{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"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":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"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":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"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":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"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":"1812.08233","title":"Invariance, Causality and Robustness","created":"2018-12-19","cited_by_count":123},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1705.01359","title":"FOIL it! Find One mismatch between Image and Language caption","created":"2017-05-03","cited_by_count":95},{"id":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72},{"id":"1911.12580","title":"Stable Learning via Sample Reweighting","created":"2019-11-28","cited_by_count":70},{"id":"2205.00272","title":"Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning","created":"2022-04-30","cited_by_count":69},{"id":"2001.11713","title":"Stable Prediction with Model Misspecification and Agnostic Distribution Shift","created":"2020-01-31","cited_by_count":62},{"id":"2004.08814","title":"Graph-Structured Referring Expression Reasoning in The Wild","created":"2020-04-19","cited_by_count":58},{"id":"1711.06370","title":"Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries","created":"2017-11-17","cited_by_count":56},{"id":"2104.04386","title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding","created":"2021-04-09","cited_by_count":52},{"id":"1911.09042","title":"Learning Cross-modal Context Graph for Visual Grounding","created":"2019-11-20","cited_by_count":49},{"id":"2206.06619","title":"TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer","created":"2022-06-14","cited_by_count":42},{"id":"1810.09050","title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","created":"2018-10-22","cited_by_count":38},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35},{"id":"2109.07276","title":"Sequence Length is a Domain: Length-based Overfitting in Transformer Models","created":"2021-09-15","cited_by_count":35},{"id":"1911.03872","title":"Location Attention for Extrapolation to Longer Sequences","created":"2019-11-10","cited_by_count":33},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33},{"id":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29},{"id":"1904.09471","title":"Saliency-Guided Attention Network for Image-Sentence Matching","created":"2019-04-20","cited_by_count":21},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"2002.08510","title":"Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching","created":"2020-02-20","cited_by_count":15},{"id":"2106.04279","title":"Staircase Attention for Recurrent Processing of Sequences","created":"2021-06-08","cited_by_count":14},{"id":"2207.13325","title":"SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding","created":"2022-07-27","cited_by_count":12},{"id":"2210.12079","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","created":"2022-10-21","cited_by_count":8},{"id":"2203.15704","title":"Fine-Grained Visual Entailment","created":"2022-03-29","cited_by_count":4},{"id":"2201.09639","title":"Question Generation for Evaluating Cross-Dataset Shifts in Multi-modal Grounding","created":"2022-01-24","cited_by_count":3}],"next_cursor":null}