{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2206.04119","title":"Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem","created":"2022-06-08","cited_by_count":236},{"id":"2210.13695","title":"Structure-based Drug Design with Equivariant Diffusion Models","created":"2022-10-24","cited_by_count":217},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"2212.11972","title":"Scalable Adaptive Computation for Iterative Generation","created":"2022-12-22","cited_by_count":195},{"id":"2301.10972","title":"On the Importance of Noise Scheduling for Diffusion Models","created":"2023-01-26","cited_by_count":194},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2012.07810","title":"Real-Time High-Resolution Background Matting","created":"2020-12-14","cited_by_count":173},{"id":"1703.03872","title":"Deep Image Matting","created":"2017-03-10","cited_by_count":150},{"id":"2303.17559","title":"DDP: Diffusion Model for Dense Visual Prediction","created":"2023-03-30","cited_by_count":148},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"1908.00672","title":"Indices Matter: Learning to Index for Deep Image Matting","created":"2019-08-02","cited_by_count":93},{"id":"2302.14816","title":"Monocular Depth Estimation using Diffusion Models","created":"2023-02-28","cited_by_count":87},{"id":"2012.06722","title":"Mask Guided Matting via Progressive Refinement Network","created":"2020-12-12","cited_by_count":84},{"id":"1909.09725","title":"Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation","created":"2019-09-20","cited_by_count":79},{"id":"2001.04069","title":"Natural Image Matting via Guided Contextual Attention","created":"2020-01-13","cited_by_count":78},{"id":"2206.02904","title":"The Creativity of Text-to-Image Generation","created":"2022-05-13","cited_by_count":73},{"id":"2305.16223","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":62},{"id":"2302.09057","title":"Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent","created":"2023-02-17","cited_by_count":58},{"id":"2305.15272","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","created":"2023-05-24","cited_by_count":56},{"id":"2104.08201","title":"Semantic Image Matting","created":"2021-04-16","cited_by_count":55},{"id":"1807.10088","title":"AlphaGAN: Generative adversarial networks for natural image matting","created":"2018-07-26","cited_by_count":50},{"id":"2003.07711","title":"$F$, $B$, Alpha Matting","created":"2020-03-17","cited_by_count":50},{"id":"2212.02773","title":"DiffusionInst: Diffusion Model for Instance Segmentation","created":"2022-12-06","cited_by_count":49},{"id":"2203.15662","title":"MatteFormer: Transformer-Based Image Matting via Prior-Tokens","created":"2022-03-29","cited_by_count":48},{"id":"2309.04509","title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","created":"2023-09-08","cited_by_count":41},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39},{"id":"2011.14288","title":"Learning Affinity-Aware Upsampling for Deep Image Matting","created":"2020-11-29","cited_by_count":37},{"id":"2009.06613","title":"High-Resolution Deep Image Matting","created":"2020-09-14","cited_by_count":36},{"id":"2306.05399","title":"Matting Anything","created":"2023-06-08","cited_by_count":31},{"id":"2201.06889","title":"Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation","created":"2022-01-18","cited_by_count":22},{"id":"2306.01721","title":"Denoising Diffusion Semantic Segmentation with Mask Prior Modeling","created":"2023-06-02","cited_by_count":15},{"id":"2109.12252","title":"Long-Range Feature Propagating for Natural Image Matting","created":"2021-09-25","cited_by_count":13},{"id":"2304.01171","title":"Revisiting Context Aggregation for Image Matting","created":"2023-04-03","cited_by_count":5}],"next_cursor":null}