{"total":19,"rows":[{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35,"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":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28,"area":null},{"id":"2205.01316","title":"HL-Net: Heterophily Learning Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":22,"area":null},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21,"area":null},{"id":"2112.00967","title":"Relational Graph Learning for Grounded Video Description Generation","created":"2021-12-02","cited_by_count":12,"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":"2104.05166","title":"Object-Centric Representation Learning for Video Question Answering","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2104.12727","title":"2.5D Visual Relationship Detection","created":"2021-04-26","cited_by_count":7,"area":null},{"id":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","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":"2208.11122","title":"Distance-Aware Occlusion Detection with Focused Attention","created":"2022-08-23","cited_by_count":6,"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":"2409.00909","title":"ViRED: Prediction of Visual Relations in Engineering Drawings","created":"2024-09-02","cited_by_count":1,"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":"2311.16261","title":"RelVAE: Generative Pretraining for few-shot Visual Relationship Detection","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2410.22626","title":"Symbolic Graph Inference for Compound Scene Understanding","created":"2024-10-30","cited_by_count":0,"area":null}],"next_cursor":null}