{"total":2933,"rows":[{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906,"area":"mllm"},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"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":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"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":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503,"area":null},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447,"area":null},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388,"area":"mllm"},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349,"area":null},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318,"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":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297,"area":null},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290,"area":null},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274,"area":null},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243,"area":null},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232,"area":null},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231,"area":null},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230,"area":null},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225,"area":"diffusion"},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223,"area":"mllm"},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220,"area":null},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209,"area":null},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"area":null},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203,"area":null},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2304.03284","title":"SegGPT: Segmenting Everything In Context","created":"2023-04-06","cited_by_count":194,"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":"2107.14160","title":"Probabilistic and Geometric Depth: Detecting Objects in Perspective","created":"2021-07-29","cited_by_count":191,"area":null},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190,"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":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"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":"2212.11548","title":"Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method","created":"2022-12-22","cited_by_count":174,"area":null},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170,"area":null},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169,"area":"driving"},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"area":null},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166,"area":null},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"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":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153,"area":null},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"area":null},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2403.12580","title":"Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection","created":"2024-03-19","cited_by_count":139,"area":null},{"id":"2106.13430","title":"Subgraph Federated Learning with Missing Neighbor Generation","created":"2021-06-25","cited_by_count":132,"area":null},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130,"area":null},{"id":"2212.00785","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","created":"2022-12-01","cited_by_count":130,"area":null},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129,"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":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128,"area":"synth"},{"id":"2107.14185","title":"Feature Importance-aware Transferable Adversarial Attacks","created":"2021-07-29","cited_by_count":127,"area":null},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127,"area":null},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126,"area":null},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123,"area":null},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2203.06915","title":"SimMatch: Semi-supervised Learning with Similarity Matching","created":"2022-03-14","cited_by_count":118,"area":null},{"id":"2310.01403","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","created":"2023-10-02","cited_by_count":118,"area":null},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117,"area":null},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2106.10456","title":"Humble Teachers Teach Better Students for Semi-Supervised Object Detection","created":"2021-06-19","cited_by_count":116,"area":"distill"},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115,"area":null},{"id":"2204.13317","title":"MMRotate: A Rotated Object Detection Benchmark using PyTorch","created":"2022-04-28","cited_by_count":115,"area":null},{"id":"2209.15611","title":"Protein structure generation via folding diffusion","created":"2022-09-30","cited_by_count":115,"area":"diffusion"},{"id":"2103.11402","title":"Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework","created":"2021-03-21","cited_by_count":113,"area":null},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112,"area":"lr"},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2405.12971","title":"BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once","created":"2024-05-21","cited_by_count":111,"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}],"next_cursor":"100"}