{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2011.03029","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","created":"2020-11-05","cited_by_count":276},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2203.08450","title":"The Devil Is in the Details: Window-based Attention for Image Compression","created":"2022-03-16","cited_by_count":147},{"id":"1809.10452","title":"Context-adaptive Entropy Model for End-to-end Optimized Image Compression","created":"2018-09-27","cited_by_count":143},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"1511.06281","title":"Density Modeling of Images using a Generalized Normalization Transformation","created":"2015-11-19","cited_by_count":127},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107},{"id":"1811.12817","title":"Practical Full Resolution Learned Lossless Image Compression","created":"2018-11-30","cited_by_count":94},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81},{"id":"2001.03569","title":"Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics","created":"2020-01-10","cited_by_count":80},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2107.08373","title":"Scalable Image Coding for Humans and Machines","created":"2021-07-18","cited_by_count":66},{"id":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45},{"id":"1906.01223","title":"Content Adaptive Optimization for Neural Image Compression","created":"2019-06-04","cited_by_count":40},{"id":"2306.05085","title":"TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception","created":"2023-06-08","cited_by_count":32},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"2112.09300","title":"Towards End-to-End Image Compression and Analysis with Transformers","created":"2021-12-17","cited_by_count":26},{"id":"2302.07408","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","created":"2023-02-15","cited_by_count":19},{"id":"2111.02249","title":"Learned Image Compression for Machine Perception","created":"2021-11-03","cited_by_count":14},{"id":"2111.11927","title":"Hierarchical Graph Networks for 3D Human Pose Estimation","created":"2021-11-23","cited_by_count":12},{"id":"2305.02586","title":"Semantically Structured Image Compression via Irregular Group-Based Decoupling","created":"2023-05-04","cited_by_count":12},{"id":"2112.08168","title":"Boosting Neural Image Compression for Machines Using Latent Space Masking","created":"2021-12-15","cited_by_count":11},{"id":"2211.00918","title":"Universal Deep Image Compression via Content-Adaptive Optimization with Adapters","created":"2022-11-02","cited_by_count":11},{"id":"2308.07733","title":"Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression","created":"2023-08-15","cited_by_count":10},{"id":"2307.09026","title":"ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting","created":"2023-07-18","cited_by_count":8},{"id":"2305.02578","title":"Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts","created":"2023-05-04","cited_by_count":7},{"id":"2404.01179","title":"BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning","created":"2024-04-01","cited_by_count":6}],"next_cursor":null}