{"list":"other","total":83,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"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":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2012.14261","title":"A Survey on Neural Network Interpretability","created":"2020-12-28","cited_by_count":291},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","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":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91},{"id":"1907.09701","title":"Benchmarking Attribution Methods with Relative Feature Importance","created":"2019-07-23","cited_by_count":89},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1807.06699","title":"Adaptive Neural Trees","created":"2018-07-17","cited_by_count":64},{"id":"2206.08358","title":"MixGen: A New Multi-Modal Data Augmentation","created":"2022-06-16","cited_by_count":61},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52},{"id":"2108.11761","title":"A Framework for Learning Ante-hoc Explainable Models via Concepts","created":"2021-08-25","cited_by_count":45},{"id":"1802.05451","title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","created":"2018-02-15","cited_by_count":44},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"1909.04696","title":"Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation","created":"2019-09-10","cited_by_count":36},{"id":"2006.15327","title":"Compositional Video Synthesis with Action Graphs","created":"2020-06-27","cited_by_count":34},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33},{"id":"1803.10362","title":"Referring Relationships","created":"2018-03-28","cited_by_count":29},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28},{"id":"2007.09592","title":"Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering","created":"2020-07-19","cited_by_count":26},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25},{"id":"2208.13628","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","created":"2022-08-29","cited_by_count":19},{"id":"1902.10200","title":"Differentiable Scene Graphs","created":"2019-02-26","cited_by_count":16},{"id":"2110.03485","title":"Cartoon Explanations of Image Classifiers","created":"2021-10-07","cited_by_count":15},{"id":"2009.14558","title":"Learning Object Detection from Captions via Textual Scene Attributes","created":"2020-09-30","cited_by_count":14},{"id":"1908.05254","title":"Optimizing for Interpretability in Deep Neural Networks with Tree Regularization","created":"2019-08-14","cited_by_count":13},{"id":"1906.06765","title":"Defending Against Adversarial Attacks Using Random Forests","created":"2019-06-16","cited_by_count":7},{"id":"2209.03415","title":"A Survey of Neural Trees","created":"2022-09-07","cited_by_count":7},{"id":"2211.12857","title":"Explaining Image Classifiers with Multiscale Directional Image Representation","created":"2022-11-22","cited_by_count":7},{"id":"2109.08191","title":"Simple Post-Training Robustness Using Test Time Augmentations and Random Forest","created":"2021-09-16","cited_by_count":4}],"next_cursor":null}