{"total":164,"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":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137,"area":null},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71,"area":null},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69,"area":"mllm"},{"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":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"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":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57,"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":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54,"area":null},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51,"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":"2303.14408","title":"VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud","created":"2023-03-25","cited_by_count":43,"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":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"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":"2112.10941","title":"Structured Semantic Transfer for Multi-Label Recognition with Partial Labels","created":"2021-12-21","cited_by_count":41,"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":"2203.09138","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35,"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":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29,"area":null},{"id":"2203.02172","title":"Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels","created":"2022-03-04","cited_by_count":29,"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":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25,"area":null},{"id":"2104.14207","title":"Segmentation-grounded Scene Graph Generation","created":"2021-04-29","cited_by_count":25,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","cited_by_count":25,"area":null},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"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":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","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":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21,"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":"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":"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":"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":"2109.05346","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","created":"2021-09-11","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":"2112.08587","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","created":"2021-12-16","cited_by_count":16,"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":"2403.12033","title":"HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation","created":"2024-03-18","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":"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":"2108.08600","title":"Semantic Compositional Learning for Low-shot Scene Graph Generation","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2107.02713","title":"Predicate correlation learning for scene graph generation","created":"2021-07-06","cited_by_count":11,"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":"2503.13957","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","created":"2025-03-18","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":"2102.04760","title":"Improving Scene Graph Classification by Exploiting Knowledge from Texts","created":"2021-02-09","cited_by_count":10,"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":"2309.13237","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","created":"2023-09-23","cited_by_count":10,"area":null},{"id":"2309.17205","title":"Towards Complex-query Referring Image Segmentation: A Novel Benchmark","created":"2023-09-29","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":"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":"2104.11934","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","created":"2021-04-24","cited_by_count":9,"area":null},{"id":"2207.02400","title":"Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection","created":"2022-07-06","cited_by_count":9,"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":"2202.10824","title":"One-shot Scene Graph Generation","created":"2022-02-22","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":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2206.11653","title":"Learning To Generate Scene Graph from Head to Tail","created":"2022-06-23","cited_by_count":7,"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":"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":"2112.05727","title":"Neural Belief Propagation for Scene Graph Generation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2310.16073","title":"FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing","created":"2023-10-24","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":"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":"2411.13059","title":"Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation","created":"2024-11-20","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":"2106.08543","title":"Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions","created":"2021-06-16","cited_by_count":5,"area":null},{"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":"2303.05342","title":"Knowledge-augmented Few-shot Visual Relation Detection","created":"2023-03-09","cited_by_count":5,"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":"2508.06546","title":"Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2205.07017","title":"Importance Weighted Structure Learning for Scene Graph Generation","created":"2022-05-14","cited_by_count":4,"area":null}],"next_cursor":"100"}