{"total":305,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"area":null},{"id":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230,"area":null},{"id":"2104.00678","title":"Group-Free 3D Object Detection via Transformers","created":"2021-04-01","cited_by_count":215,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2103.00860","title":"Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation","created":"2021-03-01","cited_by_count":192,"area":null},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183,"area":null},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164,"area":null},{"id":"2108.06693","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","created":"2021-08-15","cited_by_count":159,"area":null},{"id":"2111.11837","title":"Focal and Global Knowledge Distillation for Detectors","created":"2021-11-23","cited_by_count":142,"area":"distill"},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"id":"2111.13216","title":"Cross-Domain Adaptive Teacher for Object Detection","created":"2021-11-25","cited_by_count":126,"area":"distill"},{"id":"2101.07296","title":"Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias","created":"2021-01-18","cited_by_count":118,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116,"area":null},{"id":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114,"area":"distill"},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"area":null},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2103.11402","title":"Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework","created":"2021-03-21","cited_by_count":113,"area":null},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98,"area":null},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94,"area":null},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87,"area":null},{"id":"2108.05988","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","created":"2021-08-12","cited_by_count":81,"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":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78,"area":null},{"id":"2103.16054","title":"3D-MAN: 3D Multi-frame Attention Network for Object Detection","created":"2021-03-30","cited_by_count":73,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null},{"id":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2103.00236","title":"Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection","created":"2021-02-27","cited_by_count":60,"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":"2203.06883","title":"Accelerating DETR Convergence via Semantic-Aligned Matching","created":"2022-03-14","cited_by_count":58,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2112.09791","title":"Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks","created":"2021-12-17","cited_by_count":55,"area":null},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55,"area":null},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52,"area":null},{"id":"2112.03553","title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","created":"2021-12-07","cited_by_count":48,"area":"distill"},{"id":"2208.00219","title":"Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation","created":"2022-07-30","cited_by_count":48,"area":null},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2205.01291","title":"Cross Domain Object Detection by Target-Perceived Dual Branch Distillation","created":"2022-05-03","cited_by_count":46,"area":"distill"},{"id":"2103.11731","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","created":"2021-03-22","cited_by_count":44,"area":null},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44,"area":null},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2208.00713","title":"TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation","created":"2022-08-01","cited_by_count":43,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"area":null},{"id":"2110.12724","title":"Instance-Conditional Knowledge Distillation for Object Detection","created":"2021-10-25","cited_by_count":42,"area":"distill"},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2107.05188","title":"TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation","created":"2021-07-12","cited_by_count":41,"area":null},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40,"area":null},{"id":"2207.05621","title":"MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing","created":"2022-07-12","cited_by_count":39,"area":null},{"id":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","cited_by_count":36,"area":null},{"id":"2104.10326","title":"A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation","created":"2021-04-21","cited_by_count":34,"area":null},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34,"area":null},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31,"area":null},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2210.07124","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","created":"2022-10-13","cited_by_count":31,"area":null},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30,"area":null},{"id":"2205.14882","title":"Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving","created":"2022-05-30","cited_by_count":30,"area":"driving"},{"id":"2108.12468","title":"Learning Inner-Group Relations on Point Clouds","created":"2021-08-27","cited_by_count":29,"area":null},{"id":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29,"area":null},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29,"area":null},{"id":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2207.10047","title":"Densely Constrained Depth Estimator for Monocular 3D Object Detection","created":"2022-07-20","cited_by_count":27,"area":null},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"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":"2407.08394","title":"Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers","created":"2024-07-11","cited_by_count":24,"area":"diffusion"},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23,"area":null}],"next_cursor":"100"}