{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"1612.02649","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","created":"2016-12-08","cited_by_count":243},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2112.07068","title":"Score-Based Generative Modeling with Critically-Damped Langevin Diffusion","created":"2021-12-14","cited_by_count":233},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"1807.11590","title":"Acquisition of Localization Confidence for Accurate Object Detection","created":"2018-07-30","cited_by_count":176},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117},{"id":"1609.06647","title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge","created":"2016-09-21","cited_by_count":116},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"1704.08509","title":"No More Discrimination: Cross City Adaptation of Road Scene Segmenters","created":"2017-04-27","cited_by_count":111},{"id":"2201.04684","title":"BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations","created":"2022-01-12","cited_by_count":99},{"id":"2009.05475","title":"Adversarial score matching and improved sampling for image generation","created":"2020-09-11","cited_by_count":96},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88},{"id":"1611.08408","title":"Semantic Segmentation using Adversarial Networks","created":"2016-11-25","cited_by_count":73},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"1511.07394","title":"Where To Look: Focus Regions for Visual Question Answering","created":"2015-11-23","cited_by_count":64},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54},{"id":"1807.10088","title":"AlphaGAN: Generative adversarial networks for natural image matting","created":"2018-07-26","cited_by_count":50},{"id":"2210.05944","title":"ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation","created":"2022-10-12","cited_by_count":42},{"id":"2308.16777","title":"Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models","created":"2023-08-31","cited_by_count":33},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27},{"id":"1512.02167","title":"Simple Baseline for Visual Question Answering","created":"2015-12-07","cited_by_count":24},{"id":"2209.11228","title":"NamedMask: Distilling Segmenters from Complementary Foundation Models","created":"2022-09-22","cited_by_count":20},{"id":"2309.01141","title":"VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders","created":"2023-09-03","cited_by_count":18},{"id":"2406.01451","title":"SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation","created":"2024-06-03","cited_by_count":17},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","cited_by_count":13},{"id":"2208.05647","title":"PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding","created":"2022-08-11","cited_by_count":12},{"id":"2006.10451","title":"Learning High-Resolution Domain-Specific Representations with a GAN Generator","created":"2020-06-18","cited_by_count":9},{"id":"2310.10975","title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","created":"2023-10-17","cited_by_count":8},{"id":"2311.01091","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","created":"2023-11-02","cited_by_count":6},{"id":"2310.16616","title":"Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network","created":"2023-10-25","cited_by_count":5},{"id":"2310.18142","title":"Semi-Supervised Panoptic Narrative Grounding","created":"2023-10-27","cited_by_count":4}],"next_cursor":null}