{"list":"other","total":62,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2306.17843","title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","created":"2023-06-30","cited_by_count":397},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"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":"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":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"2204.06184","title":"COAP: Compositional Articulated Occupancy of People","created":"2022-04-13","cited_by_count":59},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2110.03480","title":"Learning to Regress Bodies from Images using Differentiable Semantic Rendering","created":"2021-10-07","cited_by_count":39},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38},{"id":"2209.09552","title":"Cross-modal Learning for Image-Guided Point Cloud Shape Completion","created":"2022-09-20","cited_by_count":36},{"id":"2404.04819","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","created":"2024-04-07","cited_by_count":29},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21},{"id":"2207.00826","title":"ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs","created":"2022-07-02","cited_by_count":17},{"id":"2409.16178","title":"SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image","created":"2024-09-24","cited_by_count":9}],"next_cursor":null}