{"list":"other","total":142,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"id":"2004.02806","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","created":"2020-04-01","cited_by_count":397},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2006.10685","title":"Deep Learning Enabled Semantic Communication Systems","created":"2020-06-18","cited_by_count":292},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1811.03378","title":"Activation Functions: Comparison of trends in Practice and Research for Deep Learning","created":"2018-11-08","cited_by_count":130},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1305.6663","title":"Generalized Denoising Auto-Encoders as Generative Models","created":"2013-05-29","cited_by_count":113},{"id":"1603.08029","title":"Resnet in Resnet: Generalizing Residual Architectures","created":"2016-03-25","cited_by_count":110},{"id":"2005.08135","title":"VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change","created":"2020-05-17","cited_by_count":101},{"id":"2207.00427","title":"Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges","created":"2022-06-10","cited_by_count":95},{"id":"1910.13796","title":"Deep Learning vs. Traditional Computer Vision","created":"2019-10-30","cited_by_count":94},{"id":"2201.01389","title":"Semantic Communications: Principles and Challenges","created":"2021-12-30","cited_by_count":91},{"id":"2009.12836","title":"Normalization Techniques in Training DNNs: Methodology, Analysis and Application","created":"2020-09-27","cited_by_count":90},{"id":"2112.10255","title":"Task-Oriented Multi-User Semantic Communications","created":"2021-12-19","cited_by_count":75},{"id":"2007.11095","title":"A Lite Distributed Semantic Communication System for Internet of Things","created":"2020-07-21","cited_by_count":73},{"id":"2211.14343","title":"Less Data, More Knowledge: Building Next Generation Semantic Communication Networks","created":"2022-11-25","cited_by_count":62},{"id":"2309.08895","title":"CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications","created":"2023-09-16","cited_by_count":59},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58},{"id":"2206.00422","title":"Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing","created":"2022-06-01","cited_by_count":56},{"id":"2108.07357","title":"Task-Oriented Multi-User Semantic Communications for VQA Task","created":"2021-08-16","cited_by_count":51},{"id":"2203.02662","title":"A Survey on Metaverse: Fundamentals, Security, and Privacy","created":"2022-03-05","cited_by_count":51},{"id":"2110.00196","title":"What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence","created":"2021-10-01","cited_by_count":50},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44},{"id":"2211.08747","title":"Deep Joint Source-Channel Coding for Semantic Communications","created":"2022-11-16","cited_by_count":41},{"id":"2202.02559","title":"Digital Twin of Wireless Systems: Overview, Taxonomy, Challenges, and Opportunities","created":"2022-02-05","cited_by_count":40},{"id":"2309.01249","title":"Large AI Model Empowered Multimodal Semantic Communications","created":"2023-09-03","cited_by_count":38},{"id":"2305.06152","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","created":"2023-05-06","cited_by_count":37},{"id":"2208.04094","title":"Towards Semantic Communications: Deep Learning-Based Image Semantic Coding","created":"2022-08-08","cited_by_count":36},{"id":"2401.00124","title":"Generative AI-driven Semantic Communication Networks: Architecture, Technologies and Applications","created":"2023-12-30","cited_by_count":36},{"id":"2307.03492","title":"Large AI Model-Based Semantic Communications","created":"2023-07-07","cited_by_count":35},{"id":"2210.08901","title":"Contrastive Language-Image Pre-Training with Knowledge Graphs","created":"2022-10-17","cited_by_count":34},{"id":"2110.13522","title":"Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs","created":"2021-10-26","cited_by_count":28},{"id":"2301.11283","title":"Real-Time Digital Twins: Vision and Research Directions for 6G and Beyond","created":"2023-01-26","cited_by_count":26},{"id":"2102.12037","title":"Conditional Image Generation by Conditioning Variational Auto-Encoders","created":"2021-02-24","cited_by_count":25},{"id":"2307.07712","title":"Visual Analytics For Machine Learning: A Data Perspective Survey","created":"2023-07-15","cited_by_count":25},{"id":"2011.00905","title":"Advanced Semantics for Commonsense Knowledge Extraction","created":"2020-11-02","cited_by_count":24},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23},{"id":"2209.12274","title":"Personalized Saliency in Task-Oriented Semantic Communications: Image Transmission and Performance Analysis","created":"2022-09-25","cited_by_count":23},{"id":"2405.01221","title":"A Survey on Semantic Communication Networks: Architecture, Security, and Privacy","created":"2024-05-02","cited_by_count":22},{"id":"2310.14277","title":"A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application","created":"2023-10-22","cited_by_count":21},{"id":"1902.02771","title":"Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification","created":"2019-01-21","cited_by_count":19},{"id":"2407.18468","title":"Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints","created":"2024-07-26","cited_by_count":19},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19},{"id":"2309.11127","title":"Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation","created":"2023-09-20","cited_by_count":17},{"id":"2311.03783","title":"Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI","created":"2023-11-07","cited_by_count":17},{"id":"2209.11519","title":"Vector Quantized Semantic Communication System","created":"2022-09-23","cited_by_count":16},{"id":"2309.02387","title":"Semantic Communications Based on Adaptive Generative Models and Information Bottleneck","created":"2023-09-05","cited_by_count":16},{"id":"2311.08146","title":"Joint Source-Channel Coding for Channel-Adaptive Digital Semantic Communications","created":"2023-11-14","cited_by_count":15},{"id":"1712.01252","title":"An Equivalence of Fully Connected Layer and Convolutional Layer","created":"2017-12-04","cited_by_count":14},{"id":"2302.13721","title":"Wireless End-to-End Image Transmission System using Semantic Communications","created":"2023-02-27","cited_by_count":14},{"id":"2304.12502","title":"Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach","created":"2023-04-25","cited_by_count":14},{"id":"2306.15534","title":"SCAN: Semantic Communication with Adaptive Channel Feedback","created":"2023-06-27","cited_by_count":14},{"id":"2202.03705","title":"A Survey on Semantic Communications for Intelligent Wireless Networks","created":"2022-02-08","cited_by_count":13},{"id":"2211.12783","title":"Semantic-Aware Sensing Information Transmission for Metaverse: A Contest Theoretic Approach","created":"2022-11-23","cited_by_count":13},{"id":"2302.13560","title":"Task-oriented Explainable Semantic Communications","created":"2023-02-27","cited_by_count":13},{"id":"2303.11543","title":"DeepMA: End-to-end Deep Multiple Access for Wireless Image Transmission in Semantic Communication","created":"2023-03-21","cited_by_count":12},{"id":"2403.05783","title":"Large Generative Model Assisted 3D Semantic Communication","created":"2024-03-09","cited_by_count":12},{"id":"2407.00020","title":"Visual Language Model based Cross-modal Semantic Communication Systems","created":"2024-05-06","cited_by_count":12},{"id":"2210.04474","title":"Rethinking Wireless Communication Security in Semantic Internet of Things","created":"2022-10-10","cited_by_count":11},{"id":"2311.12443","title":"Knowledge Base Enabled Semantic Communication: A Generative Perspective","created":"2023-11-21","cited_by_count":11}],"next_cursor":"100"}