{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"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":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"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":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"1503.00848","title":"Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation","created":"2015-03-03","cited_by_count":91},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"2211.04604","title":"StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects","created":"2022-11-08","cited_by_count":50},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49},{"id":"2405.13800","title":"Dense Connector for MLLMs","created":"2024-05-22","cited_by_count":49},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45},{"id":"1511.06406","title":"Denoising Criterion for Variational Auto-Encoding Framework","created":"2015-11-19","cited_by_count":43},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37},{"id":"2009.06138","title":"SCOUTER: Slot Attention-based Classifier for Explainable Image Recognition","created":"2020-09-14","cited_by_count":29},{"id":"2410.11829","title":"MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding","created":"2024-10-15","cited_by_count":23},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19},{"id":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","cited_by_count":14},{"id":"2501.15878","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","created":"2025-01-27","cited_by_count":13},{"id":"2401.00463","title":"Analyzing Local Representations of Self-supervised Vision Transformers","created":"2023-12-31","cited_by_count":8},{"id":"2411.01801","title":"Bootstrapping Top-down Information for Self-modulating Slot Attention","created":"2024-11-04","cited_by_count":6},{"id":"2402.03326","title":"Slot Structured World Models","created":"2024-01-08","cited_by_count":5},{"id":"2210.13053","title":"Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers","created":"2022-10-24","cited_by_count":4},{"id":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4},{"id":"2404.19654","title":"Masked Multi-Query Slot Attention for Unsupervised Object Discovery","created":"2024-04-30","cited_by_count":3}],"next_cursor":null}