{"total":150,"rows":[{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332,"area":null},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929,"area":"wm"},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274,"area":null},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193,"area":null},{"id":"2308.09244","title":"SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos","created":"2023-08-18","cited_by_count":150,"area":null},{"id":"2303.13076","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","created":"2023-03-23","cited_by_count":133,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"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":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74,"area":null},{"id":"2301.01283","title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","created":"2023-01-03","cited_by_count":70,"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":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56,"area":null},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53,"area":null},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"area":null},{"id":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","cited_by_count":46,"area":null},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"area":null},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2211.10156","title":"DETRDistill: A Universal Knowledge Distillation Framework for DETR-families","created":"2022-11-17","cited_by_count":36,"area":"distill"},{"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":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2308.04409","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","created":"2023-08-08","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":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"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":"2409.00620","title":"Enhancing Vectorized Map Perception with Historical Rasterized Maps","created":"2024-09-01","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":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2503.01342","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2212.07289","title":"ConQueR: Query Contrast Voxel-DETR for 3D Object Detection","created":"2022-12-14","cited_by_count":21,"area":null},{"id":"2305.12724","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","created":"2023-05-22","cited_by_count":20,"area":null},{"id":"2212.07593","title":"Enhanced Training of Query-Based Object Detection via Selective Query Recollection","created":"2022-12-15","cited_by_count":18,"area":null},{"id":"2211.09768","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","created":"2022-11-17","cited_by_count":17,"area":"distill"},{"id":"2312.05760","title":"RepViT-SAM: Towards Real-Time Segmenting Anything","created":"2023-12-10","cited_by_count":17,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15,"area":"diffusion"},{"id":"2401.06704","title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","created":"2024-01-12","cited_by_count":14,"area":null},{"id":"2404.01819","title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2410.11301","title":"Open World Object Detection: A Survey","created":"2024-10-15","cited_by_count":13,"area":null},{"id":"2410.19635","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","created":"2024-10-25","cited_by_count":13,"area":null},{"id":"2306.17602","title":"S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations","created":"2023-06-30","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":"2403.17709","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","created":"2024-03-26","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":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2507.18300","title":"LMM-Det: Make Large Multimodal Models Excel in Object Detection","created":"2025-07-24","cited_by_count":10,"area":"mllm"},{"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":"2312.04519","title":"Bootstrapping Autonomous Driving Radars with Self-Supervised Learning","created":"2023-12-07","cited_by_count":9,"area":null},{"id":"2403.04309","title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection","created":"2024-03-07","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":"2305.18969","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2306.07265","title":"detrex: Benchmarking Detection Transformers","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2310.15955","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8,"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":"2305.19957","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2308.07743","title":"ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2409.11325","title":"TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2211.11953","title":"Teach-DETR: Better Training DETR with Teachers","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2307.12239","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","created":"2023-07-23","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":"2311.15776","title":"Stable Segment Anything Model","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2402.16370","title":"DEYO: DETR with YOLO for End-to-End Object Detection","created":"2024-02-26","cited_by_count":6,"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":"2305.00675","title":"End-to-End Lane detection with One-to-Several Transformer","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2308.01300","title":"Revisiting DETR Pre-training for Object Detection","created":"2023-08-02","cited_by_count":5,"area":null},{"id":"2401.07641","title":"SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2404.07603","title":"GLID: Pre-training a Generalist Encoder-Decoder Vision Model","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2405.00187","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","created":"2024-04-30","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":"2412.18951","title":"TopoBDA: Towards Bezier Deformable Attention for Road Topology Understanding","created":"2024-12-25","cited_by_count":5,"area":null},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5,"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":"2308.01904","title":"DETR Doesn't Need Multi-Scale or Locality Design","created":"2023-08-03","cited_by_count":4,"area":null},{"id":"2405.04971","title":"End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2407.08460","title":"Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2407.15354","title":"Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2505.20639","title":"Open-Det: An Efficient Learning Framework for Open-Ended Detection","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.11090","title":"Source-Free Object Detection with Detection Transformer","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2603.06917","title":"PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection","created":"2026-03-06","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":"2308.03747","title":"Mask Frozen-DETR: High Quality Instance Segmentation with One GPU","created":"2023-08-07","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":"2501.16665","title":"CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2502.05843","title":"From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning","created":"2025-02-09","cited_by_count":3,"area":"lr"},{"id":"2503.03088","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.06313","title":"Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane Detection","created":"2025-03-08","cited_by_count":3,"area":"driving"},{"id":"2503.06515","title":"SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2504.19574","title":"DG-DETR: Toward Domain Generalized Detection Transformer","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2507.01397","title":"Coherent Online Road Topology Estimation and Reasoning with Standard-Definition Maps","created":"2025-07-02","cited_by_count":3,"area":null}],"next_cursor":"100"}