{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"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":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"1608.00853","title":"A study of the effect of JPG compression on adversarial images","created":"2016-08-02","cited_by_count":197},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"1811.02248","title":"SparseFool: a few pixels make a big difference","created":"2018-11-06","cited_by_count":94},{"id":"1911.10891","title":"ColorFool: Semantic Adversarial Colorization","created":"2019-11-25","cited_by_count":89},{"id":"1904.06347","title":"Unrestricted Adversarial Examples via Semantic Manipulation","created":"2019-04-12","cited_by_count":84},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84},{"id":"1809.02805","title":"Faithful Multimodal Explanation for Visual Question Answering","created":"2018-09-08","cited_by_count":64},{"id":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60},{"id":"1802.09653","title":"On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples","created":"2018-02-27","cited_by_count":58},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2010.07526","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","created":"2020-10-15","cited_by_count":46},{"id":"2206.11695","title":"NTIRE 2022 Challenge on Perceptual Image Quality Assessment","created":"2022-06-23","cited_by_count":41},{"id":"2103.08545","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","created":"2021-03-15","cited_by_count":34},{"id":"2004.03744","title":"e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations","created":"2020-04-07","cited_by_count":31},{"id":"2103.10480","title":"Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons","created":"2021-03-18","cited_by_count":29},{"id":"1905.04016","title":"Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables","created":"2019-05-10","cited_by_count":26},{"id":"2206.12714","title":"Defending Multimodal Fusion Models against Single-Source Adversaries","created":"2022-06-25","cited_by_count":20},{"id":"2107.01396","title":"Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity","created":"2021-07-03","cited_by_count":18},{"id":"2306.07591","title":"I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models","created":"2023-06-13","cited_by_count":17},{"id":"1906.04606","title":"Mimic and Fool: A Task Agnostic Adversarial Attack","created":"2019-06-11","cited_by_count":11},{"id":"1910.12227","title":"EdgeFool: An Adversarial Image Enhancement Filter","created":"2019-10-27","cited_by_count":10},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10},{"id":"2011.12902","title":"Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption","created":"2020-11-25","cited_by_count":8},{"id":"2008.06069","title":"Semantically Adversarial Learnable Filters","created":"2020-08-13","cited_by_count":5},{"id":"2103.00250","title":"Effective Universal Unrestricted Adversarial Attacks using a MOE Approach","created":"2021-02-27","cited_by_count":4}],"next_cursor":null}