{"total":114,"rows":[{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455,"area":"mllm"},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104,"area":"mllm"},{"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":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82,"area":"diffusion"},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73,"area":"mllm"},{"id":"2409.10542","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","created":"2024-09-01","cited_by_count":69,"area":"mllm"},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2311.16479","title":"Mitigating Hallucination in Visual Language Models with Visual Supervision","created":"2023-11-27","cited_by_count":49,"area":"mllm"},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"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":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30,"area":null},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"area":null},{"id":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","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":"2403.10261","title":"Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection","created":"2024-03-15","cited_by_count":21,"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":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19,"area":"mllm"},{"id":"2503.06166","title":"Secure On-Device Video OOD Detection Without Backpropagation","created":"2025-03-08","cited_by_count":19,"area":null},{"id":"2510.18876","title":"Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs","created":"2025-10-21","cited_by_count":18,"area":"mllm"},{"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":"2407.11213","title":"OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models","created":"2024-07-15","cited_by_count":16,"area":"mllm"},{"id":"2310.07056","title":"TextPSG: Panoptic Scene Graph Generation from Textual Descriptions","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2412.06322","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","created":"2024-12-09","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":"2502.02589","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","created":"2025-02-04","cited_by_count":12,"area":null},{"id":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2403.14886","title":"DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2406.01029","title":"CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos","created":"2024-06-03","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":"2504.13617","title":"Compile Scene Graphs with Reinforcement Learning","created":"2025-04-18","cited_by_count":11,"area":"lr"},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2311.14580","title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","created":"2023-11-24","cited_by_count":10,"area":"mllm"},{"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":"2406.02038","title":"Leveraging Predicate and Triplet Learning for Scene Graph Generation","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2305.15562","title":"Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation","created":"2023-05-24","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":"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":"2506.08189","title":"Open World Scene Graph Generation using Vision Language Models","created":"2025-06-09","cited_by_count":7,"area":"mllm"},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2305.17768","title":"AIMS: All-Inclusive Multi-Level Segmentation","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2503.15019","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2505.21955","title":"Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs","created":"2025-05-28","cited_by_count":6,"area":"mllm"},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2512.22238","title":"Masking Teacher and Reinforcing Student for Distilling Vision-Language Models","created":"2025-12-23","cited_by_count":6,"area":"mllm"},{"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":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","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":"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":"2407.09216","title":"A Fair Ranking and New Model for Panoptic Scene Graph Generation","created":"2024-07-12","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":"2505.03581","title":"DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes","created":"2025-05-06","cited_by_count":4,"area":"lr"},{"id":"2505.17994","title":"Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.21813","title":"CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2509.09658","title":"Measuring Epistemic Humility in Multimodal Large Language Models","created":"2025-09-11","cited_by_count":4,"area":"mllm"},{"id":"2303.10944","title":"Location-Free Scene Graph Generation","created":"2023-03-20","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":"2407.09191","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":"2510.14349","title":"Vision-Centric Activation and Coordination for Multimodal Large Language Models","created":"2025-10-16","cited_by_count":3,"area":"mllm"},{"id":"2302.02651","title":"1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2308.01180","title":"Interpretable End-to-End Driving Model for Implicit Scene Understanding","created":"2023-08-02","cited_by_count":2,"area":"driving"},{"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":"2404.09616","title":"A Review and Efficient Implementation of Scene Graph Generation Metrics","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2407.03314","title":"BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs","created":"2024-07-03","cited_by_count":2,"area":"mllm"},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","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":"2512.01827","title":"CauSight: Learning to Supersense for Visual Causal Discovery","created":"2025-12-01","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":"2304.10505","title":"Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts","created":"2023-03-24","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":"2411.16132","title":"TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2505.17695","title":"SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data","created":"2025-05-23","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":"2506.21357","title":"CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2508.12263","title":"Region-Level Context-Aware Multimodal Understanding","created":"2025-08-17","cited_by_count":1,"area":"mllm"},{"id":"2509.01209","title":"Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2512.19221","title":"From Pixels to Predicates Structuring urban perception with scene graphs","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","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":"2605.13667","title":"SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models","created":"2026-05-13","cited_by_count":1,"area":"mllm"},{"id":"2606.06100","title":"HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2210.11253","title":"Image Semantic Relation Generation","created":"2022-10-19","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":"2310.00712","title":"Logical Bias Learning for Object Relation Prediction","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2405.03650","title":"Generated Contents Enrichment","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2405.16401","title":"Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2412.10436","title":"Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2501.19069","title":"Improving vision-language alignment with graph spiking hybrid Networks","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2506.19639","title":"HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2507.09200","title":"THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage","created":"2025-07-12","cited_by_count":0,"area":null}],"next_cursor":"100"}