{"total":285,"rows":[{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"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":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713,"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":"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":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"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":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"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":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"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":"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":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82,"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":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"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":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58,"area":null},{"id":"2410.06245","title":"HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction","created":"2024-10-08","cited_by_count":57,"area":null},{"id":"2103.11832","title":"Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion","created":"2021-03-22","cited_by_count":56,"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":"2305.15862","title":"A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion","created":"2023-05-25","cited_by_count":47,"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":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42,"area":null},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39,"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":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36,"area":null},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34,"area":null},{"id":"2307.12730","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","created":"2023-07-24","cited_by_count":34,"area":null},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2103.06564","title":"PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation","created":"2021-03-11","cited_by_count":29,"area":null},{"id":"2106.12413","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2109.02038","title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","created":"2021-09-05","cited_by_count":28,"area":null},{"id":"2101.11342","title":"Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search","created":"2021-01-27","cited_by_count":27,"area":null},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2404.01614","title":"LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2103.14282","title":"Rethinking Graph Neural Architecture Search from Message-passing","created":"2021-03-26","cited_by_count":26,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25,"area":null},{"id":"2111.00902","title":"PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2401.00027","title":"Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring","created":"2023-12-29","cited_by_count":24,"area":null},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23,"area":null},{"id":"2412.13441","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","created":"2024-12-18","cited_by_count":23,"area":null},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21,"area":null},{"id":"2108.03428","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","created":"2021-08-07","cited_by_count":21,"area":null},{"id":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","cited_by_count":20,"area":null},{"id":"2203.09775","title":"ContrastMask: Contrastive Learning to Segment Every Thing","created":"2022-03-18","cited_by_count":20,"area":null},{"id":"2101.08809","title":"PyGlove: Symbolic Programming for Automated Machine Learning","created":"2021-01-21","cited_by_count":19,"area":null},{"id":"2103.04507","title":"OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection","created":"2021-03-08","cited_by_count":19,"area":null},{"id":"2108.00386","title":"WAS-VTON: Warping Architecture Search for Virtual Try-on Network","created":"2021-08-01","cited_by_count":18,"area":null},{"id":"2305.17654","title":"MixDehazeNet : Mix Structure Block For Image Dehazing Network","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2306.15988","title":"AFPN: Asymptotic Feature Pyramid Network for Object Detection","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2402.04672","title":"G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection","created":"2024-02-07","cited_by_count":17,"area":null},{"id":"2107.01548","title":"SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images","created":"2021-07-04","cited_by_count":16,"area":null},{"id":"2111.13280","title":"Efficient Self-Ensemble for Semantic Segmentation","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","cited_by_count":16,"area":null},{"id":"2105.03186","title":"A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15,"area":null},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2107.04735","title":"Local-to-Global Self-Attention in Vision Transformers","created":"2021-07-10","cited_by_count":13,"area":null},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2303.17144","title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving","created":"2023-03-30","cited_by_count":13,"area":null},{"id":"2110.13713","title":"YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs","created":"2021-10-26","cited_by_count":12,"area":null},{"id":"2111.11057","title":"Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images","created":"2021-11-22","cited_by_count":12,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2203.00860","title":"D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2207.07889","title":"You Should Look at All Objects","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2407.02047","title":"CountFormer: Multi-View Crowd Counting Transformer","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2111.07535","title":"T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging","created":"2021-11-15","cited_by_count":11,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11,"area":null},{"id":"2311.03312","title":"A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation","created":"2023-11-06","cited_by_count":11,"area":null},{"id":"2110.03002","title":"Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2206.13728","title":"Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2208.11356","title":"Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2303.07868","title":"DynaMask: Dynamic Mask Selection for Instance Segmentation","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2312.07006","title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","created":"2023-12-12","cited_by_count":10,"area":null},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2201.10781","title":"ASFD: Automatic and Scalable Face Detector","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2203.07155","title":"Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection","created":"2022-03-14","cited_by_count":9,"area":null}],"next_cursor":"100"}