{"list":"other","total":66,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2208.09392","title":"Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise","created":"2022-08-19","cited_by_count":276},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2104.10475","title":"Camouflaged Object Segmentation with Distraction Mining","created":"2021-04-21","cited_by_count":151},{"id":"1703.03872","title":"Deep Image Matting","created":"2017-03-10","cited_by_count":150},{"id":"2303.09769","title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners","created":"2023-03-17","cited_by_count":130},{"id":"2011.11961","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","created":"2020-11-24","cited_by_count":127},{"id":"2007.08074","title":"Suppress and Balance: A Simple Gated Network for Salient Object Detection","created":"2020-07-16","cited_by_count":126},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124},{"id":"2304.05750","title":"Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications","created":"2023-04-12","cited_by_count":121},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2003.00651","title":"Global Context-Aware Progressive Aggregation Network for Salient Object Detection","created":"2020-03-02","cited_by_count":109},{"id":"2312.12274","title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","created":"2023-12-19","cited_by_count":73},{"id":"1809.01354","title":"Semantic Human Matting","created":"2018-09-05","cited_by_count":67},{"id":"2012.11582","title":"HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation","created":"2020-12-21","cited_by_count":66},{"id":"2002.00569","title":"DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data","created":"2020-02-03","cited_by_count":61},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60},{"id":"2210.09670","title":"Hierarchical Normalization for Robust Monocular Depth Estimation","created":"2022-10-18","cited_by_count":52},{"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":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44},{"id":"2311.18832","title":"Exploiting Diffusion Prior for Generalizable Dense Prediction","created":"2023-11-30","cited_by_count":38},{"id":"2312.01985","title":"UniGS: Unified Representation for Image Generation and Segmentation","created":"2023-12-04","cited_by_count":29},{"id":"2203.16828","title":"Rethinking Portrait Matting with Privacy Preserving","created":"2022-03-31","cited_by_count":25},{"id":"2401.10227","title":"A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting","created":"2024-01-18","cited_by_count":18},{"id":"2212.13693","title":"Parsing Objects at a Finer Granularity: A Survey","created":"2022-12-28","cited_by_count":2}],"next_cursor":null}