{"total":137,"rows":[{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183,"area":"mllm"},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67,"area":null},{"id":"2203.10202","title":"Relationformer: A Unified Framework for Image-to-Graph Generation","created":"2022-03-19","cited_by_count":67,"area":null},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65,"area":null},{"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,"area":null},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54,"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":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43,"area":"mllm"},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"area":null},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2303.07096","title":"Prototype-based Embedding Network for Scene Graph Generation","created":"2023-03-13","cited_by_count":37,"area":null},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35,"area":null},{"id":"2406.09410","title":"STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery","created":"2024-06-13","cited_by_count":31,"area":null},{"id":"2310.10404","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","created":"2023-10-16","cited_by_count":30,"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":"2204.02597","title":"Fine-Grained Predicates Learning for Scene Graph Generation","created":"2022-04-06","cited_by_count":27,"area":null},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24,"area":null},{"id":"2304.03495","title":"Devil's on the Edges: Selective Quad Attention for Scene Graph Generation","created":"2023-04-07","cited_by_count":23,"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":"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":"2309.15702","title":"SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction","created":"2023-09-27","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":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19,"area":null},{"id":"2303.15994","title":"HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation","created":"2023-03-28","cited_by_count":19,"area":null},{"id":"2310.16494","title":"Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction","created":"2023-10-25","cited_by_count":19,"area":null},{"id":"2204.04421","title":"Unbiased Directed Object Attention Graph for Object Navigation","created":"2022-04-09","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":"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":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16,"area":"mllm"},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15,"area":null},{"id":"2308.06712","title":"Compositional Feature Augmentation for Unbiased Scene Graph Generation","created":"2023-08-13","cited_by_count":15,"area":null},{"id":"2311.01755","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","created":"2023-11-03","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":"2208.03763","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","created":"2022-08-07","cited_by_count":14,"area":"distill"},{"id":"2503.17862","title":"A Causal Adjustment Module for Debiasing Scene Graph Generation","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","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":"2403.00729","title":"Can Transformers Capture Spatial Relations between Objects?","created":"2024-03-01","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":"2207.07913","title":"Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation","created":"2022-07-16","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":"2208.01909","title":"Rethinking the Evaluation of Unbiased Scene Graph Generation","created":"2022-08-03","cited_by_count":9,"area":null},{"id":"2308.03282","title":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation","created":"2023-08-07","cited_by_count":9,"area":null},{"id":"2507.17617","title":"Reusing Attention for One-stage Lane Topology Understanding","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","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":"2406.02038","title":"Leveraging Predicate and Triplet Learning for Scene Graph Generation","created":"2024-06-04","cited_by_count":8,"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":"2307.03339","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2310.00670","title":"A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2310.05867","title":"Domain-wise Invariant Learning for Panoptic Scene Graph Generation","created":"2023-10-09","cited_by_count":7,"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":"2312.04314","title":"GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives","created":"2023-12-07","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":"2112.05727","title":"Neural Belief Propagation for Scene Graph Generation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2401.14626","title":"Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2412.12788","title":"RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning","created":"2024-12-17","cited_by_count":6,"area":"rag"},{"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":"2309.05069","title":"Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels","created":"2023-09-10","cited_by_count":5,"area":"distill"},{"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":"2504.00844","title":"PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2112.13078","title":"Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks","created":"2021-12-24","cited_by_count":4,"area":null},{"id":"2205.07017","title":"Importance Weighted Structure Learning for Scene Graph Generation","created":"2022-05-14","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":"2301.00146","title":"Peer Learning for Unbiased Scene Graph Generation","created":"2022-12-31","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":"2308.02339","title":"Improving Scene Graph Generation with Superpixel-Based Interaction Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2401.01130","title":"Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models","created":"2024-01-02","cited_by_count":4,"area":"diffusion"},{"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":"2407.15396","title":"Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation","created":"2024-07-22","cited_by_count":4,"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":"2303.13209","title":"Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning","created":"2023-03-23","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":"2306.10122","title":"Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2308.04802","title":"Generalized Unbiased Scene Graph Generation","created":"2023-08-09","cited_by_count":3,"area":null},{"id":"2405.16116","title":"REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation","created":"2024-05-25","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":"2407.09191","title":"From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation","created":"2024-07-12","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":"2303.01080","title":"LANDMARK: Language-guided Representation Enhancement Framework for Scene Graph Generation","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2308.05286","title":"Informative Scene Graph Generation via Debiasing","created":"2023-08-10","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":"2309.03542","title":"Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction","created":"2023-09-07","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":"2401.14111","title":"Image Synthesis with Graph Conditioning: CLIP-Guided Diffusion Models for Scene Graphs","created":"2024-01-25","cited_by_count":2,"area":"diffusion"},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","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":"2203.09160","title":"Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation","created":"2022-03-17","cited_by_count":1,"area":null}],"next_cursor":"100"}