{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1906.02337","title":"MNIST-C: A Robustness Benchmark for Computer Vision","created":"2019-06-05","cited_by_count":138},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"1704.05712","title":"Universal Adversarial Perturbations Against Semantic Image Segmentation","created":"2017-04-19","cited_by_count":92},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57},{"id":"2005.05909","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","created":"2020-04-29","cited_by_count":45},{"id":"1907.01003","title":"Accurate, reliable and fast robustness evaluation","created":"2019-07-01","cited_by_count":43},{"id":"2101.09617","title":"A Comprehensive Evaluation Framework for Deep Model Robustness","created":"2021-01-24","cited_by_count":42},{"id":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25},{"id":"1801.09041","title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions","created":"2018-01-27","cited_by_count":22},{"id":"1611.05546","title":"Zero-Shot Visual Question Answering","created":"2016-11-17","cited_by_count":20},{"id":"1711.06232","title":"A Novel Framework for Robustness Analysis of Visual QA Models","created":"2017-11-16","cited_by_count":20},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15},{"id":"2103.02937","title":"Visual Question Answering: which investigated applications?","created":"2021-03-04","cited_by_count":11},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11},{"id":"1811.12772","title":"From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts","created":"2018-11-30","cited_by_count":5},{"id":"2105.07141","title":"Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention","created":"2021-05-15","cited_by_count":2}],"next_cursor":null}