{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"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":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"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":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"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":"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":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110},{"id":"2304.08577","title":"Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model","created":"2023-04-17","cited_by_count":107},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","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":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"2304.12518","title":"IMUPoser: Full-Body Pose Estimation using IMUs in Phones, Watches, and Earbuds","created":"2023-04-25","cited_by_count":54},{"id":"2305.01599","title":"EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors","created":"2023-05-02","cited_by_count":48},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2308.08855","title":"Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling","created":"2023-08-17","cited_by_count":43},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"1910.09031","title":"CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions","created":"2019-10-20","cited_by_count":40},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2409.13426","title":"HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device","created":"2024-09-20","cited_by_count":27},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22},{"id":"2311.02191","title":"SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data","created":"2023-11-03","cited_by_count":21},{"id":"2405.20786","title":"Stratified Avatar Generation from Sparse Observations","created":"2024-05-30","cited_by_count":21},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19},{"id":"2207.11329","title":"Video Swin Transformers for Egocentric Video Understanding @ Ego4D Challenges 2022","created":"2022-07-22","cited_by_count":5}],"next_cursor":null}