{"list":"other","total":85,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"1804.00175","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","created":"2018-03-31","cited_by_count":283},{"id":"1808.08319","title":"BOP: Benchmark for 6D Object Pose Estimation","created":"2018-08-24","cited_by_count":254},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"1701.05498","title":"T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects","created":"2017-01-19","cited_by_count":210},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152},{"id":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"id":"2204.10776","title":"Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images","created":"2022-04-22","cited_by_count":121},{"id":"2311.15707","title":"SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation","created":"2023-11-27","cited_by_count":117},{"id":"1904.03167","title":"HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects","created":"2019-04-05","cited_by_count":110},{"id":"2108.06753","title":"Learning Open-World Object Proposals without Learning to Classify","created":"2021-08-15","cited_by_count":109},{"id":"1905.09304","title":"PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking","created":"2019-05-22","cited_by_count":91},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91},{"id":"2307.11067","title":"CNOS: A Strong Baseline for CAD-based Novel Object Segmentation","created":"2023-07-20","cited_by_count":87},{"id":"2007.08073","title":"Unseen Object Instance Segmentation for Robotic Environments","created":"2020-07-16","cited_by_count":85},{"id":"1512.07506","title":"Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd","created":"2015-12-23","cited_by_count":79},{"id":"1911.01911","title":"BlenderProc","created":"2019-10-25","cited_by_count":77},{"id":"2302.13075","title":"BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects","created":"2023-02-25","cited_by_count":70},{"id":"2007.15157","title":"Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation","created":"2020-07-30","cited_by_count":64},{"id":"2003.06800","title":"OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features","created":"2020-03-15","cited_by_count":35},{"id":"2311.03774","title":"Meta-Adapter: An Online Few-shot Learner for Vision-Language Model","created":"2023-11-07","cited_by_count":31},{"id":"2303.09674","title":"DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection","created":"2023-03-16","cited_by_count":21},{"id":"2304.05096","title":"Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection","created":"2023-04-11","cited_by_count":21},{"id":"2210.04845","title":"FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training","created":"2022-10-10","cited_by_count":20},{"id":"2211.11679","title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","created":"2022-11-21","cited_by_count":19},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19},{"id":"2401.13051","title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","created":"2024-01-23","cited_by_count":17},{"id":"1803.04610","title":"Target Driven Instance Detection","created":"2018-03-13","cited_by_count":14},{"id":"2211.14782","title":"Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection","created":"2022-11-27","cited_by_count":12},{"id":"2307.03073","title":"Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning","created":"2023-07-06","cited_by_count":12},{"id":"2302.03793","title":"Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction","created":"2023-02-07","cited_by_count":10},{"id":"2312.03628","title":"Boosting Segment Anything Model Towards Open-Vocabulary Learning","created":"2023-12-06","cited_by_count":10},{"id":"2305.17220","title":"VoxDet: Voxel Learning for Novel Instance Detection","created":"2023-05-26","cited_by_count":8},{"id":"2310.19257","title":"A High-Resolution Dataset for Instance Detection with Multi-View Instance Capture","created":"2023-10-30","cited_by_count":4},{"id":"2402.16674","title":"ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer","created":"2024-02-26","cited_by_count":3}],"next_cursor":null}