{"total":61,"rows":[{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158,"area":"distill"},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2105.09491","title":"Generalized Few-Shot Object Detection without Forgetting","created":"2021-05-20","cited_by_count":88,"area":null},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82,"area":"diffusion"},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"area":null},{"id":"2304.10417","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","created":"2023-04-20","cited_by_count":64,"area":null},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57,"area":null},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44,"area":null},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31,"area":null},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28,"area":null},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27,"area":null},{"id":"2201.06794","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2107.05080","title":"Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration","created":"2021-07-11","cited_by_count":21,"area":null},{"id":"2109.05346","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","created":"2021-09-11","cited_by_count":18,"area":null},{"id":"2308.09472","title":"Vision Relation Transformer for Unbiased Scene Graph Generation","created":"2023-08-18","cited_by_count":18,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2207.04602","title":"Adaptive Fine-Grained Predicates Learning for Scene Graph Generation","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2107.02713","title":"Predicate correlation learning for scene graph generation","created":"2021-07-06","cited_by_count":11,"area":null},{"id":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2503.13957","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2102.04760","title":"Improving Scene Graph Classification by Exploiting Knowledge from Texts","created":"2021-02-09","cited_by_count":10,"area":null},{"id":"2212.00017","title":"Knowledge-augmented Deep Learning and Its Applications: A Survey","created":"2022-11-30","cited_by_count":10,"area":null},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2104.11934","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","created":"2021-04-24","cited_by_count":9,"area":null},{"id":"2202.10201","title":"OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics","created":"2022-02-21","cited_by_count":9,"area":null},{"id":"2110.03562","title":"Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2211.06444","title":"Probabilistic Debiasing of Scene Graphs","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2310.01636","title":"Adaptive Visual Scene Understanding: Incremental Scene Graph Generation","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2104.12727","title":"2.5D Visual Relationship Detection","created":"2021-04-26","cited_by_count":7,"area":null},{"id":"2306.05689","title":"Single-Stage Visual Relationship Learning using Conditional Queries","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2503.13947","title":"Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2107.13279","title":"Pseudo-LiDAR Based Road Detection","created":"2021-07-28","cited_by_count":6,"area":null},{"id":"2208.04165","title":"Neural Message Passing for Visual Relationship Detection","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2412.09388","title":"All You Need in Knowledge Distillation Is a Tailored Coordinate System","created":"2024-12-12","cited_by_count":6,"area":"distill"},{"id":"2301.00351","title":"Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation","created":"2023-01-01","cited_by_count":5,"area":null},{"id":"2402.17213","title":"VCD: A Dataset for Visual Commonsense Discovery in Images","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2404.07788","title":"AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generation","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2112.07270","title":"Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2305.18668","title":"Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2510.04714","title":"Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2110.05731","title":"Topic Scene Graph Generation by Attention Distillation from Caption","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2111.10686","title":"Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection","created":"2021-11-20","cited_by_count":3,"area":null},{"id":"2207.03729","title":"GEMS: Scene Expansion using Generative Models of Graphs","created":"2022-07-08","cited_by_count":3,"area":null},{"id":"2406.06028","title":"ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2504.12606","title":"Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2107.07154","title":"What and When to Look?: Temporal Span Proposal Network for Video Relation Detection","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2204.02149","title":"Automatic Image Content Extraction: Operationalizing Machine Learning in Humanistic Photographic Studies of Large Visual Archives","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2208.00351","title":"Chinese grammatical error correction based on knowledge distillation","created":"2022-07-31","cited_by_count":1,"area":"distill"},{"id":"2309.08931","title":"A Novel Neural-symbolic System under Statistical Relational Learning","created":"2023-09-16","cited_by_count":1,"area":"lr"},{"id":"2103.00497","title":"Distilling Knowledge via Intermediate Classifiers","created":"2021-02-28","cited_by_count":0,"area":"distill"},{"id":"2206.09111","title":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2303.10766","title":"Multi-modal reward for visual relationships-based image captioning","created":"2023-03-19","cited_by_count":0,"area":null},{"id":"2308.12910","title":"SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2606.15328","title":"SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.21228","title":"T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}