{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2003.13830","title":"Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation","created":"2020-03-30","cited_by_count":256},{"id":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2211.01367","title":"Two-Stream Network for Sign Language Recognition and Translation","created":"2022-11-02","cited_by_count":123},{"id":"2004.14874","title":"Progressive Transformers for End-to-End Sign Language Production","created":"2020-04-30","cited_by_count":120},{"id":"2407.12705","title":"IMAGDressing-v1: Customizable Virtual Dressing","created":"2024-07-17","cited_by_count":100},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2203.04287","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","created":"2022-03-08","cited_by_count":80},{"id":"2306.15162","title":"YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus","created":"2023-06-27","cited_by_count":75},{"id":"1705.06400","title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","created":"2017-05-18","cited_by_count":61},{"id":"2110.05382","title":"SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition","created":"2021-10-11","cited_by_count":60},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59},{"id":"2008.12405","title":"Adversarial Training for Multi-Channel Sign Language Production","created":"2020-08-27","cited_by_count":57},{"id":"2405.04164","title":"Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation","created":"2024-05-07","cited_by_count":57},{"id":"2501.15187","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","created":"2025-01-25","cited_by_count":56},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50},{"id":"2312.02702","title":"Neural Sign Actors: A diffusion model for 3D sign language production from text","created":"2023-12-05","cited_by_count":49},{"id":"2303.12080","title":"Natural Language-Assisted Sign Language Recognition","created":"2023-03-21","cited_by_count":46},{"id":"2008.10428","title":"Global-local Enhancement Network for NMFs-aware Sign Language Recognition","created":"2020-08-24","cited_by_count":38},{"id":"2302.05075","title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","created":"2023-02-10","cited_by_count":35},{"id":"2011.09846","title":"Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video","created":"2020-11-19","cited_by_count":34},{"id":"2406.07119","title":"T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text","created":"2024-06-11","cited_by_count":30},{"id":"2308.10809","title":"Improving Continuous Sign Language Recognition with Cross-Lingual Signs","created":"2023-08-21","cited_by_count":27},{"id":"2308.16082","title":"SignDiff: Diffusion Model for American Sign Language Production","created":"2023-08-30","cited_by_count":25},{"id":"2505.03351","title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","created":"2025-05-06","cited_by_count":22},{"id":"2408.08544","title":"Scaling up Multimodal Pre-training for Sign Language Understanding","created":"2024-08-16","cited_by_count":21},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21},{"id":"2505.00615","title":"Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction","created":"2025-05-01","cited_by_count":20},{"id":"2404.11499","title":"A Data-Driven Representation for Sign Language Production","created":"2024-04-17","cited_by_count":17},{"id":"2503.08529","title":"SignRep: Enhancing Self-Supervised Sign Representations","created":"2025-03-11","cited_by_count":15},{"id":"2506.15980","title":"Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization","created":"2025-06-19","cited_by_count":9},{"id":"2505.02108","title":"SignSplat: Rendering Sign Language via Gaussian Splatting","created":"2025-05-04","cited_by_count":6},{"id":"2510.07453","title":"Meaningful Pose-Based Sign Language Evaluation","created":"2025-10-08","cited_by_count":6},{"id":"2512.08040","title":"Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment","created":"2025-12-08","cited_by_count":6},{"id":"2601.19577","title":"MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation","created":"2026-01-27","cited_by_count":4},{"id":"2506.09643","title":"Using Sign Language Production as Data Augmentation to enhance Sign Language Translation","created":"2025-06-11","cited_by_count":3},{"id":"2507.06060","title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","created":"2025-07-08","cited_by_count":1}],"next_cursor":null}