{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1809.06839","title":"Albumentations: fast and flexible image augmentations","created":"2018-09-18","cited_by_count":560},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178},{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165},{"id":"1908.03851","title":"IoU Loss for 2D/3D Object Detection","created":"2019-08-11","cited_by_count":128},{"id":"2007.03496","title":"AutoAssign: Differentiable Label Assignment for Dense Object Detection","created":"2020-07-07","cited_by_count":100},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"2204.07974","title":"Anomaly Detection in Autonomous Driving: A Survey","created":"2022-04-17","cited_by_count":87},{"id":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74},{"id":"2012.03544","title":"End-to-End Object Detection with Fully Convolutional Network","created":"2020-12-07","cited_by_count":70},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32},{"id":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","cited_by_count":26},{"id":"2009.13592","title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","created":"2020-09-28","cited_by_count":25},{"id":"2008.07294","title":"AP-Loss for Accurate One-Stage Object Detection","created":"2020-08-17","cited_by_count":24},{"id":"2211.12735","title":"Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration","created":"2022-11-23","cited_by_count":24},{"id":"2107.11669","title":"Rank & Sort Loss for Object Detection and Instance Segmentation","created":"2021-07-24","cited_by_count":22},{"id":"2402.16370","title":"DEYO: DETR with YOLO for End-to-End Object Detection","created":"2024-02-26","cited_by_count":6},{"id":"2407.04381","title":"Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection","created":"2024-07-05","cited_by_count":5}],"next_cursor":null}