{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","cited_by_count":150},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"1612.05872","title":"3D Shape Induction from 2D Views of Multiple Objects","created":"2016-12-18","cited_by_count":121},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"1811.00472","title":"Class-Agnostic Counting","created":"2018-11-01","cited_by_count":85},{"id":"1906.06818","title":"Stacked Capsule Autoencoders","created":"2019-06-17","cited_by_count":82},{"id":"2208.13721","title":"CounTR: Transformer-based Generalised Visual Counting","created":"2022-08-29","cited_by_count":79},{"id":"2211.08217","title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","created":"2022-11-15","cited_by_count":65},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"2211.16582","title":"SinDDM: A Single Image Denoising Diffusion Model","created":"2022-11-29","cited_by_count":60},{"id":"2407.04619","title":"CountGD: Multi-Modal Open-World Counting","created":"2024-07-05","cited_by_count":59},{"id":"2207.10988","title":"Few-shot Object Counting and Detection","created":"2022-07-22","cited_by_count":55},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50},{"id":"2404.16622","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","created":"2024-04-25","cited_by_count":49},{"id":"2211.12445","title":"SinDiffusion: Learning a Diffusion Model from a Single Natural Image","created":"2022-11-22","cited_by_count":42},{"id":"2306.01851","title":"Open-world Text-specified Object Counting","created":"2023-06-02","cited_by_count":41},{"id":"2311.12386","title":"Point, Segment and Count: A Generalized Framework for Object Counting","created":"2023-11-21","cited_by_count":39},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"2205.14212","title":"Exemplar Free Class Agnostic Counting","created":"2022-05-27","cited_by_count":32},{"id":"2302.03956","title":"Neural Congealing: Aligning Images to a Joint Semantic Atlas","created":"2023-02-08","cited_by_count":31},{"id":"2303.16201","title":"ASIC: Aligning Sparse in-the-wild Image Collections","created":"2023-03-28","cited_by_count":27},{"id":"2409.18686","title":"A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation","created":"2024-09-27","cited_by_count":21},{"id":"2203.16521","title":"CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs","created":"2022-03-30","cited_by_count":17},{"id":"2212.04965","title":"Seeing a Rose in Five Thousand Ways","created":"2022-12-09","cited_by_count":13},{"id":"2309.04820","title":"ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting","created":"2023-09-09","cited_by_count":13},{"id":"2407.11850","title":"SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images","created":"2024-07-16","cited_by_count":6},{"id":"2307.08727","title":"Learning to Count without Annotations","created":"2023-07-17","cited_by_count":5},{"id":"2401.05236","title":"Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects","created":"2024-01-10","cited_by_count":5},{"id":"2506.06462","title":"Splat and Replace: 3D Reconstruction with Repetitive Elements","created":"2025-06-06","cited_by_count":5},{"id":"2208.12278","title":"Learning Continuous Implicit Representation for Near-Periodic Patterns","created":"2022-08-25","cited_by_count":4},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4},{"id":"2603.21229","title":"Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species","created":"2026-03-22","cited_by_count":2},{"id":"2508.17636","title":"Few-Shot Pattern Detection via Template Matching and Regression","created":"2025-08-25","cited_by_count":1},{"id":"2510.22842","title":"FastJAM: a Fast Joint Alignment Model for Images","created":"2025-10-26","cited_by_count":1}],"next_cursor":null}