{"list":"other","total":73,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"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":"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":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147},{"id":"1912.12898","title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","created":"2019-12-30","cited_by_count":143},{"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":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"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":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","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":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95},{"id":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"1806.11538","title":"Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation","created":"2018-06-29","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":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"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":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"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":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"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":"2006.09623","title":"Learning Visual Commonsense for Robust Scene Graph Generation","created":"2020-06-17","cited_by_count":47},{"id":"1811.06410","title":"LinkNet: Relational Embedding for Scene Graph","created":"2018-11-15","cited_by_count":45},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44},{"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":"2005.08230","title":"Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation","created":"2020-05-17","cited_by_count":31},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31},{"id":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","cited_by_count":31},{"id":"2001.02359","title":"Weakly Supervised Visual Semantic Parsing","created":"2020-01-08","cited_by_count":28},{"id":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","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":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25},{"id":"2104.14207","title":"Segmentation-grounded Scene Graph Generation","created":"2021-04-29","cited_by_count":25},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23},{"id":"2307.05276","title":"Unbiased Scene Graph Generation via Two-stage Causal Modeling","created":"2023-07-11","cited_by_count":21},{"id":"2008.07832","title":"Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models","created":"2020-08-18","cited_by_count":19},{"id":"2004.00436","title":"Exploring Long Tail Visual Relationship Recognition with Large Vocabulary","created":"2020-03-25","cited_by_count":16},{"id":"2204.04836","title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","created":"2022-04-11","cited_by_count":16},{"id":"2007.05756","title":"Generative Compositional Augmentations for Scene Graph Prediction","created":"2020-07-11","cited_by_count":14},{"id":"2001.04735","title":"NODIS: Neural Ordinary Differential Scene Understanding","created":"2020-01-14","cited_by_count":12},{"id":"2112.05727","title":"Neural Belief Propagation for Scene Graph Generation","created":"2021-12-10","cited_by_count":6}],"next_cursor":null}