{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"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":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"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":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87},{"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":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"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":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65},{"id":"1907.10043","title":"Canonical Surface Mapping via Geometric Cycle Consistency","created":"2019-07-23","cited_by_count":63},{"id":"2107.10844","title":"DOVE: Learning Deformable 3D Objects by Watching Videos","created":"2021-07-22","cited_by_count":61},{"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":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43},{"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":"2306.00576","title":"MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding","created":"2023-06-01","cited_by_count":36},{"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":"2211.03889","title":"Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories","created":"2022-11-07","cited_by_count":29},{"id":"2403.17103","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","created":"2024-03-25","cited_by_count":26},{"id":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21},{"id":"2311.18303","title":"OmniMotionGPT: Animal Motion Generation with Limited Data","created":"2023-11-30","cited_by_count":20},{"id":"2412.00837","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer","created":"2024-12-01","cited_by_count":20},{"id":"2405.11286","title":"Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion","created":"2024-05-18","cited_by_count":19},{"id":"2111.08176","title":"Coarse-to-fine Animal Pose and Shape Estimation","created":"2021-11-16","cited_by_count":16},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9},{"id":"2112.02091","title":"Class-agnostic Reconstruction of Dynamic Objects from Videos","created":"2021-12-03","cited_by_count":8},{"id":"2412.13185","title":"Move-in-2D: 2D-Conditioned Human Motion Generation","created":"2024-12-17","cited_by_count":8},{"id":"2507.10437","title":"4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos","created":"2025-07-14","cited_by_count":6},{"id":"2411.10275","title":"4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields","created":"2024-11-15","cited_by_count":5},{"id":"2504.15782","title":"Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos","created":"2025-04-22","cited_by_count":4},{"id":"2406.14412","title":"Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data","created":"2024-06-20","cited_by_count":1}],"next_cursor":null}