{"list":"other","total":65,"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":"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"1809.10790","title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","created":"2018-09-27","cited_by_count":241},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2012.07277","title":"Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs","created":"2020-12-14","cited_by_count":83},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58},{"id":"2211.11736","title":"Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models","created":"2022-11-21","cited_by_count":58},{"id":"1708.04225","title":"Deep Object-Centric Representations for Generalizable Robot Learning","created":"2017-08-14","cited_by_count":50},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46},{"id":"1704.03414","title":"A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection","created":"2017-04-11","cited_by_count":43},{"id":"1907.05518","title":"Graph-Structured Visual Imitation","created":"2019-07-11","cited_by_count":43},{"id":"1811.05432","title":"Deep Object-Centric Policies for Autonomous Driving","created":"2018-11-13","cited_by_count":41},{"id":"1911.04679","title":"Object-Centric Task and Motion Planning in Dynamic Environments","created":"2019-11-12","cited_by_count":35},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21},{"id":"1910.03568","title":"Object-centric Forward Modeling for Model Predictive Control","created":"2019-10-08","cited_by_count":19},{"id":"2007.06245","title":"Reconstruction Bottlenecks in Object-Centric Generative Models","created":"2020-07-13","cited_by_count":17},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17},{"id":"2210.02324","title":"Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images","created":"2022-10-05","cited_by_count":16},{"id":"1906.01035","title":"A Perspective on Objects and Systematic Generalization in Model-Based RL","created":"2019-06-03","cited_by_count":14},{"id":"2107.09046","title":"Playful Interactions for Representation Learning","created":"2021-07-19","cited_by_count":13},{"id":"2204.08479","title":"Inductive Biases for Object-Centric Representations in the Presence of Complex Textures","created":"2022-04-18","cited_by_count":13},{"id":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11},{"id":"2303.05501","title":"PDSketch: Integrated Planning Domain Programming and Learning","created":"2023-03-09","cited_by_count":7}],"next_cursor":null}