{"total":78,"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":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114,"area":"mllm"},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","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":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2305.13812","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality","created":"2023-05-23","cited_by_count":32,"area":"mllm"},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"id":"2403.12736","title":"Towards Multimodal In-Context Learning for Vision & Language Models","created":"2024-03-19","cited_by_count":25,"area":"mllm"},{"id":"2212.04542","title":"VASR: Visual Analogies of Situation Recognition","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21,"area":"mllm"},{"id":"2310.18511","title":"3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition","created":"2023-10-27","cited_by_count":21,"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":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20,"area":null},{"id":"2406.19875","title":"InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows","created":"2024-06-28","cited_by_count":20,"area":"mllm"},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19,"area":null},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2401.03082","title":"UMIE: Unified Multimodal Information Extraction with Instruction Tuning","created":"2024-01-05","cited_by_count":17,"area":null},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16,"area":null},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15,"area":"diffusion"},{"id":"2111.10135","title":"Grounded Situation Recognition with Transformers","created":"2021-11-19","cited_by_count":14,"area":null},{"id":"2210.10828","title":"Grounded Video Situation Recognition","created":"2022-10-19","cited_by_count":13,"area":null},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13,"area":null},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2210.03102","title":"Ambiguous Images With Human Judgments for Robust Visual Event Classification","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","cited_by_count":12,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2306.08966","title":"Training Multimedia Event Extraction With Generated Images and Captions","created":"2023-06-15","cited_by_count":11,"area":null},{"id":"2306.08685","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","created":"2023-06-14","cited_by_count":10,"area":"mllm"},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2210.12079","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2211.01781","title":"Video Event Extraction via Tracking Visual States of Arguments","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2404.15785","title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","created":"2024-04-24","cited_by_count":7,"area":"mllm"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2307.00586","title":"ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2406.12420","title":"MMUTF: Multimodal Multimedia Event Argument Extraction with Unified Template Filling","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2510.13796","title":"The Mechanistic Emergence of Symbol Grounding in Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2310.16616","title":"Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2512.19537","title":"Event Extraction in Large Language Model","created":"2025-12-22","cited_by_count":5,"area":"mllm"},{"id":"2308.10562","title":"Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2310.15129","title":"Location-Aware Visual Question Generation with Lightweight Models","created":"2023-10-23","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":"2502.14893","title":"NOTA: Multimodal Music Notation Understanding for Visual Large Language Model","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2206.07207","title":"Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities","created":"2022-06-14","cited_by_count":3,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2410.02483","title":"Event-Customized Image Generation","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2509.12876","title":"Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2205.04402","title":"Detecting the Role of an Entity in Harmful Memes: Techniques and Their Limitations","created":"2022-05-09","cited_by_count":2,"area":null},{"id":"2211.07441","title":"Multi-VQG: Generating Engaging Questions for Multiple Images","created":"2022-11-14","cited_by_count":2,"area":null},{"id":"2404.04763","title":"GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2508.11350","title":"HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model","created":"2025-08-15","cited_by_count":2,"area":"lr"},{"id":"2508.16070","title":"Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants","created":"2025-08-22","cited_by_count":2,"area":"mllm"},{"id":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2402.19339","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2403.05101","title":"Rule-driven News Captioning","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2408.09511","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","created":"2024-08-18","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":"2604.01586","title":"SHOE: Semantic HOI Open-Vocabulary Evaluation Metric","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2109.06488","title":"Multilevel profiling of situation and dialogue-based deep networks for movie genre classification using movie trailers","created":"2021-09-14","cited_by_count":0,"area":null},{"id":"2301.03410","title":"In Defense of Structural Symbolic Representation for Video Event-Relation Prediction","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2507.14686","title":"From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition","created":"2025-07-19","cited_by_count":0,"area":"mllm"},{"id":"2508.04945","title":"Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.21816","title":"The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2602.13748","title":"RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2606.17950","title":"Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.26775","title":"Evaluation Pitfalls and Challenges in Multimedia Event Extraction","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.35955","title":"HEIR: Learning Human-Entity Interactions with Functional Roles","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06928","title":"Metonymic Circuits for Abstract Concept Grounding in Vision Transformers","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}