{"total":334,"rows":[{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129,"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":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112,"area":null},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109,"area":null},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104,"area":null},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","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":"2402.19474","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":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83,"area":null},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82,"area":"diffusion"},{"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":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"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":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67,"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":"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":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58,"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":"2205.08536","title":"Disentangling Visual Embeddings for Attributes and Objects","created":"2022-05-17","cited_by_count":55,"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":"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":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"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":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2105.01017","title":"Learning Graph Embeddings for Open World Compositional Zero-Shot Learning","created":"2021-05-03","cited_by_count":49,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44,"area":null},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"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":"2207.11455","title":"UC-OWOD: Unknown-Classified Open World Object Detection","created":"2022-07-23","cited_by_count":40,"area":null},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39,"area":null},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2305.02743","title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","created":"2023-05-04","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"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":"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":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34,"area":"lr"},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34,"area":null},{"id":"2503.11240","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","created":"2025-03-14","cited_by_count":32,"area":"diffusion"},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31,"area":null},{"id":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31,"area":null},{"id":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","cited_by_count":31,"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":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30,"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":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28,"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":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27,"area":null},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"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":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","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":"2206.00415","title":"Learning Invariant Visual Representations for Compositional Zero-Shot Learning","created":"2022-06-01","cited_by_count":24,"area":null},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24,"area":null},{"id":"2209.07896","title":"3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs","created":"2022-09-16","cited_by_count":24,"area":null},{"id":"2305.14428","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"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":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23,"area":null},{"id":"2410.08876","title":"RoRA-VLM: Robust Retrieval-Augmented Vision Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2108.08584","title":"Exploiting Scene Graphs for Human-Object Interaction Detection","created":"2021-08-19","cited_by_count":22,"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":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2107.05080","title":"Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration","created":"2021-07-11","cited_by_count":21,"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":"2401.10224","title":"The Manga Whisperer: Automatically Generating Transcriptions for Comics","created":"2024-01-18","cited_by_count":21,"area":null},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","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":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2304.05387","title":"MOST: Multiple Object localization with Self-supervised Transformers for object discovery","created":"2023-04-11","cited_by_count":17,"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":"2308.04016","title":"Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning","created":"2023-08-08","cited_by_count":16,"area":null}],"next_cursor":"100"}