{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1808.00671","title":"PCN: Point Completion Network","created":"2018-08-02","cited_by_count":384},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2103.03231","title":"DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks","created":"2021-03-04","cited_by_count":232},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"1810.10191","title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","created":"2018-10-24","cited_by_count":154},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"1805.11085","title":"More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch","created":"2018-05-28","cited_by_count":102},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"2204.02389","title":"ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer","created":"2022-04-05","cited_by_count":75},{"id":"2109.07991","title":"ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations","created":"2021-09-16","cited_by_count":68},{"id":"2212.03858","title":"See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation","created":"2022-12-07","cited_by_count":68},{"id":"1710.05512","title":"The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?","created":"2017-10-16","cited_by_count":67},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"1906.06322","title":"Connecting Touch and Vision via Cross-Modal Prediction","created":"2019-06-14","cited_by_count":66},{"id":"2012.08456","title":"TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors","created":"2020-12-15","cited_by_count":63},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"2109.04027","title":"Taxim: An Example-based Simulation Model for GelSight Tactile Sensors","created":"2021-09-09","cited_by_count":43},{"id":"2007.03778","title":"3D Shape Reconstruction from Vision and Touch","created":"2020-07-07","cited_by_count":42},{"id":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","cited_by_count":42},{"id":"1903.04128","title":"Manipulation by Feel: Touch-Based Control with Deep Predictive Models","created":"2019-03-11","cited_by_count":36},{"id":"2107.09584","title":"Active 3D Shape Reconstruction from Vision and Touch","created":"2021-07-20","cited_by_count":34},{"id":"1706.00932","title":"See, Hear, and Read: Deep Aligned Representations","created":"2017-06-03","cited_by_count":32},{"id":"2109.09884","title":"ShapeMap 3-D: Efficient shape mapping through dense touch and vision","created":"2021-09-20","cited_by_count":31},{"id":"1708.00922","title":"Improved GelSight Tactile Sensor for Measuring Geometry and Slip","created":"2017-08-02","cited_by_count":28},{"id":"2203.05549","title":"Context is Everything: Implicit Identification for Dynamics Adaptation","created":"2022-03-10","cited_by_count":27},{"id":"1704.02223","title":"An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges","created":"2017-04-07","cited_by_count":21},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18},{"id":"1902.06273","title":"\"Touching to See\" and \"Seeing to Feel\": Robotic Cross-modal SensoryData Generation for Visual-Tactile Perception","created":"2019-02-17","cited_by_count":17},{"id":"1708.04441","title":"Localizing the Object Contact through Matching Tactile Features with Visual Map","created":"2017-08-15","cited_by_count":11},{"id":"1708.04776","title":"Modality-specific Cross-modal Similarity Measurement with Recurrent Attention Network","created":"2017-08-16","cited_by_count":11},{"id":"2203.09149","title":"Active Visuo-Haptic Object Shape Completion","created":"2022-03-17","cited_by_count":11},{"id":"2208.02885","title":"Grasp Stability Prediction with Sim-to-Real Transfer from Tactile Sensing","created":"2022-08-04","cited_by_count":8}],"next_cursor":null}