{"list":"other","total":58,"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":"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"id":"2107.14160","title":"Probabilistic and Geometric Depth: Detecting Objects in Perspective","created":"2021-07-29","cited_by_count":191},{"id":"2004.12636","title":"3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection","created":"2020-04-27","cited_by_count":176},{"id":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166},{"id":"1904.01649","title":"MVX-Net: Multimodal VoxelNet for 3D Object Detection","created":"2019-04-02","cited_by_count":163},{"id":"2009.00784","title":"CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection","created":"2020-09-02","cited_by_count":147},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2209.03102","title":"MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection","created":"2022-09-07","cited_by_count":62},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60},{"id":"2405.05258","title":"Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving","created":"2024-05-08","cited_by_count":54},{"id":"2210.08064","title":"LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds","created":"2022-10-14","cited_by_count":41},{"id":"2203.15245","title":"Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients","created":"2022-03-29","cited_by_count":17},{"id":"1803.00387","title":"A General Pipeline for 3D Detection of Vehicles","created":"2018-02-12","cited_by_count":15},{"id":"2209.10733","title":"FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection","created":"2022-09-22","cited_by_count":14},{"id":"2407.19394","title":"Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets","created":"2024-07-28","cited_by_count":14},{"id":"2112.13310","title":"Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence","created":"2021-12-26","cited_by_count":12},{"id":"2211.13529","title":"3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection","created":"2022-11-24","cited_by_count":11},{"id":"2101.00561","title":"Six-channel Image Representation for Cross-domain Object Detection","created":"2021-01-03","cited_by_count":8},{"id":"2007.06233","title":"Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection","created":"2020-07-13","cited_by_count":7},{"id":"2201.09396","title":"Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs","created":"2022-01-23","cited_by_count":6},{"id":"2309.02049","title":"Diffusion-based 3D Object Detection with Random Boxes","created":"2023-09-05","cited_by_count":5},{"id":"2410.09691","title":"Robust 3D Point Clouds Classification based on Declarative Defenders","created":"2024-10-13","cited_by_count":2},{"id":"2410.14874","title":"Beyond Isolated Heads: Multi-Overlapped-Head Self-Attention for Vision Transformers","created":"2024-10-18","cited_by_count":1}],"next_cursor":null}