{"total":173,"rows":[{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2203.04287","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","created":"2022-03-08","cited_by_count":80,"area":null},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77,"area":null},{"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,"area":null},{"id":"2205.12870","title":"Open-Domain Sign Language Translation Learned from Online Video","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2305.04868","title":"SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding","created":"2023-05-08","cited_by_count":59,"area":null},{"id":"2501.15187","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","created":"2025-01-25","cited_by_count":56,"area":null},{"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,"area":"diffusion"},{"id":"2402.09611","title":"Towards Privacy-Aware Sign Language Translation at Scale","created":"2024-02-14","cited_by_count":44,"area":null},{"id":"2304.06371","title":"Sign Language Translation from Instructional Videos","created":"2023-04-13","cited_by_count":39,"area":null},{"id":"2407.11144","title":"YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus","created":"2024-07-15","cited_by_count":36,"area":null},{"id":"2303.12793","title":"CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning","created":"2023-03-22","cited_by_count":33,"area":null},{"id":"2305.12876","title":"Gloss-Free End-to-End Sign Language Translation","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2406.07119","title":"T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text","created":"2024-06-11","cited_by_count":30,"area":null},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29,"area":null},{"id":"2111.03635","title":"BBC-Oxford British Sign Language Dataset","created":"2021-11-05","cited_by_count":28,"area":null},{"id":"2103.15910","title":"Sign Language Production: A Review","created":"2021-03-29","cited_by_count":26,"area":null},{"id":"2501.09754","title":"Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues","created":"2025-01-16","cited_by_count":26,"area":null},{"id":"2308.16082","title":"SignDiff: Diffusion Model for American Sign Language Production","created":"2023-08-30","cited_by_count":25,"area":"diffusion"},{"id":"2403.12556","title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","created":"2024-03-19","cited_by_count":24,"area":null},{"id":"2408.09949","title":"C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval","created":"2024-08-19","cited_by_count":24,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22,"area":null},{"id":"2411.16765","title":"SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction","created":"2024-11-25","cited_by_count":22,"area":null},{"id":"2505.03351","title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","created":"2025-05-06","cited_by_count":22,"area":null},{"id":"2211.13613","title":"Ham2Pose: Animating Sign Language Notation into Pose Sequences","created":"2022-11-24","cited_by_count":21,"area":null},{"id":"2408.08544","title":"Scaling up Multimodal Pre-training for Sign Language Understanding","created":"2024-08-16","cited_by_count":21,"area":null},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2407.01264","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","created":"2024-07-01","cited_by_count":20,"area":null},{"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,"area":null},{"id":"2406.06907","title":"SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale","created":"2024-06-11","cited_by_count":19,"area":null},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2405.10266","title":"A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision","created":"2024-05-16","cited_by_count":15,"area":null},{"id":"2503.08529","title":"SignRep: Enhancing Self-Supervised Sign Representations","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2207.03714","title":"Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation","created":"2022-07-08","cited_by_count":14,"area":null},{"id":"2312.12917","title":"Sign Language Production with Latent Motion Transformer","created":"2023-12-20","cited_by_count":13,"area":null},{"id":"2202.05383","title":"Including Facial Expressions in Contextual Embeddings for Sign Language Generation","created":"2022-02-11","cited_by_count":12,"area":null},{"id":"2304.10482","title":"Reconstructing Signing Avatars From Video Using Linguistic Priors","created":"2023-04-20","cited_by_count":12,"area":null},{"id":"2505.15438","title":"Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2506.00129","title":"Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation","created":"2025-05-30","cited_by_count":12,"area":null},{"id":"2303.11771","title":"Self-Sufficient Framework for Continuous Sign Language Recognition","created":"2023-03-21","cited_by_count":11,"area":null},{"id":"2408.13585","title":"FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluation","created":"2024-08-24","cited_by_count":10,"area":null},{"id":"2203.09679","title":"Modeling Intensification for Sign Language Generation: A Computational Approach","created":"2022-03-18","cited_by_count":9,"area":null},{"id":"2309.12179","title":"Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2407.03817","title":"Markerless Multi-view 3D Human Pose Estimation: a survey","created":"2024-07-04","cited_by_count":9,"area":null},{"id":"2408.10593","title":"An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2506.15980","title":"Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization","created":"2025-06-19","cited_by_count":9,"area":"diffusion"},{"id":"2603.13240","title":"Gloss-Free Sign Language Translation: An Unbiased Evaluation of Progress in the Field","created":"2026-02-18","cited_by_count":9,"area":null},{"id":"2201.01609","title":"All You Need In Sign Language