{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"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":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"1812.04072","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","created":"2018-12-10","cited_by_count":105},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"1905.12887","title":"Does computer vision matter for action?","created":"2019-05-30","cited_by_count":64},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"1411.4958","title":"Designing Deep Networks for Surface Normal Estimation","created":"2014-11-18","cited_by_count":59},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"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":"2310.16667","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","created":"2023-10-25","cited_by_count":46},{"id":"2309.01151","title":"EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment","created":"2023-09-03","cited_by_count":44},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41},{"id":"2206.08355","title":"FWD: Real-time Novel View Synthesis with Forward Warping and Depth","created":"2022-06-16","cited_by_count":39},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34},{"id":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33},{"id":"2401.03201","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","created":"2024-01-06","cited_by_count":32},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31},{"id":"1806.09573","title":"Learning Single-Image Depth from Videos using Quality Assessment Networks","created":"2018-06-25","cited_by_count":25},{"id":"2303.11057","title":"Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation","created":"2023-03-20","cited_by_count":25},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","cited_by_count":18},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18},{"id":"1812.00940","title":"Visual Memory for Robust Path Following","created":"2018-12-03","cited_by_count":16},{"id":"2112.01520","title":"Recognizing Scenes from Novel Viewpoints","created":"2021-12-02","cited_by_count":5}],"next_cursor":null}