{"list":"other","total":97,"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":"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"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":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"1904.06830","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","created":"2019-04-15","cited_by_count":147},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2104.14639","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","created":"2021-04-29","cited_by_count":123},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88},{"id":"1904.03754","title":"ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact","created":"2019-04-07","cited_by_count":87},{"id":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82},{"id":"1902.07816","title":"Mixture Models for Diverse Machine Translation: Tricks of the Trade","created":"2019-02-20","cited_by_count":77},{"id":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2403.17827","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","created":"2024-03-26","cited_by_count":62},{"id":"2403.19649","title":"GraspXL: Generating Grasping Motions for Diverse Objects at Scale","created":"2024-03-28","cited_by_count":60},{"id":"1610.04889","title":"Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input","created":"2016-10-16","cited_by_count":56},{"id":"2309.03891","title":"ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation","created":"2023-09-07","cited_by_count":55},{"id":"2208.12250","title":"Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands","created":"2022-08-25","cited_by_count":51},{"id":"2211.00099","title":"UmeTrack: Unified multi-view end-to-end hand tracking for VR","created":"2022-10-31","cited_by_count":50},{"id":"2309.08942","title":"AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose","created":"2023-09-16","cited_by_count":49},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48},{"id":"1704.02612","title":"BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis","created":"2017-04-09","cited_by_count":46},{"id":"2312.08869","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","created":"2023-12-10","cited_by_count":44},{"id":"2208.10441","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","created":"2022-08-22","cited_by_count":40},{"id":"2407.12371","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","created":"2024-07-17","cited_by_count":36},{"id":"1908.08391","title":"Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks","created":"2019-08-22","cited_by_count":29},{"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":"2312.02137","title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","created":"2023-12-04","cited_by_count":26},{"id":"2204.13998","title":"Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction","created":"2022-04-03","cited_by_count":24},{"id":"2203.10385","title":"PressureVision: Estimating Hand Pressure from a Single RGB Image","created":"2022-03-19","cited_by_count":23},{"id":"1904.04882","title":"Contextual Attention for Hand Detection in the Wild","created":"2019-04-09","cited_by_count":16},{"id":"2104.11466","title":"H2O: A Benchmark for Visual Human-human Object Handover Analysis","created":"2021-04-23","cited_by_count":16},{"id":"2305.01618","title":"ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation","created":"2023-05-02","cited_by_count":16},{"id":"2301.07652","title":"HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects","created":"2023-01-18","cited_by_count":12},{"id":"2407.12727","title":"NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model","created":"2024-07-17","cited_by_count":10},{"id":"2312.07937","title":"BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics","created":"2023-12-13","cited_by_count":7},{"id":"2405.04963","title":"Audio Matters Too! Enhancing Markerless Motion Capture with Audio Signals for String Performance Capture","created":"2024-05-08","cited_by_count":3}],"next_cursor":null}