{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"1908.07201","title":"Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images \"In the Wild\"","created":"2019-08-20","cited_by_count":106},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"1811.05804","title":"Creatures great and SMAL: Recovering the shape and motion of animals from video","created":"2018-11-14","cited_by_count":84},{"id":"2007.11110","title":"Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop","created":"2020-07-21","cited_by_count":81},{"id":"2011.12438","title":"Continuous Surface Embeddings","created":"2020-11-24","cited_by_count":80},{"id":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66},{"id":"1912.08265","title":"Learning from Synthetic Animals","created":"2019-12-17","cited_by_count":65},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","cited_by_count":59},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2203.15536","title":"BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information","created":"2022-03-29","cited_by_count":51},{"id":"2303.14747","title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","created":"2023-03-26","cited_by_count":47},{"id":"2308.11737","title":"Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape","created":"2023-08-22","cited_by_count":44},{"id":"2008.06133","title":"3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View","created":"2020-08-13","cited_by_count":40},{"id":"2203.07436","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","created":"2022-03-14","cited_by_count":39},{"id":"2304.10535","title":"Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion","created":"2023-04-20","cited_by_count":38},{"id":"2004.07788","title":"RGBD-Dog: Predicting Canine Pose from RGBD Sensors","created":"2020-04-16","cited_by_count":35},{"id":"2105.09396","title":"Birds of a Feather: Capturing Avian Shape Models from Images","created":"2021-05-19","cited_by_count":30},{"id":"2403.17103","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","created":"2024-03-25","cited_by_count":26},{"id":"2412.00837","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer","created":"2024-12-01","cited_by_count":20},{"id":"2108.13958","title":"A Novel Dataset for Keypoint Detection of quadruped Animals from Images","created":"2021-08-31","cited_by_count":19},{"id":"2106.10102","title":"hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition","created":"2021-06-18","cited_by_count":18},{"id":"2306.08103","title":"Generating Images with 3D Annotations Using Diffusion Models","created":"2023-06-13","cited_by_count":18},{"id":"2111.08176","title":"Coarse-to-fine Animal Pose and Shape Estimation","created":"2021-11-16","cited_by_count":16},{"id":"2404.03042","title":"AWOL: Analysis WithOut synthesis using Language","created":"2024-04-03","cited_by_count":12},{"id":"2412.08101","title":"Generative Zoo","created":"2024-12-11","cited_by_count":12},{"id":"2412.04464","title":"DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction","created":"2024-12-05","cited_by_count":11},{"id":"2312.11894","title":"3D-LFM: Lifting Foundation Model","created":"2023-12-19","cited_by_count":8},{"id":"2410.03438","title":"Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images","created":"2024-10-04","cited_by_count":7},{"id":"2305.17845","title":"SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose Estimation","created":"2023-05-29","cited_by_count":6},{"id":"2507.10437","title":"4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos","created":"2025-07-14","cited_by_count":6},{"id":"2507.04258","title":"MoReMouse: Monocular Reconstruction of Laboratory Mouse","created":"2025-07-06","cited_by_count":1}],"next_cursor":null}