{"total":104,"rows":[{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"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":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33,"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":"2309.12188","title":"SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs","created":"2023-09-21","cited_by_count":24,"area":null},{"id":"2307.05276","title":"Unbiased Scene Graph Generation via Two-stage Causal Modeling","created":"2023-07-11","cited_by_count":21,"area":null},{"id":"2402.11565","title":"Continual Learning on Graphs: Challenges, Solutions, and Opportunities","created":"2024-02-18","cited_by_count":21,"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":"2307.08699","title":"Pair then Relation: Pair-Net for Panoptic Scene Graph Generation","created":"2023-07-17","cited_by_count":17,"area":null},{"id":"2205.07229","title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","created":"2022-05-15","cited_by_count":16,"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":"2110.00273","title":"From SLAM to Situational Awareness: Challenges and Survey","created":"2021-10-01","cited_by_count":15,"area":null},{"id":"2403.12033","title":"HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2503.17862","title":"A Causal Adjustment Module for Debiasing Scene Graph Generation","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2207.09963","title":"Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry","created":"2022-07-20","cited_by_count":12,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2306.08789","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","created":"2023-06-15","cited_by_count":10,"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":"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":"2309.10170","title":"Generative modeling, design and analysis of spider silk protein sequences for enhanced mechanical properties","created":"2023-09-18","cited_by_count":9,"area":null},{"id":"2505.19510","title":"LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study","created":"2025-05-26","cited_by_count":9,"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":"2508.09185","title":"A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality","created":"2025-08-07","cited_by_count":8,"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":"2310.09118","title":"DSG: An End-to-End Document Structure Generator","created":"2023-10-13","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":"2402.12269","title":"Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss","created":"2024-02-19","cited_by_count":7,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2404.09231","title":"Tri-modal Confluence with Temporal Dynamics for Scene Graph Generation in Operating Rooms","created":"2024-04-14","cited_by_count":6,"area":null},{"id":"2109.10492","title":"Single Image Dehazing with An Independent Detail-Recovery Network","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2204.11291","title":"Large Scale Time-Series Representation Learning via Simultaneous Low and High Frequency Feature Bootstrapping","created":"2022-04-24","cited_by_count":5,"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":"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":"2406.03865","title":"Semantic Similarity Score for Measuring Visual Similarity at Semantic Level","created":"2024-06-06","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":"2604.25072","title":"Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2211.01796","title":"Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning","created":"2022-11-02","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":"2402.03840","title":"Belief Scene Graphs: Expanding Partial Scenes with Objects through Computation of Expectation","created":"2024-02-06","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":"2207.01072","title":"Dynamic Sub-Cluster-Aware Network for Few-Shot Skin Disease Classification","created":"2022-07-03","cited_by_count":3,"area":null},{"id":"2303.14643","title":"POAR: Towards Open Vocabulary Pedestrian Attribute Recognition","created":"2023-03-26","cited_by_count":3,"area":null},{"id":"2304.09789","title":"Automatic Interaction and Activity Recognition from Videos of Human Manual Demonstrations with Application to Anomaly Detection","created":"2023-04-19","cited_by_count":3,"area":null},{"id":"2305.19205","title":"AMatFormer: Efficient Feature Matching via Anchor Matching Transformer","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2312.13219","title":"Interactive Visual Task Learning for Robots","created":"2023-12-20","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":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2411.10509","title":"TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding","created":"2024-11-15","cited_by_count":3,"area":null},{"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":"2201.05121","title":"STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization","created":"2022-01-13","cited_by_count":2,"area":null},{"id":"2202.13321","title":"Bayesian Robust Tensor Ring Model for Incomplete Multiway Data","created":"2022-02-27","cited_by_count":2,"area":null},{"id":"2206.00222","title":"Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment","created":"2022-06-01","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":"2309.03542","title":"Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction","created":"2023-09-07","cited_by_count":2,"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":"2407.00609","title":"ESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2407.11393","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2505.15867","title":"SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.06165","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2512.01827","title":"CauSight: Learning to Supersense for Visual Causal Discovery","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2303.06635","title":"Schema Inference for Interpretable Image Classification","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2303.16459","title":"GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2311.11782","title":"Robust Tumor Segmentation with Hyperspectral Imaging and Graph Neural Networks","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2401.06256","title":"A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2401.12835","title":"SGTR+: End-to-end Scene Graph Generation with Transformer","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2401.14743","title":"Synthetic Multimodal Dataset for Empowering Safety and Well-being in Home Environments","created":"2024-01-26","cited_by_count":1,"area":null},{"id":"2402.14461","title":"S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2407.06000","title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","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":"2504.12817","title":"Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2505.23451","title":"A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation","created":"2025-05-29","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":"2512.02966","title":"Lumos: Let there be Language Model System Certification","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2603.06386","title":"REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.06088","title":"OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.06157","title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2201.11104","title":"Combining Optimal Path Search With Task-Dependent Learning in a Neural Network","created":"2022-01-26","cited_by_count":0,"area":null},{"id":"2305.17208","title":"A Categorical Representation Language and Computational System for Knowledge-Based Planning","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2402.17207","title":"Deployment Prior Injection for Run-time Calibratable Object Detection","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2403.03134","title":"Simplicity in Complexity : Explaining Visual Complexity using Deep Segmentation Models","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2404.01887","title":"3D scene generation from scene graphs and self-attention","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2404.13842","title":"On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2405.03650","title":"Generated Contents Enrichment","created":"2024-05-06","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":"2505.04058","title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2507.23543","title":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.11497","title":"Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.21928","title":"SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.27558","title":"Toward Accurate Long-Horizon Robotic Manipulation: Language-to-Action with Foundation Models via Scene Graphs","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2603.07704","title":"PARSE: Part-Aware Relational Spatial Modeling","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.25004","title":"Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.03697","title":"SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding","created":"2026-04-04","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}],"next_cursor":"100"}