{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2111.11215","title":"Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction","created":"2021-11-22","cited_by_count":964},{"id":"2103.14024","title":"PlenOctrees for Real-time Rendering of Neural Radiance Fields","created":"2021-03-25","cited_by_count":905},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2103.10380","title":"FastNeRF: High-Fidelity Neural Rendering at 200FPS","created":"2021-03-18","cited_by_count":511},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2103.14645","title":"Baking Neural Radiance Fields for Real-Time View Synthesis","created":"2021-03-26","cited_by_count":468},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2104.01542","title":"Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations","created":"2021-04-04","cited_by_count":108},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"id":"1904.04686","title":"Multi-Target Embodied Question Answering","created":"2019-04-09","cited_by_count":74},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68},{"id":"2204.00628","title":"Learning Neural Acoustic Fields","created":"2022-04-04","cited_by_count":65},{"id":"2202.13330","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","created":"2022-02-27","cited_by_count":63},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51},{"id":"1708.04686","title":"VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation","created":"2017-08-15","cited_by_count":50},{"id":"2003.00403","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","created":"2020-03-01","cited_by_count":50},{"id":"2111.06387","title":"Learning Signal-Agnostic Manifolds of Neural Fields","created":"2021-11-11","cited_by_count":45},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34},{"id":"2202.07028","title":"One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones","created":"2022-02-14","cited_by_count":26},{"id":"2207.06403","title":"3D Concept Grounding on Neural Fields","created":"2022-07-13","cited_by_count":13},{"id":"1704.03895","title":"What's in a Question: Using Visual Questions as a Form of Supervision","created":"2017-04-12","cited_by_count":4}],"next_cursor":null}