{"list":"other","total":58,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"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":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"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":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"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":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"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":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"id":"1904.01828","title":"Unsupervised Deep Tracking","created":"2019-04-03","cited_by_count":74},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49},{"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":"2011.14381","title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","created":"2020-11-29","cited_by_count":44},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21},{"id":"2308.09951","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","created":"2023-08-19","cited_by_count":20},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19},{"id":"2110.15949","title":"Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains","created":"2021-10-29","cited_by_count":18},{"id":"2204.01784","title":"Object Permanence Emerges in a Random Walk along Memory","created":"2022-04-04","cited_by_count":18},{"id":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","cited_by_count":16},{"id":"2404.05136","title":"Self-Supervised Multi-Object Tracking with Path Consistency","created":"2024-04-08","cited_by_count":16},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14},{"id":"2309.00942","title":"Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning","created":"2023-09-02","cited_by_count":8},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7},{"id":"2410.15728","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","created":"2024-10-21","cited_by_count":5},{"id":"2401.11110","title":"VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE","created":"2024-01-20","cited_by_count":2}],"next_cursor":null}