{"list":"other","total":93,"rows":[{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"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":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"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":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"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":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"1611.07450","title":"Grad-CAM: Why did you say that?","created":"2016-11-22","cited_by_count":161},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125},{"id":"1801.06889","title":"Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers","created":"2018-01-21","cited_by_count":117},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"1807.09685","title":"Grounding Visual Explanations","created":"2018-07-25","cited_by_count":93},{"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":"1809.02805","title":"Faithful Multimodal Explanation for Visual Question Answering","created":"2018-09-08","cited_by_count":64},{"id":"1805.05492","title":"Did the Model Understand the Question?","created":"2018-05-14","cited_by_count":60},{"id":"1803.05268","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","created":"2018-03-14","cited_by_count":51},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2102.05228","title":"Towards Better Explanations of Class Activation Mapping","created":"2021-02-10","cited_by_count":47},{"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":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46},{"id":"1902.07864","title":"Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering","created":"2019-02-21","cited_by_count":38},{"id":"1806.09809","title":"Generating Counterfactual Explanations with Natural Language","created":"2018-06-26","cited_by_count":37},{"id":"1908.06306","title":"U-CAM: Visual Explanation using Uncertainty based Class Activation Maps","created":"2019-08-17","cited_by_count":36},{"id":"1605.09553","title":"Attention Correctness in Neural Image Captioning","created":"2016-05-31","cited_by_count":35},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34},{"id":"1908.10700","title":"Explainable Video Action Reasoning via Prior Knowledge and State Transitions","created":"2019-08-28","cited_by_count":33},{"id":"2009.13290","title":"The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances","created":"2020-09-28","cited_by_count":32},{"id":"1704.03162","title":"Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering","created":"2017-04-11","cited_by_count":31},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"1902.05715","title":"Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention","created":"2019-02-15","cited_by_count":26},{"id":"1612.07360","title":"Top-down Visual Saliency Guided by Captions","created":"2016-12-21","cited_by_count":22},{"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":"1608.08974","title":"Towards Transparent AI Systems: Interpreting Visual Question Answering Models","created":"2016-08-31","cited_by_count":19},{"id":"2201.01249","title":"ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions","created":"2022-01-04","cited_by_count":19},{"id":"1812.01263","title":"Multimodal Explanations by Predicting Counterfactuality in Videos","created":"2018-12-04","cited_by_count":18},{"id":"1906.03922","title":"Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis","created":"2019-06-10","cited_by_count":18},{"id":"1704.02787","title":"Deep Affordance-grounded Sensorimotor Object Recognition","created":"2017-04-10","cited_by_count":17},{"id":"1712.08697","title":"Interpretable Counting for Visual Question Answering","created":"2017-12-23","cited_by_count":17},{"id":"1904.03589","title":"Modularized Textual Grounding for Counterfactual Resilience","created":"2019-04-07","cited_by_count":17},{"id":"1806.08977","title":"Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation","created":"2018-06-23","cited_by_count":16},{"id":"2201.06309","title":"Group Gated Fusion on Attention-based Bidirectional Alignment for Multimodal Emotion Recognition","created":"2022-01-17","cited_by_count":16},{"id":"1703.04096","title":"Improving Interpretability of Deep Neural Networks with Semantic Information","created":"2017-03-12","cited_by_count":15},{"id":"1704.06972","title":"Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition","created":"2017-04-23","cited_by_count":15},{"id":"1812.01280","title":"Learning to Explain with Complemental Examples","created":"2018-12-04","cited_by_count":15},{"id":"2001.08730","title":"Robust Explanations for Visual Question Answering","created":"2020-01-23","cited_by_count":14},{"id":"2003.00431","title":"A Study on Multimodal and Interactive Explanations for Visual Question Answering","created":"2020-03-01","cited_by_count":14},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14},{"id":"1804.00298","title":"Differential Attention for Visual Question Answering","created":"2018-04-01","cited_by_count":12},{"id":"2006.15631","title":"Improving VQA and its Explanations \\\\ by Comparing Competing Explanations","created":"2020-06-28","cited_by_count":12},{"id":"2103.01616","title":"Interpretable Multi-Modal Hate Speech Detection","created":"2021-03-02","cited_by_count":10},{"id":"2001.01037","title":"Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models","created":"2020-01-04","cited_by_count":8},{"id":"2012.08174","title":"Towards open and expandable cognitive AI architectures for large-scale multi-agent human-robot collaborative learning","created":"2020-12-15","cited_by_count":8},{"id":"2202.01072","title":"Interpretability for Multimodal Emotion Recognition using Concept Activation Vectors","created":"2022-02-02","cited_by_count":8},{"id":"1710.09511","title":"InterpNET: Neural Introspection for Interpretable Deep Learning","created":"2017-10-26","cited_by_count":5},{"id":"1808.02861","title":"Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance","created":"2018-08-08","cited_by_count":5},{"id":"2001.09671","title":"Explaining with Counter Visual Attributes and Examples","created":"2020-01-27","cited_by_count":5},{"id":"2007.00900","title":"The Impact of Explanations on AI Competency Prediction in VQA","created":"2020-07-02","cited_by_count":5},{"id":"2009.13862","title":"Where is the Model Looking At?--Concentrate and Explain the Network Attention","created":"2020-09-29","cited_by_count":4},{"id":"1712.06228","title":"Visual Explanations from Hadamard Product in Multimodal Deep Networks","created":"2017-12-18","cited_by_count":3}],"next_cursor":null}