{"list":"other","total":59,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"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":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256},{"id":"1702.01992","title":"Gated Multimodal Units for Information Fusion","created":"2017-02-07","cited_by_count":248},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","cited_by_count":168},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"2001.11190","title":"2018 Robotic Scene Segmentation Challenge","created":"2020-01-30","cited_by_count":124},{"id":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"2104.01394","title":"MMBERT: Multimodal BERT Pretraining for Improved Medical VQA","created":"2021-04-03","cited_by_count":68},{"id":"1902.00038","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","created":"2019-01-31","cited_by_count":62},{"id":"2206.11053","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","created":"2022-06-22","cited_by_count":59},{"id":"2105.08913","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","created":"2021-05-19","cited_by_count":54},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48},{"id":"2305.11692","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-05-19","cited_by_count":44},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43},{"id":"2011.13681","title":"Point and Ask: Incorporating Pointing into Visual Question Answering","created":"2020-11-27","cited_by_count":39},{"id":"2405.10948","title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","created":"2024-03-22","cited_by_count":39},{"id":"2107.10137","title":"Improved Text Classification via Contrastive Adversarial Training","created":"2021-07-21","cited_by_count":38},{"id":"2306.04652","title":"Language Adaptive Weight Generation for Multi-task Visual Grounding","created":"2023-06-06","cited_by_count":35},{"id":"2007.06198","title":"Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder","created":"2020-07-13","cited_by_count":34},{"id":"2203.14779","title":"A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition","created":"2022-03-28","cited_by_count":34},{"id":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33},{"id":"2304.01611","title":"Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder","created":"2023-04-04","cited_by_count":31},{"id":"2201.11957","title":"Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding","created":"2022-01-28","cited_by_count":29},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"2003.08760","title":"A Question-Centric Model for Visual Question Answering in Medical Imaging","created":"2020-03-02","cited_by_count":23},{"id":"2102.09528","title":"Image Compositing for Segmentation of Surgical Tools without Manual Annotations","created":"2021-02-18","cited_by_count":23},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22},{"id":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","cited_by_count":22},{"id":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20},{"id":"2308.14100","title":"Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay","created":"2023-08-27","cited_by_count":20},{"id":"2404.08677","title":"PMG : Personalized Multimodal Generation with Large Language Models","created":"2024-04-07","cited_by_count":19},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17},{"id":"2307.02452","title":"LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion","created":"2023-07-05","cited_by_count":15},{"id":"2307.12045","title":"Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-22","cited_by_count":15},{"id":"2405.10550","title":"LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion","created":"2024-05-17","cited_by_count":12},{"id":"2206.13296","title":"Consistency-preserving Visual Question Answering in Medical Imaging","created":"2022-06-27","cited_by_count":10},{"id":"2212.07651","title":"Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images","created":"2022-12-15","cited_by_count":10},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7},{"id":"2307.01067","title":"Localized Questions in Medical Visual Question Answering","created":"2023-07-03","cited_by_count":5},{"id":"2308.06889","title":"Robustness Stress Testing in Medical Image Classification","created":"2023-08-14","cited_by_count":5},{"id":"2309.03726","title":"Interpretable Visual Question Answering via Reasoning Supervision","created":"2023-09-07","cited_by_count":4}],"next_cursor":null}