{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"1906.01815","title":"Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)","created":"2019-06-05","cited_by_count":174},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"1810.10191","title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","created":"2018-10-24","cited_by_count":154},{"id":"2008.10150","title":"Contrastive learning, multi-view redundancy, and linear models","created":"2020-08-24","cited_by_count":146},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134},{"id":"1904.06618","title":"UR-FUNNY: A Multimodal Language Dataset for Understanding Humor","created":"2019-04-14","cited_by_count":132},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116},{"id":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83},{"id":"1705.04977","title":"Detecting Statistical Interactions from Neural Network Weights","created":"2017-05-14","cited_by_count":80},{"id":"2010.06572","title":"Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!","created":"2020-10-13","cited_by_count":62},{"id":"2211.11256","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","created":"2022-11-21","cited_by_count":61},{"id":"2006.15955","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","created":"2020-06-29","cited_by_count":46},{"id":"2202.03390","title":"Geometric Multimodal Contrastive Representation Learning","created":"2022-02-07","cited_by_count":40},{"id":"2110.10949","title":"Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection","created":"2021-10-21","cited_by_count":37},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36},{"id":"2006.10966","title":"Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection","created":"2020-06-19","cited_by_count":32},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31},{"id":"1907.01011","title":"Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization","created":"2019-07-01","cited_by_count":30},{"id":"1611.04035","title":"Entropic Causal Inference","created":"2016-11-12","cited_by_count":27},{"id":"2303.15445","title":"IRFL: Image Recognition of Figurative Language","created":"2023-03-27","cited_by_count":23},{"id":"2112.12337","title":"Cooperative learning for multiview analysis","created":"2021-12-23","cited_by_count":19},{"id":"2012.02813","title":"Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment","created":"2020-12-04","cited_by_count":16},{"id":"1811.08615","title":"Unsupervised Multimodal Representation Learning across Medical Images and Reports","created":"2018-11-21","cited_by_count":15},{"id":"2107.12436","title":"Feature Synergy, Redundancy, and Independence in Global Model Explanations using SHAP Vector Decomposition","created":"2021-07-26","cited_by_count":9},{"id":"1701.08868","title":"Interaction Information for Causal Inference: The Case of Directed Triangle","created":"2017-01-30","cited_by_count":7},{"id":"2302.11838","title":"Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier","created":"2023-02-23","cited_by_count":7},{"id":"1701.05243","title":"How to Find a Joint Probability Distribution of Minimum Entropy (almost) given the Marginals","created":"2017-01-18","cited_by_count":6},{"id":"2203.05108","title":"A Tighter Approximation Guarantee for Greedy Minimum Entropy Coupling","created":"2022-03-10","cited_by_count":4},{"id":"1712.02449","title":"Quantifying how much sensory information in a neural code is relevant for behavior","created":"2017-12-06","cited_by_count":3}],"next_cursor":null}