{"list":"other","total":65,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"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":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2008.13367","title":"VarifocalNet: An IoU-aware Dense Object Detector","created":"2020-08-31","cited_by_count":231},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"1807.11590","title":"Acquisition of Localization Confidence for Accurate Object Detection","created":"2018-07-30","cited_by_count":176},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2305.11003","title":"Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping","created":"2023-05-18","cited_by_count":92},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60},{"id":"2203.06883","title":"Accelerating DETR Convergence via Semantic-Aligned Matching","created":"2022-03-14","cited_by_count":58},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51},{"id":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","cited_by_count":46},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41},{"id":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37},{"id":"2307.07829","title":"HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance","created":"2023-07-15","cited_by_count":36},{"id":"2308.04409","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","created":"2023-08-08","cited_by_count":35},{"id":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"2304.03119","title":"Zero-shot Generative Model Adaptation via Image-specific Prompt Learning","created":"2023-04-06","cited_by_count":27},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","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":"2210.06223","title":"Latency-aware Spatial-wise Dynamic Networks","created":"2022-10-12","cited_by_count":25},{"id":"1907.10156","title":"DR Loss: Improving Object Detection by Distributional Ranking","created":"2019-07-23","cited_by_count":24},{"id":"2008.07294","title":"AP-Loss for Accurate One-Stage Object Detection","created":"2020-08-17","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":"1904.00761","title":"Neural Speed Reading with Structural-Jump-LSTM","created":"2019-03-20","cited_by_count":17},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15},{"id":"2112.11037","title":"SOIT: Segmenting Objects with Instance-Aware Transformers","created":"2021-12-21","cited_by_count":14},{"id":"2301.07584","title":"Joint Representation Learning for Text and 3D Point Cloud","created":"2023-01-18","cited_by_count":14},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13},{"id":"2306.03362","title":"Boosting Offline Reinforcement Learning with Action Preference Query","created":"2023-06-06","cited_by_count":12},{"id":"2203.04187","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","created":"2022-03-08","cited_by_count":11},{"id":"2306.07265","title":"detrex: Benchmarking Detection Transformers","created":"2023-06-12","cited_by_count":8},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6},{"id":"2308.01300","title":"Revisiting DETR Pre-training for Object Detection","created":"2023-08-02","cited_by_count":5},{"id":"2301.01019","title":"Correlation Loss: Enforcing Correlation between Classification and Localization","created":"2023-01-03","cited_by_count":4},{"id":"2308.03747","title":"Mask Frozen-DETR: High Quality Instance Segmentation with One GPU","created":"2023-08-07","cited_by_count":3}],"next_cursor":null}