{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1606.04586","title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning","created":"2016-06-14","cited_by_count":441},{"id":"1911.09785","title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","created":"2019-11-21","cited_by_count":349},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251},{"id":"1507.02672","title":"Semi-Supervised Learning with Ladder Networks","created":"2015-07-09","cited_by_count":247},{"id":"2106.05095","title":"ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation","created":"2021-06-09","cited_by_count":184},{"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":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99},{"id":"2004.02980","title":"LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood","created":"2020-04-06","cited_by_count":87},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"1907.10045","title":"xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera","created":"2019-07-23","cited_by_count":79},{"id":"1803.05959","title":"Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera","created":"2018-03-15","cited_by_count":68},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2208.01633","title":"UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture","created":"2022-08-02","cited_by_count":57},{"id":"2011.01519","title":"SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera","created":"2020-11-02","cited_by_count":49},{"id":"2207.02541","title":"Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection","created":"2022-07-06","cited_by_count":48},{"id":"2201.07929","title":"Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision","created":"2022-01-20","cited_by_count":34},{"id":"2308.06493","title":"EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere","created":"2023-08-12","cited_by_count":34},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"2307.08095","title":"Semi-DETR: Semi-Supervised Object Detection with Detection Transformers","created":"2023-07-16","cited_by_count":27},{"id":"2401.00889","title":"3D Human Pose Perception from Egocentric Stereo Videos","created":"2023-12-30","cited_by_count":23},{"id":"2204.11590","title":"Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training","created":"2022-04-25","cited_by_count":22},{"id":"2309.11962","title":"Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views","created":"2023-09-21","cited_by_count":22},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17},{"id":"1911.06641","title":"CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation","created":"2019-11-15","cited_by_count":16},{"id":"2406.06679","title":"PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation","created":"2024-06-10","cited_by_count":16},{"id":"2408.07221","title":"A Review of Pseudo-Labeling for Computer Vision","created":"2024-08-13","cited_by_count":16},{"id":"2408.17168","title":"EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs","created":"2024-08-30","cited_by_count":13},{"id":"2504.05265","title":"From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models","created":"2025-04-07","cited_by_count":11},{"id":"2503.11652","title":"Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation","created":"2025-03-14","cited_by_count":7},{"id":"2401.03836","title":"WidthFormer: Toward Efficient Transformer-based BEV View Transformation","created":"2024-01-08","cited_by_count":5},{"id":"2503.23094","title":"FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video","created":"2025-03-29","cited_by_count":5},{"id":"2411.18377","title":"XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration","created":"2024-11-27","cited_by_count":3},{"id":"2206.04785","title":"Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation","created":"2022-06-09","cited_by_count":2}],"next_cursor":null}