{"total":579,"rows":[{"id":"2204.00964","title":"AdaFace: Quality Adaptive Margin for Face Recognition","created":"2022-04-03","cited_by_count":391,"area":null},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332,"area":"wm"},{"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":"2102.09480","title":"Unbiased Teacher for Semi-Supervised Object Detection","created":"2021-02-18","cited_by_count":306,"area":null},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300,"area":null},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170,"area":null},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168,"area":null},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160,"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":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114,"area":"distill"},{"id":"2101.06653","title":"LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting","created":"2021-01-17","cited_by_count":113,"area":null},{"id":"2405.20320","title":"Improving the Training of Rectified Flows","created":"2024-05-30","cited_by_count":108,"area":"diffusion"},{"id":"2103.02911","title":"Semi-supervised Left Atrium Segmentation with Mutual Consistency Training","created":"2021-03-04","cited_by_count":104,"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":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89,"area":null},{"id":"2206.02066","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","created":"2022-06-04","cited_by_count":84,"area":null},{"id":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80,"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":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76,"area":null},{"id":"2109.05488","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","created":"2021-09-12","cited_by_count":76,"area":null},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2407.09359","title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","created":"2024-07-12","cited_by_count":74,"area":null},{"id":"2103.01795","title":"Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation","created":"2021-03-02","cited_by_count":69,"area":null},{"id":"2109.03216","title":"Learning Fast Sample Re-weighting Without Reward Data","created":"2021-09-07","cited_by_count":69,"area":null},{"id":"2203.17261","title":"R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis","created":"2022-03-31","cited_by_count":69,"area":null},{"id":"2206.09500","title":"Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors","created":"2022-06-19","cited_by_count":69,"area":null},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65,"area":null},{"id":"2105.00405","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","created":"2021-05-02","cited_by_count":65,"area":null},{"id":"2204.12511","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","created":"2022-04-26","cited_by_count":63,"area":null},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61,"area":null},{"id":"2307.15254","title":"Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification","created":"2023-07-28","cited_by_count":60,"area":null},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58,"area":null},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57,"area":null},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"area":null},{"id":"2410.10777","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation","created":"2024-10-14","cited_by_count":54,"area":null},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2103.16368","title":"Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection","created":"2021-03-29","cited_by_count":49,"area":null},{"id":"2103.12474","title":"On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors","created":"2021-03-23","cited_by_count":48,"area":null},{"id":"2112.03694","title":"Hard Sample Aware Noise Robust Learning for Histopathology Image Classification","created":"2021-12-05","cited_by_count":48,"area":null},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47,"area":null},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46,"area":null},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"area":null},{"id":"2108.04547","title":"Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation","created":"2021-08-10","cited_by_count":45,"area":null},{"id":"2306.04300","title":"CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation","created":"2023-06-07","cited_by_count":44,"area":null},{"id":"2109.06141","title":"On Tilted Losses in Machine Learning: Theory and Applications","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43,"area":null},{"id":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43,"area":"distill"},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42,"area":null},{"id":"2310.05900","title":"Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network","created":"2023-10-09","cited_by_count":42,"area":null},{"id":"2202.13670","title":"FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving","created":"2022-02-28","cited_by_count":41,"area":null},{"id":"2311.00926","title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","created":"2023-11-02","cited_by_count":41,"area":null},{"id":"2108.05617","title":"Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning","created":"2021-08-12","cited_by_count":40,"area":null},{"id":"2207.08485","title":"Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation","created":"2022-07-18","cited_by_count":37,"area":null},{"id":"2402.03634","title":"Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2402.14873","title":"Technical