{"total":73,"rows":[{"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":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"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":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"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":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13,"area":null},{"id":"2401.09769","title":"A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2405.19708","title":"Text Guided Image Editing with Automatic Concept Locating and Forgetting","created":"2024-05-30","cited_by_count":12,"area":"diffusion"},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2305.13777","title":"VisorGPT: Learning Visual Prior via Generative Pre-Training","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2402.13607","title":"CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models","created":"2024-02-21","cited_by_count":11,"area":"mllm"},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2309.02286","title":"Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes","created":"2023-09-05","cited_by_count":8,"area":null},{"id":"2409.14993","title":"Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification","created":"2024-09-23","cited_by_count":8,"area":"mllm"},{"id":"2210.09549","title":"Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation","created":"2022-10-18","cited_by_count":7,"area":"diffusion"},{"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":"2505.03173","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2403.14270","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","created":"2024-03-21","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2307.16206","title":"Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space","created":"2023-07-30","cited_by_count":5,"area":null},{"id":"2411.13929","title":"From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2507.17257","title":"Agent Identity Evals: Measuring Agentic Identity","created":"2025-07-23","cited_by_count":5,"area":"agents"},{"id":"2601.10168","title":"RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation","created":"2026-01-15","cited_by_count":5,"area":"rag"},{"id":"2210.14862","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","created":"2022-10-26","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":"2307.04838","title":"CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction","created":"2023-07-10","cited_by_count":4,"area":"mllm"},{"id":"2407.21580","title":"Voxel Scene Graph for Intracranial Hemorrhage","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2504.07867","title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2308.14378","title":"GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2403.04482","title":"On the Topology Awareness and Generalization Performance of Graph Neural Networks","created":"2024-03-07","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":"2504.17959","title":"CIVIL: Causal and Intuitive Visual Imitation Learning","created":"2025-04-24","cited_by_count":3,"area":"offlinerl"},{"id":"2506.16404","title":"Generating Directed Graphs with Dual Attention and Asymmetric Encoding","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2509.20941","title":"Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2404.09616","title":"A Review and Efficient Implementation of Scene Graph Generation Metrics","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2510.21744","title":"FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2601.08876","title":"The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2606.29395","title":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","created":"2026-06-28","cited_by_count":2,"area":"agents"},{"id":"2305.06141","title":"Active Semantic Localization with Graph Neural Embedding","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2406.12736","title":"Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2501.11653","title":"Dynamic Scene Understanding from Vision-Language Representations","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2503.06182","title":"FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2503.18988","title":"SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation","created":"2025-03-23","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":"2512.18386","title":"RecurGS: Interactive Scene Modeling via Discrete-State Recurrent Gaussian Fusion","created":"2025-12-20","cited_by_count":1,"area":null},{"id":"2601.11632","title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","created":"2026-01-14","cited_by_count":1,"area":"mllm"},{"id":"2603.27513","title":"Understanding Semantic Perturbations on In-Processing Generative Image Watermarks","created":"2026-03-29","cited_by_count":1,"area":"safety"},{"id":"2604.15951","title":"Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2211.16697","title":"SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2305.13258","title":"NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2308.04600","title":"Model of models -- Part 1","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2309.08179","title":"STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation","created":"2023-09-15","cited_by_count":0,"area":"distill"},{"id":"2403.09172","title":"SHAN: Object-Level Privacy Detection via Inference on Scene Heterogeneous Graph","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2408.14187","title":"Ensemble Predicate Decoding for Unbiased Scene Graph Generation","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2408.16621","title":"Towards Infusing Auxiliary Knowledge for Distracted Driver Detection","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2411.13287","title":"Unbiased Scene Graph Generation by Type-Aware Message Passing on Heterogeneous and Dual Graphs","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2412.00067","title":"Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs","created":"2024-11-25","cited_by_count":0,"area":"safety"},{"id":"2501.05066","title":"Improving Skeleton-based Action Recognition with Interactive Object Information","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2505.22633","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","created":"2025-05-28","cited_by_count":0,"area":"mllm"},{"id":"2512.00185","title":"Chunking Strategies for Multimodal AI Systems","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.07269","title":"A graph generation pipeline for critical infrastructures based on heuristics, images and depth data","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2604.07132","title":"CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.11004","title":"Panoptic Pairwise Distortion Graph","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.18184","title":"Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.18197","title":"RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.02724","title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.21580","title":"GraphVid: Interactive Graph-Controllable Video Generation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.14835","title":"OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2610.08800","title":"A Review Of Robotic World Models For Dynamic Environments Based On Factor And Scene Graphs","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}