{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1905.06088","title":"Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning","created":"2019-05-15","cited_by_count":151},{"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":"2408.08872","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","created":"2024-08-16","cited_by_count":116},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1705.08841","title":"Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations","created":"2017-05-24","cited_by_count":100},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"2111.06077","title":"A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations","created":"2021-11-11","cited_by_count":99},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"1910.09772","title":"Weakly Supervised Disentanglement with Guarantees","created":"2019-10-22","cited_by_count":82},{"id":"2103.15619","title":"SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data","created":"2021-03-29","cited_by_count":78},{"id":"2112.15424","title":"A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges","created":"2021-11-12","cited_by_count":69},{"id":"2001.11797","title":"A comparison of Vector Symbolic Architectures","created":"2020-01-31","cited_by_count":64},{"id":"1811.09845","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","created":"2018-11-24","cited_by_count":61},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"1912.03915","title":"Learning Disentangled Representations via Mutual Information Estimation","created":"2019-12-09","cited_by_count":52},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51},{"id":"1804.10469","title":"Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders","created":"2018-04-27","cited_by_count":49},{"id":"2003.03461","title":"Semi-Supervised StyleGAN for Disentanglement Learning","created":"2020-03-06","cited_by_count":43},{"id":"1911.04679","title":"Object-Centric Task and Motion Planning in Dynamic Environments","created":"2019-11-12","cited_by_count":35},{"id":"2106.05268","title":"Vector Symbolic Architectures as a Computing Framework for Emerging Hardware","created":"2021-06-09","cited_by_count":35},{"id":"2102.10543","title":"Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View","created":"2021-02-21","cited_by_count":34},{"id":"2102.10303","title":"Towards Building A Group-based Unsupervised Representation Disentanglement Framework","created":"2021-02-20","cited_by_count":22},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20},{"id":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17},{"id":"1906.06034","title":"InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs","created":"2019-06-14","cited_by_count":16},{"id":"2002.11576","title":"NestedVAE: Isolating Common Factors via Weak Supervision","created":"2020-02-26","cited_by_count":13},{"id":"1910.10223","title":"Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis","created":"2019-10-22","cited_by_count":12},{"id":"2204.02283","title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","created":"2022-04-05","cited_by_count":11},{"id":"2311.04640","title":"Object-Centric Learning with Slot Mixture Module","created":"2023-11-08","cited_by_count":11},{"id":"2106.15550","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","created":"2021-06-29","cited_by_count":8},{"id":"2110.08343","title":"Hyperseed: Unsupervised Learning with Vector Symbolic Architectures","created":"2021-10-15","cited_by_count":8},{"id":"1806.00175","title":"Fast Exploration with Simplified Models and Approximately Optimistic Planning in Model Based Reinforcement Learning","created":"2018-06-01","cited_by_count":5},{"id":"2003.05171","title":"Vector symbolic architectures for context-free grammars","created":"2020-03-11","cited_by_count":3}],"next_cursor":null}