{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"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":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"1806.00035","title":"Assessing Generative Models via Precision and Recall","created":"2018-05-31","cited_by_count":406},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"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":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2012.10366","title":"Learning Complex 3D Human Self-Contact","created":"2020-12-18","cited_by_count":40},{"id":"2403.16428","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","created":"2024-03-25","cited_by_count":35},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"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":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28},{"id":"2407.03204","title":"Expressive Gaussian Human Avatars from Monocular RGB Video","created":"2024-07-03","cited_by_count":21},{"id":"2403.04381","title":"Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation","created":"2024-03-07","cited_by_count":19},{"id":"2208.08439","title":"MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes","created":"2022-08-17","cited_by_count":18},{"id":"2309.16670","title":"Decaf: Monocular Deformation Capture for Face and Hand Interactions","created":"2023-09-28","cited_by_count":18},{"id":"2206.02257","title":"Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey","created":"2022-06-05","cited_by_count":17},{"id":"2402.19009","title":"Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding","created":"2024-02-29","cited_by_count":10},{"id":"2411.14786","title":"FastGrasp: Efficient Grasp Synthesis with Diffusion","created":"2024-11-22","cited_by_count":7},{"id":"2502.15251","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","created":"2025-02-21","cited_by_count":7},{"id":"2505.17090","title":"EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language","created":"2025-05-20","cited_by_count":4}],"next_cursor":null}