{"total":57,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"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":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2403.00742","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","created":"2024-03-01","cited_by_count":37,"area":null},{"id":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"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":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2405.09931","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","created":"2024-05-16","cited_by_count":17,"area":null},{"id":"2410.05210","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2308.01236","title":"Grounded Image Text Matching with Mismatched Relation Reasoning","created":"2023-08-02","cited_by_count":8,"area":null},{"id":"2310.15061","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2403.02875","title":"Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2306.16533","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2504.00942","title":"Experiential Semantic Information and Brain Alignment: Are Multimodal Models Better than Language Models?","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2508.15360","title":"An Empirical Study on How Video-LLMs Answer Video Questions","created":"2025-08-21","cited_by_count":4,"area":null},{"id":"2409.06579","title":"Quantifying and Enabling the Interpretability of CLIP-like Models","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2410.24219","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2211.04971","title":"Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2405.20846","title":"Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.06622","title":"ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2305.03517","title":"Few-shot Domain-Adaptive Visually-fused Event Detection from Text","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2309.11252","title":"The Scenario Refiner: Grounding subjects in images at the morphological level","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2401.16575","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2411.05023","title":"Multimodal Quantum Natural Language Processing: A Novel Framework for using Quantum Methods to Analyse Real Data","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2503.11103","title":"Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2605.06157","title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2409.01389","title":"CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2411.04242","title":"Multimodal Structure-Aware Quantum Data Processing","created":"2024-11-06","cited_by_count":0,"area":null},{"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":"2509.13474","title":"Semantic-Enhanced Cross-Modal Place Recognition for Robust Robot Localization","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2601.22929","title":"Semantic Leakage from Image Embeddings","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.08762","title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}