{"total":1020,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"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":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135,"area":null},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"area":null},{"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,"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":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614,"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":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472,"area":null},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"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":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213,"area":null},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"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":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2303.07338","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","created":"2023-03-13","cited_by_count":184,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"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":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"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":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167,"area":null},{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162,"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":"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":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148,"area":null},{"id":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2203.06953","title":"Forward Compatible Few-Shot Class-Incremental Learning","created":"2022-03-14","cited_by_count":127,"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":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121,"area":null},{"id":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115,"area":"inference"},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109,"area":null},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2311.12058","title":"FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin","created":"2023-11-18","cited_by_count":103,"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":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93,"area":null},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2105.04206","title":"You Only Learn One Representation: Unified Network for Multiple Tasks","created":"2021-05-10","cited_by_count":86,"area":null},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84,"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":"2306.09700","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","created":"2023-06-16","cited_by_count":82,"area":null},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81,"area":null},{"id":"2107.13802","title":"RigNet: Repetitive Image Guided Network for Depth Completion","created":"2021-07-29","cited_by_count":80,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66,"area":null},{"id":"2111.15557","title":"Low-light Image Enhancement via Breaking Down the Darkness","created":"2021-11-30","cited_by_count":65,"area":null},{"id":"2309.07117","title":"PILOT: A Pre-Trained Model-Based Continual Learning Toolbox","created":"2023-09-13","cited_by_count":64,"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":"2203.03875","title":"Occupancy Flow Fields for Motion Forecasting in Autonomous Driving","created":"2022-03-08","cited_by_count":62,"area":null},{"id":"2105.01922","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","created":"2021-05-05","cited_by_count":61,"area":null},{"id":"2103.00236","title":"Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection","created":"2021-02-27","cited_by_count":60,"area":null},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59,"area":null},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58,"area":null},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57,"area":null},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57,"area":null},{"id":"2104.12673","title":"Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data","created":"2021-04-26","cited_by_count":55,"area":null},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55,"area":null},{"id":"2209.07790","title":"A Large-scale Multiple-objective Method for Black-box Attack against Object Detection","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2305.04925","title":"PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds","created":"2023-05-08","cited_by_count":54,"area":null},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"area":null},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53,"area":null},{"id":"2203.09831","title":"DTA: Physical Camouflage Attacks using Differentiable Transformation Network","created":"2022-03-18","cited_by_count":51,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2205.12740","title":"SIoU Loss: More Powerful Learning for Bounding Box Regression","created":"2022-05-25","cited_by_count":49,"area":null},{"id":"2108.03227","title":"Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images","created":"2021-08-06","cited_by_count":48,"area":null},{"id":"2103.08273","title":"Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation","created":"2021-03-15","cited_by_count":46,"area":"distill"},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2112.02991","title":"Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery","created":"2021-12-06","cited_by_count":45,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2310.20234","title":"HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds","created":"2023-10-31","cited_by_count":45,"area":null},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44,"area":"distill"},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2203.04275","title":"Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap","created":"2022-03-08","cited_by_count":44,"area":null},{"id":"2107.04259","title":"Unity Perception: Generate Synthetic Data for Computer Vision","created":"2021-07-09","cited_by_count":43,"area":null},{"id":"2112.05749","title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","created":"2021-12-10","cited_by_count":43,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42,"area":null},{"id":"2312.08977","title":"Weighted Ensemble Models Are Strong Continual Learners","created":"2023-12-14","cited_by_count":42,"area":null},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41,"area":null},{"id":"2112.04840","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","created":"2021-12-09","cited_by_count":40,"area":"distill"},{"id":"2205.09723","title":"Robust and Efficient Medical Imaging with Self-Supervision","created":"2022-05-19","cited_by_count":40,"area":null},{"id":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40,"area":null},{"id":"2104.11747","title":"Learnable Online Graph Representations for 3D Multi-Object Tracking","created":"2021-04-23","cited_by_count":38,"area":null},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2407.20892","title":"What is YOLOv5: A deep look into the internal features of the popular object detector","created":"2024-07-30","cited_by_count":37,"area":null}],"next_cursor":"100"}