{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1903.02351","title":"CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning","created":"2019-03-06","cited_by_count":217},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1801.05401","title":"Low-Shot Learning from Imaginary Data","created":"2018-01-16","cited_by_count":181},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"1805.10483","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","created":"2018-05-26","cited_by_count":138},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"1704.00159","title":"Compositional Human Pose Regression","created":"2017-04-01","cited_by_count":124},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"1811.00472","title":"Class-Agnostic Counting","created":"2018-11-01","cited_by_count":85},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"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":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"id":"1804.03287","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","created":"2018-04-10","cited_by_count":60},{"id":"1811.12222","title":"ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving","created":"2018-11-29","cited_by_count":59},{"id":"2007.11864","title":"Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation","created":"2020-07-23","cited_by_count":52},{"id":"1909.11229","title":"Pretraining boosts out-of-domain robustness for pose estimation","created":"2019-09-24","cited_by_count":47},{"id":"1803.09331","title":"StarMap for Category-Agnostic Keypoint and Viewpoint Estimation","created":"2018-03-25","cited_by_count":42},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"1903.09214","title":"Multi-person Articulated Tracking with Spatial and Temporal Embeddings","created":"2019-03-21","cited_by_count":38},{"id":"1910.00216","title":"Revisiting Fine-tuning for Few-shot Learning","created":"2019-10-01","cited_by_count":29},{"id":"1909.04951","title":"AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces","created":"2019-09-11","cited_by_count":28},{"id":"2105.10154","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","created":"2021-05-21","cited_by_count":26},{"id":"1604.08685","title":"Single Image 3D Interpreter Network","created":"2016-04-29","cited_by_count":19},{"id":"1910.11535","title":"TRB: A Novel Triplet Representation for Understanding 2D Human Body","created":"2019-10-25","cited_by_count":10}],"next_cursor":null}