{"total":711,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234,"area":null},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351,"area":null},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152,"area":null},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087,"area":null},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"area":null},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751,"area":null},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616,"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":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565,"area":null},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514,"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":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381,"area":null},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352,"area":null},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352,"area":null},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344,"area":null},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327,"area":null},{"id":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316,"area":null},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297,"area":null},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295,"area":null},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2104.00678","title":"Group-Free 3D Object Detection via Transformers","created":"2021-04-01","cited_by_count":215,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2102.04803","title":"DetCo: Unsupervised Contrastive Learning for Object Detection","created":"2021-02-09","cited_by_count":205,"area":null},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182,"area":null},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166,"area":null},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157,"area":null},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"area":null},{"id":"2211.11317","title":"DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection","created":"2022-11-21","cited_by_count":154,"area":null},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152,"area":null},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151,"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":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148,"area":null},{"id":"2206.15398","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","created":"2022-06-30","cited_by_count":147,"area":null},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142,"area":null},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131,"area":null},{"id":"2305.17382","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","created":"2023-05-27","cited_by_count":130,"area":null},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128,"area":null},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2210.04620","title":"FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings","created":"2022-10-10","cited_by_count":125,"area":null},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123,"area":null},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122,"area":null},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2301.07673","title":"OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models","created":"2023-01-18","cited_by_count":115,"area":null},{"id":"2106.02637","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","created":"2021-06-04","cited_by_count":110,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2203.14506","title":"Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection","created":"2022-03-28","cited_by_count":104,"area":null},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103,"area":null},{"id":"2202.12181","title":"FreeSOLO: Learning to Segment Objects without Annotations","created":"2022-02-24","cited_by_count":102,"area":null},{"id":"2110.05474","title":"Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning","created":"2021-10-11","cited_by_count":101,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96,"area":null},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93,"area":null},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91,"area":null},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91,"area":null},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87,"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":"2104.03775","title":"Geometry-based Distance Decomposition for Monocular 3D Object Detection","created":"2021-04-08","cited_by_count":84,"area":null},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2304.14340","title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection","created":"2023-04-27","cited_by_count":83,"area":null},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79,"area":null},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79,"area":null},{"id":"2106.04550","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","created":"2021-06-08","cited_by_count":76,"area":null},{"id":"2305.11733","title":"Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment","created":"2023-05-19","cited_by_count":75,"area":null},{"id":"2104.11896","title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","created":"2021-04-24","cited_by_count":74,"area":null},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74,"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":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71,"area":null},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70,"area":null},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70,"area":null}],"next_cursor":"100"}