{"list":"other","total":66,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"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":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"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":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"id":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"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":"2005.02819","title":"Geoopt: Riemannian Optimization in PyTorch","created":"2020-05-06","cited_by_count":114},{"id":"2307.14768","title":"Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining","created":"2023-07-27","cited_by_count":105},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77},{"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":"2110.05382","title":"SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition","created":"2021-10-11","cited_by_count":60},{"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":"2405.04164","title":"Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation","created":"2024-05-07","cited_by_count":57},{"id":"2303.03202","title":"Continuous Sign Language Recognition with Correlation Network","created":"2023-03-06","cited_by_count":56},{"id":"2501.15187","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","created":"2025-01-25","cited_by_count":56},{"id":"2307.07361","title":"Gloss Attention for Gloss-free Sign Language Translation","created":"2023-07-14","cited_by_count":51},{"id":"2303.15919","title":"Fully Hyperbolic Convolutional Neural Networks for Computer Vision","created":"2023-03-28","cited_by_count":49},{"id":"2303.12080","title":"Natural Language-Assisted Sign Language Recognition","created":"2023-03-21","cited_by_count":46},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44},{"id":"2402.09611","title":"Towards Privacy-Aware Sign Language Translation at Scale","created":"2024-02-14","cited_by_count":44},{"id":"2407.01290","title":"Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space","created":"2024-07-01","cited_by_count":43},{"id":"2010.05264","title":"Boosting Continuous Sign Language Recognition via Cross Modality Augmentation","created":"2020-10-11","cited_by_count":40},{"id":"2202.13852","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","created":"2022-02-28","cited_by_count":40},{"id":"2304.06371","title":"Sign Language Translation from Instructional Videos","created":"2023-04-13","cited_by_count":39},{"id":"2008.10428","title":"Global-local Enhancement Network for NMFs-aware Sign Language Recognition","created":"2020-08-24","cited_by_count":38},{"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},{"id":"2010.04002","title":"Watch, read and lookup: learning to spot signs from multiple supervisors","created":"2020-10-08","cited_by_count":35},{"id":"2302.05075","title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","created":"2023-02-10","cited_by_count":35},{"id":"2103.16481","title":"Read and Attend: Temporal Localisation in Sign Language Videos","created":"2021-03-30","cited_by_count":34},{"id":"2303.12793","title":"CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning","created":"2023-03-22","cited_by_count":33},{"id":"2105.02351","title":"Content4All Open Research Sign Language Translation Datasets","created":"2021-05-05","cited_by_count":30},{"id":"2111.03635","title":"BBC-Oxford British Sign Language Dataset","created":"2021-11-05","cited_by_count":28},{"id":"2308.10809","title":"Improving Continuous Sign Language Recognition with Cross-Lingual Signs","created":"2023-08-21","cited_by_count":27},{"id":"2207.08734","title":"Temporal Lift Pooling for Continuous Sign Language Recognition","created":"2022-07-18","cited_by_count":26},{"id":"2501.09754","title":"Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues","created":"2025-01-16","cited_by_count":26},{"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},{"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},{"id":"2312.15645","title":"Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment","created":"2023-12-25","cited_by_count":23},{"id":"2408.08544","title":"Scaling up Multimodal Pre-training for Sign Language Understanding","created":"2024-08-16","cited_by_count":21},{"id":"2208.02802","title":"Automatic dense annotation of large-vocabulary sign language videos","created":"2022-08-04","cited_by_count":20},{"id":"2406.06907","title":"SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale","created":"2024-06-11","cited_by_count":19},{"id":"2404.11499","title":"A Data-Driven Representation for Sign Language Production","created":"2024-04-17","cited_by_count":17},{"id":"2308.09525","title":"Improving 3D Pose Estimation for Sign Language","created":"2023-08-18","cited_by_count":16},{"id":"2308.09622","title":"Is context all you need? Scaling Neural Sign Language Translation to Large Domains of Discourse","created":"2023-08-18","cited_by_count":15},{"id":"2503.08529","title":"SignRep: Enhancing Self-Supervised Sign Representations","created":"2025-03-11","cited_by_count":15},{"id":"2205.04152","title":"Scaling up sign spotting through sign language dictionaries","created":"2022-05-09","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":"2309.02965","title":"Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction","created":"2023-09-06","cited_by_count":10},{"id":"2402.07726","title":"Unsupervised Sign Language Translation and Generation","created":"2024-02-12","cited_by_count":4},{"id":"2502.05869","title":"HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition","created":"2025-02-09","cited_by_count":4},{"id":"1812.10408","title":"Hyperbolic Deep Learning for Chinese Natural Language Understanding","created":"2018-12-11","cited_by_count":3},{"id":"2308.04248","title":"Gloss Alignment Using Word Embeddings","created":"2023-08-08","cited_by_count":3}],"next_cursor":null}