{"total":388,"rows":[{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724,"area":null},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565,"area":null},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192,"area":null},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2204.05088","title":"M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","created":"2022-04-11","cited_by_count":156,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2208.11112","title":"DeepInteraction: 3D Object Detection via Modality Interaction","created":"2022-08-23","cited_by_count":125,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"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":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117,"area":null},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117,"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":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2203.03373","title":"Adversarial Texture for Fooling Person Detectors in the Physical World","created":"2022-03-07","cited_by_count":96,"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":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","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":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76,"area":null},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74,"area":null},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"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":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2203.14415","title":"Mugs: A Multi-Granular Self-Supervised Learning Framework","created":"2022-03-27","cited_by_count":54,"area":null},{"id":"2307.00764","title":"Hierarchical Open-vocabulary Universal Image Segmentation","created":"2023-07-03","cited_by_count":54,"area":null},{"id":"2207.14381","title":"Pro-tuning: Unified Prompt Tuning for Vision Tasks","created":"2022-07-28","cited_by_count":53,"area":null},{"id":"2103.16368","title":"Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection","created":"2021-03-29","cited_by_count":49,"area":null},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43,"area":null},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43,"area":null},{"id":"2310.08584","title":"Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video","created":"2023-10-12","cited_by_count":40,"area":null},{"id":"2111.00674","title":"Distilling Object Detectors with Feature Richness","created":"2021-11-01","cited_by_count":38,"area":null},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2205.15242","title":"Re-parameterizing Your Optimizers rather than Architectures","created":"2022-05-30","cited_by_count":35,"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":"2307.12730","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","created":"2023-07-24","cited_by_count":34,"area":null},{"id":"2204.02964","title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2305.02187","title":"CLUSTSEG: Clustering for Universal Segmentation","created":"2023-05-03","cited_by_count":32,"area":null},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32,"area":null},{"id":"2106.05681","title":"A Dataset And Benchmark Of Underwater Object Detection For Robot Picking","created":"2021-06-10","cited_by_count":31,"area":null},{"id":"2108.07020","title":"Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark","created":"2021-08-16","cited_by_count":31,"area":null},{"id":"2203.15371","title":"mc-BEiT: Multi-choice Discretization for Image BERT Pre-training","created":"2022-03-29","cited_by_count":31,"area":null},{"id":"2210.05174","title":"BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation","created":"2022-10-11","cited_by_count":31,"area":null},{"id":"2301.08571","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","created":"2023-01-20","cited_by_count":31,"area":null},{"id":"2303.17099","title":"BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation","created":"2023-03-30","cited_by_count":31,"area":null},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"area":null},{"id":"2406.09410","title":"STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery","created":"2024-06-13","cited_by_count":31,"area":null},{"id":"2203.09056","title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","created":"2022-03-17","cited_by_count":30,"area":null},{"id":"2207.02255","title":"OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers","created":"2022-07-05","cited_by_count":30,"area":null},{"id":"2108.03553","title":"Self-Adversarial Disentangling for Specific Domain Adaptation","created":"2021-08-08","cited_by_count":29,"area":null},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2110.04886","title":"Multi-Class Cell Detection Using Spatial Context Representation","created":"2021-10-10","cited_by_count":24,"area":null},{"id":"2308.03594","title":"FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision","created":"2023-08-07","cited_by_count":22,"area":null},{"id":"2403.11694","title":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","created":"2024-03-18","cited_by_count":22,"area":null},{"id":"2104.04782","title":"Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation","created":"2021-04-10","cited_by_count":21,"area":null},{"id":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21,"area":null},{"id":"2203.13427","title":"Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?","created":"2022-03-25","cited_by_count":21,"area":null},{"id":"2208.00928","title":"OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images","created":"2022-08-01","cited_by_count":21,"area":null},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"area":null},{"id":"2205.15562","title":"iFS-RCNN: An Incremental Few-shot Instance Segmenter","created":"2022-05-31","cited_by_count":19,"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":"2405.08768","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","created":"2024-05-14","cited_by_count":18,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2203.00871","title":"Dense Voxel Fusion for 3D Object Detection","created":"2022-03-02","cited_by_count":17,"area":null},{"id":"2208.10043","title":"Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning","created":"2022-08-22","cited_by_count":17,"area":null},{"id":"2210.00911","title":"Learning Equivariant Segmentation with Instance-Unique Querying","created":"2022-10-03","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2312.02481","title":"Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2412.16955","title":"NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors","created":"2024-12-22","cited_by_count":17,"area":null},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2401.10731","title":"Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2401.11874","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","created":"2024-01-22","cited_by_count":15,"area":null},{"id":"2406.04426","title":"DeTra: A Unified Model for Object Detection and Trajectory Forecasting","created":"2024-06-06","cited_by_count":15,"area":null}],"next_cursor":"100"}