{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"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":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"1908.05436","title":"Learning Trajectory Dependencies for Human Motion Prediction","created":"2019-08-15","cited_by_count":246},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"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":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"1812.05478","title":"Human Motion Prediction via Spatio-Temporal Inpainting","created":"2018-12-13","cited_by_count":114},{"id":"1612.06524","title":"3D Human Pose Estimation = 2D Pose Estimation + Matching","created":"2016-12-20","cited_by_count":113},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104},{"id":"1802.09232","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","created":"2018-02-26","cited_by_count":103},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2010.11531","title":"Convolutional Autoencoders for Human Motion Infilling","created":"2020-10-22","cited_by_count":73},{"id":"2203.16051","title":"Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction","created":"2022-03-30","cited_by_count":66},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64},{"id":"1603.07772","title":"Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks","created":"2016-03-24","cited_by_count":63},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"1910.02212","title":"Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction","created":"2019-10-05","cited_by_count":50},{"id":"1909.13245","title":"Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction","created":"2019-09-29","cited_by_count":47},{"id":"2304.04748","title":"Exploring Effective Factors for Improving Visual In-Context Learning","created":"2023-04-10","cited_by_count":43},{"id":"2306.08659","title":"Explore In-Context Learning for 3D Point Cloud Understanding","created":"2023-06-14","cited_by_count":40},{"id":"2108.11244","title":"Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction","created":"2021-08-25","cited_by_count":37},{"id":"1809.01844","title":"Unsupervised Learning of View-invariant Action Representations","created":"2018-09-06","cited_by_count":32},{"id":"2312.03703","title":"Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning","created":"2023-12-06","cited_by_count":27},{"id":"1901.04877","title":"Feature Boosting Network For 3D Pose Estimation","created":"2019-01-15","cited_by_count":26},{"id":"2005.08891","title":"Generative Tweening: Long-term Inbetweening of 3D Human Motions","created":"2020-05-18","cited_by_count":23},{"id":"2405.05216","title":"FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models","created":"2024-05-08","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":"2409.10473","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","created":"2024-09-16","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":"2404.07645","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","created":"2024-04-11","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":"2403.09616","title":"Explore In-Context Segmentation via Latent Diffusion Models","created":"2024-03-14","cited_by_count":12},{"id":"2408.02922","title":"Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network","created":"2024-08-06","cited_by_count":12},{"id":"2311.17408","title":"Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction","created":"2023-11-29","cited_by_count":11},{"id":"2404.11605","title":"VG4D: Vision-Language Model Goes 4D Video Recognition","created":"2024-04-17","cited_by_count":11},{"id":"2309.05073","title":"FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions","created":"2023-09-10","cited_by_count":7},{"id":"2410.15582","title":"ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos","created":"2024-10-21","cited_by_count":4}],"next_cursor":null}