{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"1804.05172","title":"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach","created":"2018-04-14","cited_by_count":120},{"id":"1704.03470","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","created":"2017-04-11","cited_by_count":119},{"id":"1301.3592","title":"Deep Learning for Detecting Robotic Grasps","created":"2013-01-16","cited_by_count":116},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78},{"id":"2007.15157","title":"Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation","created":"2020-07-30","cited_by_count":64},{"id":"1909.04810","title":"Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network","created":"2019-09-11","cited_by_count":59},{"id":"2107.05287","title":"End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB","created":"2021-07-12","cited_by_count":44},{"id":"2109.11103","title":"Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling","created":"2021-09-23","cited_by_count":43},{"id":"2308.00640","title":"VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes","created":"2023-08-01","cited_by_count":42},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2302.12610","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","created":"2023-02-24","cited_by_count":34},{"id":"2309.09818","title":"Grasp-Anything: Large-scale Grasp Dataset from Foundation Models","created":"2023-09-18","cited_by_count":33},{"id":"1808.10313","title":"ROI-based Robotic Grasp Detection for Object Overlapping Scenes","created":"2018-08-30","cited_by_count":31},{"id":"2406.09489","title":"Language-driven Grasp Detection","created":"2024-06-13","cited_by_count":26},{"id":"2104.00492","title":"A Joint Network for Grasp Detection Conditioned on Natural Language Commands","created":"2021-04-01","cited_by_count":23},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22},{"id":"2203.08037","title":"Interactive Robotic Grasping with Attribute-Guided Disambiguation","created":"2022-03-15","cited_by_count":19},{"id":"2205.04028","title":"Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions","created":"2022-05-09","cited_by_count":19},{"id":"2309.10932","title":"Open-Vocabulary Affordance Detection using Knowledge Distillation and Text-Point Correlation","created":"2023-09-19","cited_by_count":18},{"id":"2407.13842","title":"Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidance","created":"2024-07-18","cited_by_count":16},{"id":"2202.11911","title":"When Transformer Meets Robotic Grasping: Exploits Context for Efficient Grasp Detection","created":"2022-02-24","cited_by_count":12},{"id":"2304.09448","title":"EC^2: Emergent Communication for Embodied Control","created":"2023-04-19","cited_by_count":10},{"id":"2108.01483","title":"Research Challenges and Progress in Robotic Grasping and Manipulation Competitions","created":"2021-08-03","cited_by_count":9},{"id":"2211.04275","title":"Machine Learning-based Framework for Optimally Solving the Analytical Inverse Kinematics for Redundant Manipulators","created":"2022-11-08","cited_by_count":9},{"id":"2407.17967","title":"Lightweight Language-driven Grasp Detection using Conditional Consistency Model","created":"2024-07-25","cited_by_count":9},{"id":"2211.04895","title":"Grasp Learning: Models, Methods, and Performance","created":"2022-11-09","cited_by_count":8},{"id":"2211.02516","title":"Singularity Avoidance with Application to Online Trajectory Optimization for Serial Manipulators","created":"2022-11-04","cited_by_count":7}],"next_cursor":null}