-21","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2310.03535","title":"Towards Unified Deep Image Deraining: A Survey and A New Benchmark","created":"2023-10-05","cited_by_count":34,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2411.17787","title":"Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient","created":"2024-11-26","cited_by_count":33,"area":null},{"id":"2205.07417","title":"Transformers in 3D Point Clouds: A Survey","created":"2022-05-16","cited_by_count":31,"area":null},{"id":"2209.10218","title":"HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification","created":"2022-09-21","cited_by_count":30,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2309.00121","title":"Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation","created":"2023-08-31","cited_by_count":30,"area":null},{"id":"2309.05282","title":"Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving","created":"2023-09-11","cited_by_count":30,"area":null},{"id":"2312.09299","title":"Weight subcloning: direct initialization of transformers using larger pretrained ones","created":"2023-12-14","cited_by_count":30,"area":null},{"id":"2402.00059","title":"FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting","created":"2024-01-28","cited_by_count":30,"area":null},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30,"area":null},{"id":"2112.11699","title":"Few-Shot Object Detection: A Comprehensive Survey","created":"2021-12-22","cited_by_count":29,"area":null},{"id":"2207.04976","title":"Dual Vision Transformer","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29,"area":null},{"id":"2310.03916","title":"Toward a Foundation Model for Time Series Data","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2306.17798","title":"Masked Contrastive Graph Representation Learning for Age Estimation","created":"2023-06-16","cited_by_count":27,"area":null},{"id":"2309.10356","title":"RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26,"area":null},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2207.07370","title":"CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer with Modality-Correlated Cross-Attention for Brain Tumor Segmentation","created":"2022-07-15","cited_by_count":24,"area":null},{"id":"2403.02579","title":"Geometric Dynamics of Signal Propagation Predict Trainability of Transformers","created":"2024-03-05","cited_by_count":24,"area":null},{"id":"2312.00634","title":"A Recent Survey of Vision Transformers for Medical Image Segmentation","created":"2023-12-01","cited_by_count":23,"area":null},{"id":"2503.24071","title":"From Colors to Classes: Emergence of Concepts in Vision Transformers","created":"2025-03-31","cited_by_count":23,"area":null},{"id":"2111.15637","title":"Building extraction with vision transformer","created":"2021-11-29","cited_by_count":22,"area":null},{"id":"2203.15269","title":"Vision Transformers in Medical Computer Vision -- A Contemplative Retrospection","created":"2022-03-29","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2308.04791","title":"PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer","created":"2023-08-09","cited_by_count":22,"area":null},{"id":"2309.17031","title":"Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2401.06960","title":"Transformer for Object Re-Identification: A Survey","created":"2024-01-13","cited_by_count":22,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2208.04309","title":"3D Vision with Transformers: A Survey","created":"2022-08-08","cited_by_count":21,"area":null},{"id":"2209.01578","title":"Spatial-Temporal Transformer for Video Snapshot Compressive Imaging","created":"2022-09-04","cited_by_count":21,"area":null},{"id":"2204.11448","title":"High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2205.12466","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2303.06471","title":"Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review","created":"2023-03-11","cited_by_count":20,"area":null},{"id":"2206.00826","title":"BayesFormer: Transformer with Uncertainty Estimation","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2209.03300","title":"Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising","created":"2022-09-07","cited_by_count":19,"area":null},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19,"area":null},{"id":"2303.14548","title":"Viewpoint Equivariance for Multi-View 3D Object Detection","created":"2023-03-25","cited_by_count":18,"area":null},{"id":"2305.10006","title":"EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging","created":"2023-05-17","cited_by_count":18,"area":null},{"id":"2309.16217","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","created":"2023-09-28","cited_by_count":18,"area":null}],"next_cursor":"100"}