{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"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":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"1908.10028","title":"Attention-based Dropout Layer for Weakly Supervised Object Localization","created":"2019-08-27","cited_by_count":125},{"id":"1704.03470","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","created":"2017-04-11","cited_by_count":119},{"id":"1703.05605","title":"Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval","created":"2017-03-16","cited_by_count":68},{"id":"1911.12529","title":"One-Shot Object Detection with Co-Attention and Co-Excitation","created":"2019-11-28","cited_by_count":67},{"id":"1301.6705","title":"Probabilistic Latent Semantic Analysis","created":"2013-01-23","cited_by_count":63},{"id":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"id":"1911.09042","title":"Learning Cross-modal Context Graph for Visual Grounding","created":"2019-11-20","cited_by_count":49},{"id":"1803.06049","title":"Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts","created":"2018-03-16","cited_by_count":48},{"id":"2011.10039","title":"Creative Sketch Generation","created":"2020-11-19","cited_by_count":44},{"id":"1803.02284","title":"Zero-Shot Sketch-Image Hashing","created":"2018-03-06","cited_by_count":43},{"id":"2007.02190","title":"B\\'ezierSketch: A generative model for scalable vector sketches","created":"2020-07-04","cited_by_count":43},{"id":"1401.0166","title":"Medical Image Fusion: A survey of the state of the art","created":"2013-12-31","cited_by_count":39},{"id":"1904.03797","title":"FoveaBox: Beyond Anchor-based Object Detector","created":"2019-04-08","cited_by_count":37},{"id":"1804.01401","title":"SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval","created":"2018-04-04","cited_by_count":35},{"id":"1912.11258","title":"Multi-Graph Transformer for Free-Hand Sketch Recognition","created":"2019-12-24","cited_by_count":35},{"id":"2203.14817","title":"Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval","created":"2022-03-28","cited_by_count":27},{"id":"1511.05756","title":"Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction","created":"2015-11-18","cited_by_count":26},{"id":"2008.06551","title":"Sketch-Guided Object Localization in Natural Images","created":"2020-08-14","cited_by_count":21},{"id":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","cited_by_count":20},{"id":"1603.07415","title":"Attentive Contexts for Object Detection","created":"2016-03-24","cited_by_count":17},{"id":"1808.02312","title":"Universal Perceptual Grouping","created":"2018-08-07","cited_by_count":14},{"id":"1811.08982","title":"Polarity Loss for Zero-shot Object Detection","created":"2018-11-22","cited_by_count":14},{"id":"1904.09320","title":"Context-Aware Zero-Shot Recognition","created":"2019-04-19","cited_by_count":12},{"id":"1802.00209","title":"Dual Recurrent Attention Units for Visual Question Answering","created":"2018-02-01","cited_by_count":5},{"id":"1809.07069","title":"Faster Training of Mask R-CNN by Focusing on Instance Boundaries","created":"2018-09-19","cited_by_count":5},{"id":"1909.12456","title":"ASSD: Attentive Single Shot Multibox Detector","created":"2019-09-27","cited_by_count":5},{"id":"1602.04364","title":"Look, Listen and Learn - A Multimodal LSTM for Speaker Identification","created":"2016-02-13","cited_by_count":4}],"next_cursor":null}