{"list":"other","total":61,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2002.10187","title":"3DSSD: Point-based 3D Single Stage Object Detector","created":"2020-02-24","cited_by_count":440},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1902.06326","title":"PIXOR: Real-time 3D Object Detection from Point Clouds","created":"2019-02-17","cited_by_count":358},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2104.00678","title":"Group-Free 3D Object Detection via Transformers","created":"2021-04-01","cited_by_count":215},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"1511.02300","title":"Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images","created":"2015-11-07","cited_by_count":111},{"id":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97},{"id":"2107.03438","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","created":"2021-07-07","cited_by_count":89},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84},{"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":"2007.14626","title":"Object-and-Action Aware Model for Visual Language Navigation","created":"2020-07-29","cited_by_count":77},{"id":"2104.04386","title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding","created":"2021-04-09","cited_by_count":52},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33},{"id":"2012.01634","title":"Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D","created":"2020-12-03","cited_by_count":30},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16},{"id":"1906.01452","title":"Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning","created":"2019-06-03","cited_by_count":12},{"id":"2208.14209","title":"A Circular Window-based Cascade Transformer for Online Action Detection","created":"2022-08-30","cited_by_count":4}],"next_cursor":null}