{"list":"other","total":75,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2306.17843","title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","created":"2023-06-30","cited_by_count":397},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"2211.16431","title":"NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360{\\deg} Views","created":"2022-11-29","cited_by_count":148},{"id":"1908.10543","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","created":"2019-08-28","cited_by_count":146},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61},{"id":"2204.03635","title":"Zero-Shot Category-Level Object Pose Estimation","created":"2022-04-07","cited_by_count":57},{"id":"2306.09109","title":"NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations","created":"2023-06-15","cited_by_count":53},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45},{"id":"2102.11870","title":"UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering","created":"2021-02-23","cited_by_count":44},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32},{"id":"2310.06836","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","created":"2023-10-10","cited_by_count":32},{"id":"2306.05720","title":"Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model","created":"2023-06-09","cited_by_count":30},{"id":"2106.00677","title":"Bootstrap Your Own Correspondences","created":"2021-06-01","cited_by_count":27},{"id":"2303.16201","title":"ASIC: Aligning Sparse in-the-wild Image Collections","created":"2023-03-28","cited_by_count":27},{"id":"2210.07199","title":"Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild","created":"2022-10-13","cited_by_count":22},{"id":"2212.08861","title":"DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models","created":"2022-12-17","cited_by_count":12},{"id":"2212.00281","title":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models","created":"2022-12-01","cited_by_count":2}],"next_cursor":null}