Production","created":"2022-01-05","cited_by_count":8,"area":null},{"id":"2211.00448","title":"Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition","created":"2022-11-01","cited_by_count":8,"area":null},{"id":"2407.11855","title":"Scaling Sign Language Translation","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2408.05436","title":"A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities","created":"2024-08-10","cited_by_count":8,"area":null},{"id":"2210.03951","title":"ArabSign: A Multi-modality Dataset and Benchmark for Continuous Arabic Sign Language Recognition","created":"2022-10-08","cited_by_count":7,"area":null},{"id":"2210.16579","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","created":"2022-10-29","cited_by_count":7,"area":null},{"id":"2411.05783","title":"ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articles","created":"2024-11-08","cited_by_count":7,"area":null},{"id":"2310.04753","title":"A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset","created":"2023-10-07","cited_by_count":6,"area":null},{"id":"2406.01316","title":"Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2407.05404","title":"iSign: A Benchmark for Indian Sign Language Processing","created":"2024-07-07","cited_by_count":6,"area":null},{"id":"2407.12593","title":"EvSign: Sign Language Recognition and Translation with Streaming Events","created":"2024-07-17","cited_by_count":6,"area":null},{"id":"2407.15806","title":"FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2506.03615","title":"Isharah: A Large-Scale Multi-Scene Dataset for Continuous Sign Language Recognition","created":"2025-06-04","cited_by_count":6,"area":null},{"id":"2510.07453","title":"Meaningful Pose-Based Sign Language Evaluation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2510.19367","title":"Sign Language Translation with Sentence Embedding Supervision","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2512.08040","title":"Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2311.12128","title":"Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models","created":"2023-11-20","cited_by_count":5,"area":null},{"id":"2403.10434","title":"Spotter+GPT: Turning Sign Spottings into Sentences with LLMs","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2407.02854","title":"A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production","created":"2024-07-03","cited_by_count":5,"area":null},{"id":"2407.16394","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2409.01073","title":"SCOPE: Sign Language Contextual Processing with Embedding from LLMs","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2508.15902","title":"Text-Driven 3D Hand Motion Generation from Sign Language Data","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2208.06183","title":"Non-Autoregressive Sign Language Production via Knowledge Distillation","created":"2022-08-12","cited_by_count":4,"area":"distill"},{"id":"2406.11049","title":"Reconsidering Sentence-Level Sign Language Translation","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2407.12842","title":"MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2504.16315","title":"SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2505.17090","title":"EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2601.19577","title":"MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation","created":"2026-01-27","cited_by_count":4,"area":"diffusion"},{"id":"2105.02742","title":"Pose-Guided Sign Language Video GAN with Dynamic Lambda","created":"2021-05-06","cited_by_count":3,"area":null},{"id":"2210.13326","title":"Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2212.01140","title":"Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2308.08849","title":"A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2403.19920","title":"MI-NeRF: Learning a Single Face NeRF from Multiple Identities","created":"2024-03-29","cited_by_count":3,"area":null},{"id":"2409.01901","title":"3D-LEX v1.0: 3D Lexicons for American Sign Language and Sign Language of the Netherlands","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2510.18439","title":"Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation","created":"2025-10-21","cited_by_count":3,"area":"mllm"},{"id":"2307.05440","title":"ISLTranslate: Dataset for Translating Indian Sign Language","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2405.10718","title":"SignLLM: Sign Language Production Large Language Models","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2407.08906","title":"AirSketch: Generative Motion to Sketch","created":"2024-07-12","cited_by_count":2,"area":"diffusion"},{"id":"2409.09149","title":"Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss","created":"2024-09-13","cited_by_count":2,"area":"diffusion"},{"id":"2409.11960","title":"A Chinese Continuous Sign Language Dataset Based on Complex Environments","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2409.15284","title":"The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2506.06966","title":"Dual-view Spatio-Temporal Feature Fusion with CNN-Transformer Hybrid Network for Chinese Isolated Sign Language Recognition","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2512.07273","title":"RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2512.08094","title":"Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2603.10446","title":"SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.23617","title":"M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.22367","title":"CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2207.04021","title":"ASL-Homework-RGBD Dataset: An annotated dataset of 45 fluent and non-fluent signers performing American Sign Language homeworks","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2209.02402","title":"Topic Detection in Continuous Sign Language Videos","created":"2022-09-01","cited_by_count":1,"area":null}],"next_cursor":"100"}