{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1603.04042","title":"Deep Interactive Object Selection","created":"2016-03-13","cited_by_count":160},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"2010.00514","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","created":"2020-10-01","cited_by_count":131},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"1903.06593","title":"PifPaf: Composite Fields for Human Pose Estimation","created":"2019-03-15","cited_by_count":120},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"2010.00515","title":"Linguistic Structure Guided Context Modeling for Referring Image Segmentation","created":"2020-10-01","cited_by_count":102},{"id":"2204.02574","title":"FocalClick: Towards Practical Interactive Image Segmentation","created":"2022-04-06","cited_by_count":102},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"1711.06475","title":"AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding","created":"2017-11-17","cited_by_count":73},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68},{"id":"1509.04874","title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","created":"2015-09-16","cited_by_count":58},{"id":"2007.02846","title":"Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation","created":"2020-07-06","cited_by_count":57},{"id":"2205.13764","title":"Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images","created":"2022-05-27","cited_by_count":56},{"id":"2309.01017","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","created":"2023-09-02","cited_by_count":54},{"id":"1911.07451","title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","created":"2019-11-18","cited_by_count":49},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2312.12198","title":"Mask Grounding for Referring Image Segmentation","created":"2023-12-19","cited_by_count":40},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","cited_by_count":26},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20},{"id":"2207.10258","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","created":"2022-07-21","cited_by_count":19},{"id":"1511.06676","title":"Personalizing Human Video Pose Estimation","created":"2015-11-20","cited_by_count":16},{"id":"2111.10747","title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","created":"2021-11-21","cited_by_count":14},{"id":"2403.19407","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","created":"2024-03-28","cited_by_count":14},{"id":"2212.07855","title":"QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query","created":"2022-12-15","cited_by_count":13},{"id":"2108.00399","title":"Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition","created":"2021-08-01","cited_by_count":12},{"id":"2107.12569","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","created":"2021-07-27","cited_by_count":11},{"id":"2303.11320","title":"ScribbleSeg: Scribble-based Interactive Image Segmentation","created":"2023-03-20","cited_by_count":10}],"next_cursor":null}