{"total":64,"rows":[{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150,"area":null},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2402.02216","title":"Position: Graph Foundation Models are Already Here","created":"2024-02-03","cited_by_count":86,"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":"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":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"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":"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":"2305.02743","title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","created":"2023-05-04","cited_by_count":39,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","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":"2205.01316","title":"HL-Net: Heterophily Learning Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":22,"area":null},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2208.01834","title":"Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation","created":"2022-08-03","cited_by_count":20,"area":null},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2312.10439","title":"Simple Image-level Classification Improves Open-vocabulary Object Detection","created":"2023-12-16","cited_by_count":15,"area":null},{"id":"2310.07056","title":"TextPSG: Panoptic Scene Graph Generation from Textual Descriptions","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2312.03587","title":"Language-Informed Visual Concept Learning","created":"2023-12-06","cited_by_count":12,"area":null},{"id":"2504.13617","title":"Compile Scene Graphs with Reinforcement Learning","created":"2025-04-18","cited_by_count":11,"area":"lr"},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","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":"2307.03339","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","created":"2023-07-07","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":"2312.06116","title":"Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2404.02527","title":"Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2303.10863","title":"Decomposed Prototype Learning for Few-Shot Scene Graph Generation","created":"2023-03-20","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":"2312.07740","title":"HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2502.15370","title":"Weakly Supervised Video Scene Graph Generation via Natural Language Supervision","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2303.10944","title":"Location-Free Scene Graph Generation","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2509.21576","title":"Vision Language Models Cannot Plan, but Can They Formalize?","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2210.08675","title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","created":"2022-10-17","cited_by_count":2,"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":"2306.01937","title":"LIC-GAN: Language Information Conditioned Graph Generative GAN Model","created":"2023-06-02","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":"2410.19896","title":"FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysis","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2411.13572","title":"Public Health Advocacy Dataset: A Dataset of Tobacco Usage Videos from Social Media","created":"2024-11-12","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":"2604.20136","title":"IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory","created":"2026-04-22","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":"2403.16184","title":"Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement","created":"2024-03-24","cited_by_count":1,"area":"mllm"},{"id":"2507.04509","title":"MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization","created":"2025-07-06","cited_by_count":1,"area":"mllm"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2602.00637","title":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.09165","title":"All-in-One Conditioning for Text-to-Image Synthesis","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2209.02749","title":"Scalable Regularization of Scene Graph Generation Models using Symbolic Theories","created":"2022-09-06","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":"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":"2501.06546","title":"Natural Language Supervision for Low-light Image Enhancement","created":"2025-01-11","cited_by_count":0,"area":null},{"id":"2504.02417","title":"Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.05651","title":"Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2511.05935","title":"Interaction-Centric Knowledge Infusion and Transfer for Open-Vocabulary Scene Graph Generation","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2606.05916","title":"Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.15336","title":"SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}