{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"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":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"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":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"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":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","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":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"1803.04376","title":"Discriminability objective for training descriptive captions","created":"2018-03-12","cited_by_count":67},{"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":"1903.02827","title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up","created":"2019-03-07","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":"2002.04264","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","created":"2020-02-11","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":"1707.09423","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","created":"2017-07-28","cited_by_count":61},{"id":"1909.04412","title":"Cross-X Learning for Fine-Grained Visual Categorization","created":"2019-09-10","cited_by_count":61},{"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":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"2104.00885","title":"Adaptive Class Suppression Loss for Long-Tail Object Detection","created":"2021-04-02","cited_by_count":55},{"id":"2108.07507","title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","created":"2021-08-17","cited_by_count":51},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"1807.09915","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","created":"2018-07-26","cited_by_count":47},{"id":"2003.05235","title":"Channel Interaction Networks for Fine-Grained Image Categorization","created":"2020-03-11","cited_by_count":47},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"1807.04979","title":"Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition","created":"2018-07-13","cited_by_count":41},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35},{"id":"2005.06653","title":"Structured Query-Based Image Retrieval Using Scene Graphs","created":"2020-05-13","cited_by_count":33},{"id":"1703.03054","title":"Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection","created":"2017-03-08","cited_by_count":28},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28},{"id":"2204.02597","title":"Fine-Grained Predicates Learning for Scene Graph Generation","created":"2022-04-06","cited_by_count":27},{"id":"1905.01595","title":"On Exploring Undetermined Relationships for Visual Relationship Detection","created":"2019-05-05","cited_by_count":26},{"id":"2104.14207","title":"Segmentation-grounded Scene Graph Generation","created":"2021-04-29","cited_by_count":25},{"id":"2201.06794","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","created":"2022-01-18","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":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21},{"id":"2109.05346","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","created":"2021-09-11","cited_by_count":18},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15},{"id":"2102.09875","title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition","created":"2021-02-19","cited_by_count":11},{"id":"2107.02713","title":"Predicate correlation learning for scene graph generation","created":"2021-07-06","cited_by_count":11},{"id":"2203.09160","title":"Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation","created":"2022-03-17","cited_by_count":1}],"next_cursor":null}