{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1711.11157","title":"A Semantic Loss Function for Deep Learning with Symbolic Knowledge","created":"2017-11-29","cited_by_count":270},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1711.04574","title":"Learning Explanatory Rules from Noisy Data","created":"2017-11-13","cited_by_count":211},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2012.13635","title":"Logic Tensor Networks","created":"2020-12-25","cited_by_count":199},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1705.11040","title":"End-to-End Differentiable Proving","created":"2017-05-31","cited_by_count":161},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"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":"1603.06318","title":"Harnessing Deep Neural Networks with Logic Rules","created":"2016-03-21","cited_by_count":135},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"1808.10437","title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","created":"2018-08-30","cited_by_count":127},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"2003.05541","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","created":"2020-03-11","cited_by_count":115},{"id":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"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":"2002.06100","title":"Analyzing Differentiable Fuzzy Logic Operators","created":"2020-02-14","cited_by_count":101},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2007.08970","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","created":"2020-07-17","cited_by_count":95},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95},{"id":"2004.08154","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","created":"2020-04-17","cited_by_count":93},{"id":"2012.06060","title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","created":"2020-12-11","cited_by_count":93},{"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":"1909.08453","title":"Pose-aware Multi-level Feature Network for Human Object Interaction Detection","created":"2019-09-18","cited_by_count":88},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84},{"id":"2010.16219","title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","created":"2020-10-30","cited_by_count":81},{"id":"2008.06662","title":"Compositional Generalization via Neural-Symbolic Stack Machines","created":"2020-08-15","cited_by_count":80},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"1811.00090","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","created":"2018-10-31","cited_by_count":78},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"1609.05566","title":"Label-Free Supervision of Neural Networks with Physics and Domain Knowledge","created":"2016-09-18","cited_by_count":74},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2007.08728","title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","created":"2020-07-17","cited_by_count":72},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55},{"id":"1807.07545","title":"Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks","created":"2018-07-19","cited_by_count":51},{"id":"2010.10001","title":"Contextual Heterogeneous Graph Network for Human-Object Interaction Detection","created":"2020-10-20","cited_by_count":50},{"id":"1909.01161","title":"Embedding Symbolic Knowledge into Deep Networks","created":"2019-09-03","cited_by_count":49},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44},{"id":"2010.05647","title":"Improving Compositional Generalization in Semantic Parsing","created":"2020-10-12","cited_by_count":42},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","cited_by_count":40},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"id":"2204.09290","title":"Human-Object Interaction Detection via Disentangled Transformer","created":"2022-04-20","cited_by_count":40},{"id":"1910.02481","title":"Learn to Explain Efficiently via Neural Logic Inductive Learning","created":"2019-10-06","cited_by_count":38},{"id":"2008.09514","title":"Neural Logic Reasoning","created":"2020-08-20","cited_by_count":38},{"id":"2112.00578","title":"Systematic Generalization with Edge Transformers","created":"2021-12-01","cited_by_count":38},{"id":"2204.00746","title":"What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions","created":"2022-04-02","cited_by_count":35},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34},{"id":"2010.01005","title":"DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection","created":"2020-10-02","cited_by_count":31},{"id":"1809.04640","title":"Jump to better conclusions: SCAN both left and right","created":"2018-09-12","cited_by_count":29},{"id":"2308.12595","title":"Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation","created":"2023-08-24","cited_by_count":29},{"id":"1704.08243","title":"C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset","created":"2017-04-26","cited_by_count":24},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24},{"id":"1909.04402","title":"Compositional Generalization in Image Captioning","created":"2019-09-10","cited_by_count":23},{"id":"2204.04911","title":"Category-Aware Transformer Network for Better Human-Object Interaction Detection","created":"2022-04-11","cited_by_count":22},{"id":"2203.10537","title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","created":"2022-03-20","cited_by_count":19},{"id":"2303.02260","title":"Learning to reason over visual objects","created":"2023-03-03","cited_by_count":19},{"id":"2309.13556","title":"LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning","created":"2023-09-24","cited_by_count":17},{"id":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15},{"id":"1608.07639","title":"Learning to generalize to new compositions in image understanding","created":"2016-08-27","cited_by_count":12},{"id":"2207.05293","title":"Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection","created":"2022-07-12","cited_by_count":12},{"id":"2207.02400","title":"Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection","created":"2022-07-06","cited_by_count":9}],"next_cursor":null}