{"list":"other","total":70,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"1704.04232","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","created":"2017-04-13","cited_by_count":207},{"id":"1511.08308","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","created":"2015-11-26","cited_by_count":201},{"id":"1703.08448","title":"Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach","created":"2017-03-24","cited_by_count":201},{"id":"1604.00825","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","created":"2016-04-04","cited_by_count":199},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1804.06962","title":"Adversarial Complementary Learning for Weakly Supervised Object Localization","created":"2018-04-19","cited_by_count":166},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"1812.04246","title":"Classification-Reconstruction Learning for Open-Set Recognition","created":"2018-12-11","cited_by_count":146},{"id":"1908.10028","title":"Attention-based Dropout Layer for Weakly Supervised Object Localization","created":"2019-08-27","cited_by_count":125},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"2001.07437","title":"Evaluating Weakly Supervised Object Localization Methods Right","created":"2020-01-21","cited_by_count":105},{"id":"2110.08484","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","created":"2021-10-16","cited_by_count":101},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"1909.00948","title":"HarDNet: A Low Memory Traffic Network","created":"2019-09-03","cited_by_count":76},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71},{"id":"2110.08398","title":"Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks","created":"2021-10-15","cited_by_count":68},{"id":"2102.01645","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","created":"2021-02-02","cited_by_count":57},{"id":"2008.05096","title":"Inter-Image Communication for Weakly Supervised Localization","created":"2020-08-12","cited_by_count":52},{"id":"2002.11359","title":"Rethinking the Route Towards Weakly Supervised Object Localization","created":"2020-02-26","cited_by_count":46},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46},{"id":"1705.01371","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","created":"2017-05-03","cited_by_count":40},{"id":"2110.12427","title":"Image-Based CLIP-Guided Essence Transfer","created":"2021-10-24","cited_by_count":39},{"id":"2007.09727","title":"Geometry Constrained Weakly Supervised Object Localization","created":"2020-07-19","cited_by_count":36},{"id":"1708.01676","title":"Query-guided Regression Network with Context Policy for Phrase Grounding","created":"2017-08-04","cited_by_count":34},{"id":"2108.00873","title":"Shallow Feature Matters for Weakly Supervised Object Localization","created":"2021-08-02","cited_by_count":34},{"id":"1811.11683","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","created":"2018-11-28","cited_by_count":32},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30},{"id":"1911.10688","title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","created":"2019-11-25","cited_by_count":25},{"id":"1711.04323","title":"High-Order Attention Models for Visual Question Answering","created":"2017-11-12","cited_by_count":22},{"id":"2112.00580","title":"Background Activation Suppression for Weakly Supervised Object Localization","created":"2021-12-01","cited_by_count":22},{"id":"1411.7399","title":"Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation","created":"2014-11-26","cited_by_count":16},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16},{"id":"1803.06506","title":"Learning Unsupervised Visual Grounding Through Semantic Self-Supervision","created":"2018-03-17","cited_by_count":10},{"id":"2111.14131","title":"Learning a Weight Map for Weakly-Supervised Localization","created":"2021-11-28","cited_by_count":1}],"next_cursor":null}