{"total":100,"rows":[{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104,"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":"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":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50,"area":null},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45,"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":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44,"area":"mllm"},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2305.13812","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality","created":"2023-05-23","cited_by_count":32,"area":"mllm"},{"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":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31,"area":null},{"id":"2311.10988","title":"Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention","created":"2023-11-18","cited_by_count":29,"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":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25,"area":null},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24,"area":null},{"id":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23,"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":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","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":"2207.11441","title":"Meta Spatio-Temporal Debiasing for Video Scene Graph Generation","created":"2022-07-23","cited_by_count":20,"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":"2212.00443","title":"Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network","created":"2022-12-01","cited_by_count":17,"area":null},{"id":"2307.08699","title":"Pair then Relation: Pair-Net for Panoptic Scene Graph Generation","created":"2023-07-17","cited_by_count":17,"area":null},{"id":"2107.12604","title":"Image Scene Graph Generation (SGG) Benchmark","created":"2021-07-27","cited_by_count":15,"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":"2305.08522","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","created":"2023-05-15","cited_by_count":14,"area":null},{"id":"2306.03597","title":"Human-Object Interaction Prediction in Videos through Gaze Following","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2311.16492","title":"VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2401.09786","title":"Adaptive Self-training Framework for Fine-grained Scene Graph Generation","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2403.17709","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","created":"2024-03-26","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":"2309.13237","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","created":"2023-09-23","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":"2207.11401","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","created":"2022-07-23","cited_by_count":8,"area":"mllm"},{"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":"2406.02038","title":"Leveraging Predicate and Triplet Learning for Scene Graph Generation","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2311.12889","title":"Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge","created":"2023-11-21","cited_by_count":7,"area":null},{"id":"2506.08189","title":"Open World Scene Graph Generation using Vision Language Models","created":"2025-06-09","cited_by_count":7,"area":"mllm"},{"id":"2112.05727","title":"Neural Belief Propagation for Scene Graph Generation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2310.16073","title":"FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2106.08543","title":"Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2107.05448","title":"Scenes and Surroundings: Scene Graph Generation using Relation Transformer","created":"2021-07-12","cited_by_count":5,"area":null},{"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":"2412.11026","title":"SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation","created":"2024-12-15","cited_by_count":5,"area":"lr"},{"id":"2205.07017","title":"Importance Weighted Structure Learning for Scene Graph Generation","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2207.09927","title":"ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2210.06240","title":"Explore Contextual Information for 3D Scene Graph Generation","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2307.04838","title":"CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction","created":"2023-07-10","cited_by_count":4,"area":"mllm"},{"id":"2308.02339","title":"Improving Scene Graph Generation with Superpixel-Based Interaction Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2405.12648","title":"Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","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":"2201.11697","title":"Constrained Structure Learning for Scene Graph Generation","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2208.07109","title":"Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation","created":"2022-08-15","cited_by_count":3,"area":"moe"},{"id":"2301.07666","title":"DDS: Decoupled Dynamic Scene-Graph Generation Network","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2303.10944","title":"Location-Free Scene Graph Generation","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2304.00590","title":"SPAN: Learning Similarity between Scene Graphs and Images with Transformers","created":"2023-04-02","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":"2307.06527","title":"Free-Form Composition Networks for Egocentric Action Recognition","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2309.00215","title":"Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2309.03240","title":"RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2311.01192","title":"Semantic Scene Graph Generation Based on an Edge Dual Scene Graph and Message Passing Neural Network","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2505.20106","title":"From Data to Modeling: Fully Open-vocabulary Scene Graph Generation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2202.07271","title":"Hyper-relationship Learning Network for Scene Graph Generation","created":"2022-02-15","cited_by_count":1,"area":null},{"id":"2203.06215","title":"Can I see an Example? Active Learning the Long Tail of Attributes and Relations","created":"2022-03-11","cited_by_count":1,"area":null},{"id":"2204.11143","title":"Supplementing Missing Visions via Dialog for Scene Graph Generations","created":"2022-04-23","cited_by_count":1,"area":null},{"id":"2211.04773","title":"SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2302.06350","title":"VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2311.04834","title":"Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2401.12479","title":"TD^2-Net: Toward Denoising and Debiasing for Dynamic Scene Graph Generation","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2501.05687","title":"UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2506.01487","title":"FDSG: Forecasting Dynamic Scene Graphs","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.15583","title":"DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement","created":"2025-06-18","cited_by_count":1,"area":"mllm"},{"id":"2512.05524","title":"VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2605.13667","title":"SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models","created":"2026-05-13","cited_by_count":1,"area":"mllm"},{"id":"2108.11618","title":"Few-shot Visual Relationship Co-localization","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2211.16697","title":"SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2212.09329","title":"SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2302.01403","title":"Self-Supervised Relation Alignment for Scene Graph Generation","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2308.05274","title":"Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2308.12048","title":"Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation","created":"2023-08-23","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":"2403.11959","title":"IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Counting","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2406.19316","title":"Enhanced Data Transfer Cooperating with Artificial Triplets for Scene Graph Generation","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2410.15517","title":"SceneGraMMi: Scene Graph-boosted Hybrid-fusion for Multi-Modal Misinformation Veracity Prediction","created":"2024-10-20","cited_by_count":0,"area":null},{"id":"2503.14524","title":"Salient Temporal Encoding for Dynamic Scene Graph Generation","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2603.10538","title":"DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.17298","title":"Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.19631","title":"MOSA: Motion-Guided Semantic Alignment for Dynamic Scene Graph Generation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.22702","title":"Modular Diffusion Models for Structured Visual Recognition","created":"2026-06-21","cited_by_count":0,"area":"diffusion"},{"id":"2608.14835","title":"OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generation","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}