{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"1611.07828","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","created":"2016-11-23","cited_by_count":221},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123},{"id":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92},{"id":"1711.08585","title":"Exploiting temporal information for 3D pose estimation","created":"2017-11-23","cited_by_count":89},{"id":"2107.13788","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","created":"2021-07-29","cited_by_count":85},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64},{"id":"2108.07181","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","created":"2021-08-16","cited_by_count":62},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"2002.05907","title":"A Survey on 3D Skeleton-Based Action Recognition Using Learning Method","created":"2020-02-14","cited_by_count":47},{"id":"2307.05853","title":"GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video","created":"2023-07-12","cited_by_count":47},{"id":"2103.15507","title":"Context Modeling in 3D Human Pose Estimation: A Unified Perspective","created":"2021-03-29","cited_by_count":37},{"id":"2404.00658","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","created":"2024-03-31","cited_by_count":34},{"id":"2112.15012","title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","created":"2021-12-30","cited_by_count":31},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"2403.18926","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","created":"2024-02-27","cited_by_count":28},{"id":"2312.03703","title":"Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning","created":"2023-12-06","cited_by_count":27},{"id":"2302.01825","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","created":"2023-02-03","cited_by_count":23},{"id":"2311.12028","title":"Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation","created":"2023-11-20","cited_by_count":15},{"id":"2501.01770","title":"TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation","created":"2025-01-03","cited_by_count":14},{"id":"2109.07353","title":"Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos","created":"2021-09-15","cited_by_count":13},{"id":"2312.11850","title":"GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction","created":"2023-12-19","cited_by_count":12},{"id":"2305.05785","title":"Regular Splitting Graph Network for 3D Human Pose Estimation","created":"2023-05-09","cited_by_count":11},{"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},{"id":"2311.17408","title":"Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction","created":"2023-11-29","cited_by_count":11},{"id":"2312.11894","title":"3D-LFM: Lifting Foundation Model","created":"2023-12-19","cited_by_count":8}],"next_cursor":null}