{"list":"other","total":56,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1904.01786","title":"Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning","created":"2019-04-03","cited_by_count":420},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1606.07356","title":"Analyzing the Behavior of Visual Question Answering Models","created":"2016-06-23","cited_by_count":119},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92},{"id":"1901.00850","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","created":"2019-01-03","cited_by_count":73},{"id":"2006.05121","title":"Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?","created":"2020-06-09","cited_by_count":69},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60},{"id":"2206.15436","title":"Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset","created":"2022-06-30","cited_by_count":59},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1903.03166","title":"CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog","created":"2019-03-07","cited_by_count":44},{"id":"1803.09331","title":"StarMap for Category-Agnostic Keypoint and Viewpoint Estimation","created":"2018-03-25","cited_by_count":42},{"id":"2101.12378","title":"NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation","created":"2021-01-29","cited_by_count":41},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34},{"id":"2012.02107","title":"Robust Instance Segmentation through Reasoning about Multi-Object Occlusion","created":"2020-12-03","cited_by_count":23},{"id":"2209.05624","title":"Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features","created":"2022-09-12","cited_by_count":23},{"id":"2103.14098","title":"Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles","created":"2021-03-25","cited_by_count":16},{"id":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","cited_by_count":16},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16},{"id":"2009.14115","title":"CoKe: Localized Contrastive Learning for Robust Keypoint Detection","created":"2020-09-29","cited_by_count":12},{"id":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8}],"next_cursor":null}