{"list":"other","total":67,"rows":[{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"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":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"1908.05436","title":"Learning Trajectory Dependencies for Human Motion Prediction","created":"2019-08-15","cited_by_count":246},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"2004.08692","title":"A Spatio-temporal Transformer for 3D Human Motion Prediction","created":"2020-04-18","cited_by_count":133},{"id":"2003.08802","title":"Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction","created":"2020-03-17","cited_by_count":132},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2108.07152","title":"MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction","created":"2021-08-16","cited_by_count":100},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100},{"id":"1910.09070","title":"Structured Prediction Helps 3D Human Motion Modelling","created":"2019-10-20","cited_by_count":96},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1705.00053","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","created":"2017-04-28","cited_by_count":88},{"id":"1809.03036","title":"A Neural Temporal Model for Human Motion Prediction","created":"2018-09-09","cited_by_count":87},{"id":"1808.04545","title":"MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics","created":"2018-08-14","cited_by_count":86},{"id":"1902.09868","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","created":"2019-02-26","cited_by_count":85},{"id":"2110.04573","title":"Space-Time-Separable Graph Convolutional Network for Pose Forecasting","created":"2021-10-09","cited_by_count":84},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78},{"id":"2108.08422","title":"Generating Smooth Pose Sequences for Diverse Human Motion Prediction","created":"2021-08-19","cited_by_count":66},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58},{"id":"1810.09676","title":"Action-Agnostic Human Pose Forecasting","created":"2018-10-23","cited_by_count":56},{"id":"1812.02591","title":"BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN","created":"2018-12-06","cited_by_count":55},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49},{"id":"2203.01474","title":"Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction","created":"2022-03-03","cited_by_count":48},{"id":"2109.07531","title":"Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers","created":"2021-09-15","cited_by_count":46},{"id":"1909.03449","title":"Imitation Learning for Human Pose Prediction","created":"2019-09-08","cited_by_count":44},{"id":"1812.02501","title":"Zero-Shot Anticipation for Instructional Activities","created":"2018-12-06","cited_by_count":43},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"2207.00499","title":"MotionMixer: MLP-based 3D Human Body Pose Forecasting","created":"2022-07-01","cited_by_count":42},{"id":"1805.02513","title":"Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic","created":"2018-05-07","cited_by_count":41},{"id":"1912.07148","title":"Predicting the Future: A Jointly Learnt Model for Action Anticipation","created":"2019-12-16","cited_by_count":41},{"id":"1502.06648","title":"Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data","created":"2015-02-23","cited_by_count":40},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"1908.09540","title":"Uncertainty-Aware Anticipation of Activities","created":"2019-08-26","cited_by_count":39},{"id":"1808.07784","title":"Time-Agnostic Prediction: Predicting Predictable Video Frames","created":"2018-08-23","cited_by_count":37},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"2006.15327","title":"Compositional Video Synthesis with Action Graphs","created":"2020-06-27","cited_by_count":34},{"id":"2207.07351","title":"Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space","created":"2022-07-15","cited_by_count":32},{"id":"2203.04132","title":"Motron: Multimodal Probabilistic Human Motion Forecasting","created":"2022-03-08","cited_by_count":30},{"id":"1904.05869","title":"Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning","created":"2019-04-11","cited_by_count":20},{"id":"2007.06426","title":"Multitask Non-Autoregressive Model for Human Motion Prediction","created":"2020-07-13","cited_by_count":16},{"id":"2011.15079","title":"Forecasting Characteristic 3D Poses of Human Actions","created":"2020-11-30","cited_by_count":16},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14},{"id":"2103.11719","title":"TICaM: A Time-of-flight In-car Cabin Monitoring Dataset","created":"2021-03-22","cited_by_count":10}],"next_cursor":null}