{"total":88,"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":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2312.01919","title":"COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction","created":"2023-12-04","cited_by_count":96,"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":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"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":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","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":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2211.03594","title":"Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining","created":"2022-11-07","cited_by_count":25,"area":null},{"id":"2305.15377","title":"Uncovering and Quantifying Social Biases in Code Generation","created":"2023-05-24","cited_by_count":25,"area":null},{"id":"2305.16233","title":"Interactive Segment Anything NeRF with Feature Imitation","created":"2023-05-25","cited_by_count":24,"area":null},{"id":"2410.19590","title":"MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors","created":"2024-10-25","cited_by_count":22,"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":"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":"2407.17378","title":"PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction","created":"2024-07-24","cited_by_count":12,"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":"2405.15995","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","created":"2024-05-25","cited_by_count":10,"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":"2412.14233","title":"Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2505.04594","title":"Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection","created":"2025-05-07","cited_by_count":10,"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":"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":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8,"area":null},{"id":"2509.13747","title":"Improving Generalized Visual Grounding with Instance-aware Joint Learning","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2401.07323","title":"MapNeXt: Revisiting Training and Scaling Practices for Online Vectorized HD Map Construction","created":"2024-01-14","cited_by_count":6,"area":null},{"id":"2405.10148","title":"SpecDETR: A transformer-based hyperspectral point object detection network","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2304.03580","title":"Language-aware Multiple Datasets Detection Pretraining for DETRs","created":"2023-04-07","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":"2305.16253","title":"Uncovering and Categorizing Social Biases in Text-to-SQL","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2311.17902","title":"Language-conditioned Detection Transformer","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2406.15320","title":"Rethinking Remote Sensing Change Detection With A Mask View","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2407.09920","title":"MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection","created":"2024-07-13","cited_by_count":5,"area":null},{"id":"2302.10707","title":"Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios","created":"2023-02-21","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":"2412.02054","title":"Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2504.03258","title":"TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2506.13457","title":"Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art","created":"2025-06-16","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":"2303.10967","title":"Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2405.04955","title":"Improving Long Text Understanding with Knowledge Distilled from Summarization Model","created":"2024-05-08","cited_by_count":3,"area":null},{"id":"2406.03917","title":"Frequency-based Matcher for Long-tailed Semantic Segmentation","created":"2024-06-06","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":"2512.13876","title":"Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2312.11578","title":"Diffusion-Based Particle-DETR for BEV Perception","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2405.07481","title":"Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2405.19765","title":"Towards Unified Multi-granularity Text Detection with Interactive Attention","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2406.03176","title":"MMCL: Correcting Content Query Distributions for Improved Anti-Overlapping X-Ray Object Detection","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2411.06780","title":"SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking","created":"2024-11-11","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":"2601.09247","title":"Integrating Diverse Assignment Strategies into DETRs","created":"2026-01-14","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":"2603.01007","title":"Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.01485","title":"SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2309.03110","title":"Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2311.17978","title":"AutArch: An AI-assisted workflow for object detection and automated recording in archaeological catalogues","created":"2023-11-29","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":"2407.16955","title":"DVPE: Divided View Position Embedding for Multi-View 3D Object Detection","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2412.20816","title":"MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2501.05687","title":"UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation","created":"2025-01-10","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":"2605.08911","title":"Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.09367","title":"RT-SDGOD: Real-Time Single-Domain Generalized Object Detection","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.23431","title":"HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2411.10497","title":"Structure Tensor Representation for Robust Oriented Object Detection","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2506.03675","title":"BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.14835","title":"MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillation","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.03564","title":"2.5D Object Detection for Intelligent Roadside Infrastructure","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2507.13085","title":"Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.09157","title":"RT-DETR++ for UAV Object Detection","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2601.01036","title":"Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2602.13728","title":"Explore Intrinsic Geometry for Query-based Tiny and Oriented Object Detector with Momentum-based Bipartite Matching","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.01524","title":"Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.01847","title":"GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.02363","title":"Beyond Caption-Based Queries for Video Moment Retrieval","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.02924","title":"HDINO: A Concise and Efficient Open-Vocabulary Detector","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2607.06176","title":"Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14717","title":"Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.01787","title":"CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.26092","title":"Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.05191","title":"Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19071","title":"MonoMIP: Multi-Height Inverse Perspective Mapping for Monocular 3D Object Detection","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}