{"total":129,"rows":[{"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":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518,"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":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"area":null},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"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":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152,"area":null},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135,"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":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109,"area":null},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105,"area":null},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78,"area":null},{"id":"2103.16054","title":"3D-MAN: 3D Multi-frame Attention Network for Object Detection","created":"2021-03-30","cited_by_count":73,"area":null},{"id":"2107.09609","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","created":"2021-07-20","cited_by_count":72,"area":null},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72,"area":null},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70,"area":null},{"id":"2204.07335","title":"A Keypoint-based Global Association Network for Lane Detection","created":"2022-04-15","cited_by_count":68,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2201.08959","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","created":"2022-01-22","cited_by_count":62,"area":null},{"id":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58,"area":null},{"id":"2109.06085","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","created":"2021-09-13","cited_by_count":54,"area":null},{"id":"2206.10965","title":"Polar Parametrization for Vision-based Surround-View 3D Detection","created":"2022-06-22","cited_by_count":53,"area":null},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2109.01066","title":"4D-Net for Learned Multi-Modal Alignment","created":"2021-09-02","cited_by_count":44,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","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":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42,"area":null},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40,"area":null},{"id":"2303.08594","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","created":"2023-03-15","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":"2210.05174","title":"BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation","created":"2022-10-11","cited_by_count":31,"area":null},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30,"area":null},{"id":"2102.00813","title":"About Face: A Survey of Facial Recognition Evaluation","created":"2021-02-01","cited_by_count":27,"area":null},{"id":"2211.14157","title":"Learning 3D Scene Priors with 2D Supervision","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2409.13401","title":"PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images","created":"2024-09-20","cited_by_count":24,"area":null},{"id":"2103.01415","title":"A Survey of Deep Learning Techniques for Weed Detection from Images","created":"2021-03-02","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":"2308.09887","title":"Calibrating Uncertainty for Semi-Supervised Crowd Counting","created":"2023-08-19","cited_by_count":22,"area":null},{"id":"2105.13073","title":"Maria: A Visual Experience Powered Conversational Agent","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2111.12193","title":"Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation","created":"2021-11-23","cited_by_count":17,"area":null},{"id":"2205.02536","title":"YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression","created":"2022-05-05","cited_by_count":17,"area":null},{"id":"2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","created":"2022-09-06","cited_by_count":17,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2210.03953","title":"Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation","created":"2022-10-08","cited_by_count":16,"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":"2206.05717","title":"Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2211.03373","title":"BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction","created":"2022-11-07","cited_by_count":12,"area":null},{"id":"2309.04682","title":"DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions","created":"2023-09-09","cited_by_count":12,"area":null},{"id":"2407.10084","title":"Part2Object: Hierarchical Unsupervised 3D Instance Segmentation","created":"2024-07-14","cited_by_count":12,"area":null},{"id":"2108.00584","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","created":"2021-08-02","cited_by_count":11,"area":null},{"id":"2206.03431","title":"Self-supervised Domain Adaptation in Crowd Counting","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2305.00397","title":"TransCAR: Transformer-based Camera-And-Radar Fusion for 3D Object Detection","created":"2023-04-30","cited_by_count":11,"area":null},{"id":"2105.02039","title":"Towards an efficient framework for Data Extraction from Chart Images","created":"2021-05-05","cited_by_count":10,"area":null},{"id":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2302.11703","title":"fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Tasks","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2203.10719","title":"LocATe: End-to-end Localization of Actions in 3D with Transformers","created":"2022-03-21","cited_by_count":8,"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":"2301.03033","title":"RGB-T Multi-Modal Crowd Counting Based on Transformer","created":"2023-01-08","cited_by_count":7,"area":null},{"id":"2309.08020","title":"Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2406.14878","title":"MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection","created":"2024-06-21","cited_by_count":7,"area":null},{"id":"2101.11782","title":"Object Detection Made Simpler by Eliminating Heuristic NMS","created":"2021-01-28","cited_by_count":6,"area":null},{"id":"2307.06118","title":"TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image","created":"2023-07-12","cited_by_count":6,"area":null},{"id":"2310.10861","title":"SoybeanNet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (UAV) Images","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2102.11865","title":"Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps","created":"2021-02-23","cited_by_count":5,"area":null},{"id":"2203.03187","title":"Knowledge Amalgamation for Object Detection with Transformers","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2205.14659","title":"Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting","created":"2022-05-29","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":"2309.14492","title":"AiAReSeg: Catheter Detection and Segmentation in Interventional Ultrasound using Transformers","created":"2023-09-25","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":"2405.11770","title":"Learning Spatial Similarity Distribution for Few-shot Object Counting","created":"2024-05-20","cited_by_count":5,"area":null},{"id":"2406.13891","title":"DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2206.06258","title":"Featurized Query R-CNN","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2209.05809","title":"Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection","created":"2022-09-13","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":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2312.17686","title":"Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2407.10131","title":"WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models","created":"2024-07-14","cited_by_count":4,"area":null},{"id":"2506.03237","title":"UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2110.04727","title":"LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2209.10391","title":"IoU-Enhanced Attention for End-to-End Task Specific Object Detection","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2305.10801","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2305.12414","title":"Real-time Aerial Detection and Reasoning on Embedded-UAVs","created":"2023-05-21","cited_by_count":3,"area":null},{"id":"2307.11550","title":"YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2502.18745","title":"MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Clouds","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2104.03106","title":"V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2205.12646","title":"UniInst: Unique Representation for End-to-End Instance Segmentation","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2408.09734","title":"Mutually-Aware Feature Learning for Few-Shot Object Counting","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2604.10094","title":"Global monitoring of methane point sources using deep learning on hyperspectral radiance measurements from EMIT","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2105.00357","title":"RotLSTM: Rotating Memories in Recurrent Neural Networks","created":"2021-05-01","cited_by_count":1,"area":null},{"id":"2108.09691","title":"Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads","created":"2021-08-22","cited_by_count":1,"area":null},{"id":"2110.07511","title":"Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2206.00960","title":"SparseDet: Towards End-to-End 3D Object Detection","created":"2022-06-02","cited_by_count":1,"area":null}],"next_cursor":"100"}