{"total":156,"rows":[{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351,"area":null},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319,"area":null},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101,"area":null},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947,"area":null},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658,"area":null},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573,"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":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362,"area":null},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144,"area":null},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143,"area":null},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136,"area":null},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110,"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":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94,"area":null},{"id":"2203.13310","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","created":"2022-03-24","cited_by_count":86,"area":null},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79,"area":null},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78,"area":null},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2203.02636","title":"Boosting Crowd Counting via Multifaceted Attention","created":"2022-03-05","cited_by_count":73,"area":null},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"area":null},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65,"area":null},{"id":"2304.03110","title":"Continual Detection Transformer for Incremental Object Detection","created":"2023-04-06","cited_by_count":59,"area":"distill"},{"id":"2409.09350","title":"OPUS: Occupancy Prediction Using a Sparse Set","created":"2024-09-14","cited_by_count":56,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2308.04583","title":"LATR: 3D Lane Detection from Monocular Images with Transformer","created":"2023-08-08","cited_by_count":44,"area":null},{"id":"2105.04281","title":"Visual Grounding with Transformers","created":"2021-05-10","cited_by_count":42,"area":null},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2307.12612","title":"Less is More: Focus Attention for Efficient DETR","created":"2023-07-24","cited_by_count":38,"area":null},{"id":"2110.14711","title":"A Survey of Self-Supervised and Few-Shot Object Detection","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2201.00462","title":"D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation","created":"2022-01-03","cited_by_count":35,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"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":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","cited_by_count":33,"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":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2306.04557","title":"PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30,"area":null},{"id":"2105.11605","title":"TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2404.03507","title":"DQ-DETR: DETR with Dynamic Query for Tiny Object Detection","created":"2024-04-04","cited_by_count":28,"area":null},{"id":"2203.09064","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","created":"2022-03-17","cited_by_count":27,"area":null},{"id":"2208.04921","title":"TSRFormer: Table Structure Recognition with Transformers","created":"2022-08-09","cited_by_count":27,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2201.02526","title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","created":"2022-01-07","cited_by_count":25,"area":null},{"id":"2209.10904","title":"AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection","created":"2022-09-22","cited_by_count":25,"area":null},{"id":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25,"area":"moe"},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23,"area":null},{"id":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","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":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21,"area":null},{"id":"2207.08914","title":"Conditional DETR V2: Efficient Detection Transformer with Box Queries","created":"2022-07-18","cited_by_count":21,"area":null},{"id":"2211.11679","title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","created":"2022-11-21","cited_by_count":19,"area":null},{"id":"2212.05505","title":"Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection","created":"2022-12-11","cited_by_count":19,"area":null},{"id":"2307.11035","title":"Cascade-DETR: Delving into High-Quality Universal Object Detection","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2303.09735","title":"SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2502.11168","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2108.00205","title":"Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding","created":"2021-07-31","cited_by_count":16,"area":null},{"id":"2208.10035","title":"A Simple Baseline for Multi-Camera 3D Object Detection","created":"2022-08-22","cited_by_count":16,"area":null},{"id":"2209.02178","title":"Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students","created":"2022-09-06","cited_by_count":16,"area":null},{"id":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16,"area":"distill"},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2211.14710","title":"3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers","created":"2022-11-27","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":"2301.08965","title":"Raw or Cooked? Object Detection on RAW Images","created":"2023-01-21","cited_by_count":14,"area":null},{"id":"2211.08071","title":"KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2402.00033","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","created":"2024-01-08","cited_by_count":13,"area":null},{"id":"2105.03148","title":"A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approaches","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2203.00860","title":"D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2209.13948","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2303.11615","title":"Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer","created":"2023-03-21","cited_by_count":12,"area":null},{"id":"2310.14154","title":"Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection","created":"2023-10-22","cited_by_count":12,"area":null},{"id":"2205.02101","title":"Dynamic Sparse R-CNN","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2208.01838","title":"Re-Attention Transformer for Weakly Supervised Object Localization","created":"2022-08-03","cited_by_count":11,"area":null},{"id":"2312.12437","title":"Weakly Supervised Open-Vocabulary Object Detection","created":"2023-12-19","cited_by_count":11,"area":null},{"id":"2407.05358","title":"CPM: Class-conditional Prompting Machine for Audio-visual Segmentation","created":"2024-07-07","cited_by_count":11,"area":null},{"id":"2408.15178","title":"A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships","created":"2024-08-27","cited_by_count":11,"area":null},{"id":"2203.08612","title":"CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning","created":"2022-03-16","cited_by_count":10,"area":null},{"id":"2208.11356","title":"Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2206.09265","title":"SAViR-T: Spatially Attentive Visual Reasoning with Transformers","created":"2022-06-18","cited_by_count":9,"area":"lr"},{"id":"2211.02006","title":"SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2305.07270","title":"SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2302.10473","title":"Oriented object detection in optical remote sensing images using deep learning: a survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2310.14194","title":"Distractor-aware Event-based Tracking","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2111.12941","title":"Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation","created":"2021-11-25","cited_by_count":7,"area":null},{"id":"2207.14172","title":"Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2208.01195","title":"Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation","created":"2022-08-02","cited_by_count":7,"area":null},{"id":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","cited_by_count":7,"area":null}],"next_cursor":"100"}