Report on the Pangram AI-Generated Text Classifier","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33,"area":null},{"id":"2303.10610","title":"DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification","created":"2023-03-19","cited_by_count":32,"area":"diffusion"},{"id":"2206.08655","title":"Learning Implicit Feature Alignment Function for Semantic Segmentation","created":"2022-06-17","cited_by_count":31,"area":null},{"id":"2105.11672","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2103.13757","title":"I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2103.16148","title":"Class-Aware Robust Adversarial Training for Object Detection","created":"2021-03-30","cited_by_count":27,"area":null},{"id":"2110.14057","title":"Meta-learning with an Adaptive Task Scheduler","created":"2021-10-26","cited_by_count":27,"area":null},{"id":"2203.15251","title":"Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation","created":"2022-03-29","cited_by_count":27,"area":null},{"id":"2208.04921","title":"TSRFormer: Table Structure Recognition with Transformers","created":"2022-08-09","cited_by_count":27,"area":null},{"id":"2201.04236","title":"Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents","created":"2022-01-11","cited_by_count":26,"area":null},{"id":"2207.08768","title":"Rank-based Decomposable Losses in Machine Learning: A Survey","created":"2022-07-18","cited_by_count":26,"area":null},{"id":"2209.00183","title":"ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification","created":"2022-09-01","cited_by_count":25,"area":null},{"id":"2304.10756","title":"Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation","created":"2023-04-21","cited_by_count":24,"area":null},{"id":"2402.02009","title":"Robust Multi-Task Learning with Excess Risks","created":"2024-02-03","cited_by_count":24,"area":null},{"id":"2106.03300","title":"Sum of Ranked Range Loss for Supervised Learning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2107.11669","title":"Rank & Sort Loss for Object Detection and Instance Segmentation","created":"2021-07-24","cited_by_count":22,"area":null},{"id":"2212.14613","title":"Delving into Semantic Scale Imbalance","created":"2022-12-30","cited_by_count":22,"area":null},{"id":"2308.10133","title":"TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security","created":"2023-08-20","cited_by_count":22,"area":null},{"id":"2308.16572","title":"CL-MAE: Curriculum-Learned Masked Autoencoders","created":"2023-08-31","cited_by_count":22,"area":null},{"id":"2504.09228","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","created":"2025-04-12","cited_by_count":22,"area":null},{"id":"2103.07293","title":"Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association","created":"2021-03-12","cited_by_count":21,"area":null},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2409.13853","title":"Unlocking Memorization in Large Language Models with Dynamic Soft Prompting","created":"2024-09-20","cited_by_count":21,"area":null},{"id":"2104.06936","title":"IQDet: Instance-wise Quality Distribution Sampling for Object Detection","created":"2021-04-14","cited_by_count":20,"area":null},{"id":"2104.14042","title":"Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learning","created":"2021-04-28","cited_by_count":20,"area":null},{"id":"2111.14932","title":"Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection","created":"2021-11-29","cited_by_count":20,"area":null},{"id":"2207.09399","title":"RCLane: Relay Chain Prediction for Lane Detection","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2207.10391","title":"Error Compensation Framework for Flow-Guided Video Inpainting","created":"2022-07-21","cited_by_count":20,"area":null},{"id":"2406.07876","title":"Small Scale Data-Free Knowledge Distillation","created":"2024-06-12","cited_by_count":20,"area":"distill"},{"id":"2504.20998","title":"YoChameleon: Personalized Vision and Language Generation","created":"2025-04-29","cited_by_count":20,"area":"mllm"},{"id":"2106.14917","title":"Striking the Right Balance: Recall Loss for Semantic Segmentation","created":"2021-06-28","cited_by_count":19,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2208.14687","title":"TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers","created":"2022-08-31","cited_by_count":19,"area":null},{"id":"2210.08375","title":"Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining","created":"2022-10-15","cited_by_count":19,"area":null},{"id":"2405.11272","title":"Double Correction Framework for Denoising Recommendation","created":"2024-05-18","cited_by_count":19,"area":null},{"id":"2103.13109","title":"A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios","created":"2021-03-24","cited_by_count":18,"area":null},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18,"area":"mllm"}],"next_cursor":"100"}