{"list":"other","total":70,"rows":[{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"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":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"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":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"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":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"1910.11006","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","created":"2019-10-24","cited_by_count":218},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"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":"1812.01053","title":"MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language","created":"2018-12-03","cited_by_count":118},{"id":"2007.12131","title":"BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues","created":"2020-07-23","cited_by_count":106},{"id":"2307.14768","title":"Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining","created":"2023-07-27","cited_by_count":105},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83},{"id":"2203.04287","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","created":"2022-03-08","cited_by_count":80},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77},{"id":"2002.03187","title":"Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition","created":"2020-02-08","cited_by_count":74},{"id":"2105.05222","title":"Including Signed Languages in Natural Language Processing","created":"2021-05-11","cited_by_count":68},{"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":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61},{"id":"2305.04868","title":"SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding","created":"2023-05-08","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":"2103.06982","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","created":"2021-03-11","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":"2312.13303","title":"RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios","created":"2023-12-19","cited_by_count":46},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"2208.09141","title":"G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model","created":"2022-08-19","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":"2406.07119","title":"T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text","created":"2024-06-11","cited_by_count":30},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29},{"id":"2308.10809","title":"Improving Continuous Sign Language Recognition with Cross-Lingual Signs","created":"2023-08-21","cited_by_count":27},{"id":"2211.15464","title":"Considerations for meaningful sign language machine translation based on glosses","created":"2022-11-28","cited_by_count":25},{"id":"2403.18920","title":"CPR: Retrieval Augmented Generation for Copyright Protection","created":"2024-03-27","cited_by_count":24},{"id":"2211.13613","title":"Ham2Pose: Animating Sign Language Notation into Pose Sequences","created":"2022-11-24","cited_by_count":21},{"id":"2308.12191","title":"Sign Language Translation with Iterative Prototype","created":"2023-08-23","cited_by_count":20},{"id":"2401.04730","title":"A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars","created":"2024-01-09","cited_by_count":19},{"id":"2411.16810","title":"Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation","created":"2024-11-25","cited_by_count":16},{"id":"2401.05336","title":"Towards Online Continuous Sign Language Recognition and Translation","created":"2024-01-10","cited_by_count":14},{"id":"2405.07974","title":"SignAvatar: Sign Language 3D Motion Reconstruction and Generation","created":"2024-05-13","cited_by_count":14},{"id":"2405.20666","title":"MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition","created":"2024-05-31","cited_by_count":13},{"id":"2304.10482","title":"Reconstructing Signing Avatars From Video Using Linguistic Priors","created":"2023-04-20","cited_by_count":12},{"id":"2212.13023","title":"Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal","created":"2022-12-26","cited_by_count":11},{"id":"2409.16709","title":"Pose-Guided Fine-Grained Sign Language Video Generation","created":"2024-09-25","cited_by_count":8},{"id":"2405.00980","title":"A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News","created":"2024-05-02","cited_by_count":6},{"id":"2406.10501","title":"Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition","created":"2024-06-15","cited_by_count":6},{"id":"2407.05404","title":"iSign: A Benchmark for Indian Sign Language Processing","created":"2024-07-07","cited_by_count":6}],"next_cursor":null}