{"total":79,"rows":[{"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":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"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":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"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":"2312.17118","title":"Fully Sparse 3D Occupancy Prediction","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"area":null},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48,"area":null},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"area":null},{"id":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42,"area":null},{"id":"2308.10445","title":"When Prompt-based Incremental Learning Does Not Meet Strong Pretraining","created":"2023-08-21","cited_by_count":41,"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":"2403.07746","title":"Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2209.13959","title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding","created":"2022-09-28","cited_by_count":29,"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":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","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":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"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":"2412.12725","title":"RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion","created":"2024-12-17","cited_by_count":19,"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":"2407.11499","title":"Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection","created":"2024-07-16","cited_by_count":16,"area":"distill"},{"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":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10,"area":null},{"id":"2409.19648","title":"OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images","created":"2024-09-29","cited_by_count":10,"area":null},{"id":"2304.03768","title":"SparseFormer: Sparse Visual Recognition via Limited Latent Tokens","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2407.14923","title":"RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies","created":"2024-07-20","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":"2503.10152","title":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection","created":"2025-03-13","cited_by_count":9,"area":"mllm"},{"id":"2203.17020","title":"Logit Normalization for Long-tail Object Detection","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2212.12977","title":"SMMix: Self-Motivated Image Mixing for Vision Transformers","created":"2022-12-26","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":"2411.10922","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","created":"2024-11-17","cited_by_count":8,"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":"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":"2310.05989","title":"QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contexts","created":"2023-10-07","cited_by_count":5,"area":null},{"id":"2403.04303","title":"LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking","created":"2024-03-07","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":"2407.11433","title":"CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generation","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"id":"2409.06443","title":"Knowledge Distillation via Query Selection for Detection Transformer","created":"2024-09-10","cited_by_count":5,"area":"distill"},{"id":"2308.01904","title":"DETR Doesn't Need Multi-Scale or Locality Design","created":"2023-08-03","cited_by_count":4,"area":null},{"id":"2403.09212","title":"PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest","created":"2024-03-14","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":"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":"2401.14729","title":"Sketch and Refine: Towards Fast and Accurate Lane Detection","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2512.23635","title":"Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2602.11007","title":"LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2411.10715","title":"EVT: Efficient View Transformation for Multi-Modal 3D Object Detection","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2504.05601","title":"AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classes","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2303.04253","title":"TMHOI: Translational Model for Human-Object Interaction Detection","created":"2023-03-07","cited_by_count":1,"area":null},{"id":"2312.10983","title":"MatchDet: A Collaborative Framework for Image Matching and Object Detection","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2405.18857","title":"SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2412.10028","title":"Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts","created":"2024-12-13","cited_by_count":1,"area":"moe"},{"id":"2504.01383","title":"v-CLR: View-Consistent Learning for Open-World Instance Segmentation","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2602.13003","title":"MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2205.08714","title":"End-to-End Multi-Object Detection with a Regularized Mixture Model","created":"2022-05-18","cited_by_count":0,"area":null},{"id":"2309.16306","title":"Can the Query-based Object Detector Be Designed with Fewer Stages?","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2310.06470","title":"Focus on Local Regions for Query-based Object Detection","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2402.17207","title":"Deployment Prior Injection for Run-time Calibratable Object Detection","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2404.09842","title":"STMixer: A One-Stage Sparse Action Detector","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2409.01573","title":"Improving Apple Object Detection with Occlusion-Enhanced Distillation","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2409.18408","title":"Query matching for spatio-temporal action detection with query-based object detector","created":"2024-09-27","cited_by_count":0,"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":"2503.08992","title":"Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection","created":"2025-03-12","cited_by_count":0,"area":"ssm"},{"id":"2506.10242","title":"DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.12324","title":"UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2511.11824","title":"SOTFormer: A Minimal Transformer for Unified Object Tracking and Trajectory Prediction","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.08247","title":"Distilling Future Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection","created":"2025-12-09","cited_by_count":0,"area":"distill"},{"id":"2512.18187","title":"ALIGN: Advanced Query Initialization with LiDAR-Image Guidance for Occlusion-Robust 3D Object Detection","created":"2025-12-20","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":"2603.21820","title":"Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion","created":"2026-03-23","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}],"next_cursor":null}