{"total":119,"rows":[{"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573,"area":null},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"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":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103,"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":"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":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"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":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"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":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58,"area":null},{"id":"2403.15241","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","created":"2024-03-22","cited_by_count":57,"area":null},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"area":null},{"id":"2301.02364","title":"Object as Query: Lifting any 2D Object Detector to 3D Detection","created":"2023-01-06","cited_by_count":38,"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":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36,"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":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","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":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31,"area":null},{"id":"2403.00326","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2208.04921","title":"TSRFormer: Table Structure Recognition with Transformers","created":"2022-08-09","cited_by_count":27,"area":null},{"id":"2307.08095","title":"Semi-DETR: Semi-Supervised Object Detection with Detection Transformers","created":"2023-07-16","cited_by_count":27,"area":null},{"id":"2403.07284","title":"SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection","created":"2024-03-12","cited_by_count":25,"area":null},{"id":"2302.13372","title":"Localizing Moments in Long Video Via Multimodal Guidance","created":"2023-02-26","cited_by_count":23,"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":"2212.07849","title":"DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention","created":"2022-12-15","cited_by_count":21,"area":null},{"id":"2303.12079","title":"OmniTracker: Unifying Object Tracking by Tracking-with-Detection","created":"2023-03-21","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":"2204.01244","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","created":"2022-04-04","cited_by_count":16,"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":"2209.10733","title":"FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection","created":"2022-09-22","cited_by_count":14,"area":null},{"id":"2302.11481","title":"Transformer-Based Sensor Fusion for Autonomous Driving: A Survey","created":"2023-02-22","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":"2308.11093","title":"Video OWL-ViT: Temporally-consistent open-world localization in video","created":"2023-08-22","cited_by_count":13,"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":"2303.11615","title":"Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer","created":"2023-03-21","cited_by_count":12,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"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":"2306.01738","title":"OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10,"area":null},{"id":"2303.13561","title":"MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2503.01463","title":"MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","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":"2411.13753","title":"FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2203.05122","title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","created":"2022-03-10","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":"2208.14586","title":"Few-shot Adaptive Object Detection with Cross-Domain CutMix","created":"2022-08-31","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},{"id":"2306.13526","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2207.10774","title":"Focused Decoding Enables 3D Anatomical Detection by Transformers","created":"2022-07-21","cited_by_count":6,"area":null},{"id":"2308.09242","title":"ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation","created":"2023-08-18","cited_by_count":6,"area":null},{"id":"2403.14270","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","created":"2024-03-21","cited_by_count":6,"area":null},{"id":"2203.12944","title":"Transformers Meet Visual Learning Understanding: A Comprehensive Review","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2206.06829","title":"Efficient Decoder-free Object Detection with Transformers","created":"2022-06-14","cited_by_count":5,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2406.05791","title":"OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2408.06123","title":"DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2206.01232","title":"What Are Expected Queries in End-to-End Object Detection?","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2206.06258","title":"Featurized Query R-CNN","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2211.13859","title":"DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2509.23867","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2306.09165","title":"DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2307.13619","title":"RecursiveDet: End-to-End Region-based Recursive Object Detection","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2404.03819","title":"Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2502.19769","title":"QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2503.05492","title":"FastMap: Fast Queries Initialization Based Vectorized HD Map Reconstruction Framework","created":"2025-03-07","cited_by_count":3,"area":null},{"id":"2307.08353","title":"Box-DETR: Understanding and Boxing Conditional Spatial Queries","created":"2023-07-17","cited_by_count":2,"area":null},{"id":"2310.10353","title":"Multimodal Object Query Initialization for 3D Object Detection","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2405.17677","title":"Understanding differences in applying DETR to natural and medical images","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2412.19155","title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2507.13880","title":"Real-Time Fusion of Visual and Chart Data for Enhanced Maritime Vision","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2602.22595","title":"Don't let the information slip away","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2209.01620","title":"MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition","created":"2022-08-31","cited_by_count":1,"area":null},{"id":"2212.02687","title":"Vision Transformer Computation and Resilience for Dynamic Inference","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2308.14075","title":"FaceCoresetNet: Differentiable Coresets for Face Set Recognition","created":"2023-08-27","cited_by_count":1,"area":null},{"id":"2401.12835","title":"SGTR+: End-to-end Scene Graph Generation with Transformer","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2404.14657","title":"Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2405.01258","title":"Towards Consistent Object Detection via LiDAR-Camera Synergy","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2405.15176","title":"MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2406.17654","title":"MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2412.18718","title":"Evaluating the Adversarial Robustness of Detection Transformers","created":"2024-12-25","cited_by_count":1,"area":null},{"id":"2503.04107","title":"Fractional Correspondence Framework in Detection Transformer","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2508.18896","title":"DQEN: Dual Query Enhancement Network for DETR-based HOI Detection","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.06969","title":"Learning Global Representation from Queries for Vectorized HD Map Construction","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.15026","title":"MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning","created":"2025-10-16","cited_by_count":1,"area":null}],"next_cursor":"100"}