{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"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":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"1504.03641","title":"Learning to Compare Image Patches via Convolutional Neural Networks","created":"2015-04-14","cited_by_count":109},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"2111.09452","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","created":"2021-11-18","cited_by_count":71},{"id":"1803.04376","title":"Discriminability objective for training descriptive captions","created":"2018-03-12","cited_by_count":67},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"1812.02347","title":"Counterfactual Critic Multi-Agent Training for Scene Graph Generation","created":"2018-12-06","cited_by_count":53},{"id":"1906.07689","title":"Expressing Visual Relationships via Language","created":"2019-06-18","cited_by_count":49},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41},{"id":"1803.08314","title":"Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data","created":"2018-03-22","cited_by_count":37},{"id":"2007.06877","title":"Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets","created":"2020-07-14","cited_by_count":27},{"id":"2009.03949","title":"Towards Unique and Informative Captioning of Images","created":"2020-09-08","cited_by_count":25},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22},{"id":"2004.03708","title":"Context-Aware Group Captioning via Self-Attention and Contrastive Features","created":"2020-04-07","cited_by_count":17},{"id":"2108.09151","title":"Group-based Distinctive Image Captioning with Memory Attention","created":"2021-08-20","cited_by_count":13},{"id":"2303.06338","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","created":"2023-03-11","cited_by_count":12},{"id":"2102.01860","title":"L2C: Describing Visual Differences Needs Semantic Understanding of Individuals","created":"2021-02-03","cited_by_count":8},{"id":"2207.11118","title":"Rethinking the Reference-based Distinctive Image Captioning","created":"2022-07-22","cited_by_count":8},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4}],"next_cursor":null}