{"list":"other","total":53,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"2005.07310","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","created":"2020-05-15","cited_by_count":90},{"id":"1903.00839","title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing","created":"2019-03-03","cited_by_count":88},{"id":"2106.01534","title":"Deconfounded Video Moment Retrieval with Causal Intervention","created":"2021-06-03","cited_by_count":84},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"id":"2007.09554","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","created":"2020-07-19","cited_by_count":79},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53},{"id":"2305.08685","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","created":"2023-05-15","cited_by_count":35},{"id":"2209.13959","title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding","created":"2022-09-28","cited_by_count":29},{"id":"2211.15516","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","created":"2022-11-28","cited_by_count":24},{"id":"2204.03647","title":"Adapting CLIP For Phrase Localization Without Further Training","created":"2022-04-07","cited_by_count":21},{"id":"2306.08498","title":"Extending CLIP's Image-Text Alignment to Referring Image Segmentation","created":"2023-06-14","cited_by_count":19},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17},{"id":"2204.09957","title":"Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension","created":"2022-04-21","cited_by_count":8}],"next_cursor":null}