{"list":"other","total":65,"rows":[{"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":"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"1409.8403","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","created":"2014-09-30","cited_by_count":166},{"id":"1903.10132","title":"f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning","created":"2019-03-25","cited_by_count":164},{"id":"1605.04253","title":"An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild","created":"2016-05-13","cited_by_count":146},{"id":"1312.5650","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","created":"2013-12-19","cited_by_count":135},{"id":"1704.08345","title":"Semantic Autoencoder for Zero-Shot Learning","created":"2017-04-26","cited_by_count":133},{"id":"1603.00550","title":"Synthesized Classifiers for Zero-Shot Learning","created":"2016-03-02","cited_by_count":113},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"1712.01381","title":"A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts","created":"2017-12-04","cited_by_count":96},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1808.00136","title":"Multi-modal Cycle-consistent Generalized Zero-Shot Learning","created":"2018-08-01","cited_by_count":87},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"1904.04092","title":"Leveraging the Invariant Side of Generative Zero-Shot Learning","created":"2019-04-08","cited_by_count":83},{"id":"1512.04143","title":"Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks","created":"2015-12-14","cited_by_count":80},{"id":"2004.04725","title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","created":"2020-04-09","cited_by_count":80},{"id":"2103.04612","title":"Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection","created":"2021-03-08","cited_by_count":80},{"id":"2107.13807","title":"FREE: Feature Refinement for Generalized Zero-Shot Learning","created":"2021-07-29","cited_by_count":67},{"id":"1709.00663","title":"A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders","created":"2017-09-03","cited_by_count":64},{"id":"1908.05832","title":"Transferable Contrastive Network for Generalized Zero-Shot Learning","created":"2019-08-16","cited_by_count":64},{"id":"2101.07978","title":"Semantics Disentangling for Generalized Zero-Shot Learning","created":"2021-01-20","cited_by_count":56},{"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":"1612.07600","title":"Re-evaluating Automatic Metrics for Image Captioning","created":"2016-12-22","cited_by_count":45},{"id":"1611.06949","title":"Dense Captioning with Joint Inference and Visual Context","created":"2016-11-21","cited_by_count":40},{"id":"1503.00949","title":"Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning","created":"2015-03-03","cited_by_count":39},{"id":"1708.06975","title":"Generating Visual Representations for Zero-Shot Classification","created":"2017-08-23","cited_by_count":37},{"id":"1511.05284","title":"Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data","created":"2015-11-17","cited_by_count":36},{"id":"1407.5035","title":"LSDA: Large Scale Detection Through Adaptation","created":"2014-07-18","cited_by_count":32},{"id":"1805.06157","title":"Zero-Shot Object Detection by Hybrid Region Embedding","created":"2018-05-16","cited_by_count":32},{"id":"2010.04502","title":"Background Learnable Cascade for Zero-Shot Object Detection","created":"2020-10-09","cited_by_count":31},{"id":"1606.07770","title":"Captioning Images with Diverse Objects","created":"2016-06-24","cited_by_count":27},{"id":"2009.03949","title":"Towards Unique and Informative Captioning of Images","created":"2020-09-08","cited_by_count":25},{"id":"1811.10016","title":"Dissimilarity Coefficient based Weakly Supervised Object Detection","created":"2018-11-25","cited_by_count":23},{"id":"1708.05271","title":"Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects","created":"2017-08-17","cited_by_count":20},{"id":"1804.03803","title":"Decoupled Novel Object Captioner","created":"2018-04-11","cited_by_count":15},{"id":"1811.08982","title":"Polarity Loss for Zero-shot Object Detection","created":"2018-11-22","cited_by_count":14},{"id":"1705.01734","title":"Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning","created":"2017-05-04","cited_by_count":12},{"id":"1509.07225","title":"Automatic Concept Discovery from Parallel Text and Visual Corpora","created":"2015-09-24","cited_by_count":10},{"id":"1707.07102","title":"OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts","created":"2017-07-22","cited_by_count":8},{"id":"1909.02489","title":"Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation","created":"2019-09-05","cited_by_count":7},{"id":"1412.1135","title":"Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning","created":"2014-12-02","cited_by_count":6},{"id":"1712.09300","title":"Zero-Shot Learning via Latent Space Encoding","created":"2017-12-26","cited_by_count":6},{"id":"1908.00047","title":"Image Captioning with Unseen Objects","created":"2019-07-31","cited_by_count":6},{"id":"1904.09544","title":"3G structure for image caption generation","created":"2019-04-21","cited_by_count":2}],"next_cursor":null}