{"list":"other","total":68,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1712.05055","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","created":"2017-12-14","cited_by_count":653},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"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":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1802.04865","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","created":"2018-02-13","cited_by_count":245},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"1711.07131","title":"CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise","created":"2017-11-20","cited_by_count":181},{"id":"2001.01536","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","created":"2020-01-06","cited_by_count":175},{"id":"1806.02612","title":"Dimensionality-Driven Learning with Noisy Labels","created":"2018-06-07","cited_by_count":173},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1703.02391","title":"Learning from Noisy Labels with Distillation","created":"2017-03-07","cited_by_count":161},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"1808.01097","title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","created":"2018-08-03","cited_by_count":126},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1706.00038","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","created":"2017-05-31","cited_by_count":78},{"id":"2009.00893","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","created":"2020-09-02","cited_by_count":75},{"id":"2103.04062","title":"Adaptive Multi-Teacher Multi-level Knowledge Distillation","created":"2021-03-06","cited_by_count":72},{"id":"2103.15042","title":"Distilling Virtual Examples for Long-tailed Recognition","created":"2021-03-28","cited_by_count":72},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67},{"id":"1910.05134","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","created":"2019-10-11","cited_by_count":66},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"id":"1512.06974","title":"Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels","created":"2015-12-22","cited_by_count":64},{"id":"2009.07526","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","created":"2020-09-16","cited_by_count":62},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"1812.02347","title":"Counterfactual Critic Multi-Agent Training for Scene Graph Generation","created":"2018-12-06","cited_by_count":53},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51},{"id":"1910.08381","title":"Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System","created":"2019-10-18","cited_by_count":43},{"id":"2101.09028","title":"A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric","created":"2021-01-22","cited_by_count":42},{"id":"2005.08230","title":"Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation","created":"2020-05-17","cited_by_count":31},{"id":"1909.03388","title":"L_DMI: An Information-theoretic Noise-robust Loss Function","created":"2019-09-08","cited_by_count":26},{"id":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25},{"id":"2104.10510","title":"Balanced Knowledge Distillation for Long-tailed Learning","created":"2021-04-21","cited_by_count":23},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22},{"id":"2205.01316","title":"HL-Net: Heterophily Learning Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":22},{"id":"2008.07832","title":"Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models","created":"2020-08-18","cited_by_count":19},{"id":"2207.08739","title":"Rethinking Data Augmentation for Robust Visual Question Answering","created":"2022-07-18","cited_by_count":18},{"id":"2104.10351","title":"Improving Weakly-supervised Object Localization via Causal Intervention","created":"2021-04-21","cited_by_count":14},{"id":"2010.03855","title":"Dense Relational Image Captioning via Multi-task Triple-Stream Networks","created":"2020-10-08","cited_by_count":11},{"id":"2203.05243","title":"A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach","created":"2022-03-10","cited_by_count":11},{"id":"2207.09625","title":"Explicit Image Caption Editing","created":"2022-07-20","cited_by_count":7}],"next_cursor":null}