{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"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":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"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":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"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":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2107.03380","title":"RRL: Resnet as representation for Reinforcement Learning","created":"2021-07-07","cited_by_count":91},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82},{"id":"2303.07798","title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","created":"2023-03-14","cited_by_count":70},{"id":"2101.05181","title":"Memory-Augmented Reinforcement Learning for Image-Goal Navigation","created":"2021-01-13","cited_by_count":66},{"id":"2110.15443","title":"Equivariant $Q$ Learning in Spatial Action Spaces","created":"2021-10-28","cited_by_count":62},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52},{"id":"2406.20095","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","created":"2024-06-28","cited_by_count":52},{"id":"2209.02778","title":"Multi-skill Mobile Manipulation for Object Rearrangement","created":"2022-09-06","cited_by_count":46},{"id":"2310.09289","title":"An Unbiased Look at Datasets for Visuo-Motor Pre-Training","created":"2023-10-13","cited_by_count":42},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24},{"id":"2311.05348","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","created":"2023-11-09","cited_by_count":24},{"id":"2108.01069","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","created":"2021-08-02","cited_by_count":23},{"id":"2308.06564","title":"EquiDiff: A Conditional Equivariant Diffusion Model For Trajectory Prediction","created":"2023-08-12","cited_by_count":21},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20},{"id":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","cited_by_count":13}],"next_cursor":null}