{"total":206,"rows":[{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315,"area":null},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2305.16311","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","created":"2023-05-25","cited_by_count":231,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2104.05893","title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2303.17569","title":"Iterative Prompt Learning for Unsupervised Backlit Image Enhancement","created":"2023-03-30","cited_by_count":107,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97,"area":null},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2211.17256","title":"CLIPascene: Scene Sketching with Different Types and Levels of Abstraction","created":"2022-11-30","cited_by_count":64,"area":null},{"id":"2205.00303","title":"Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs","created":"2022-04-30","cited_by_count":59,"area":null},{"id":"2202.05822","title":"CLIPasso: Semantically-Aware Object Sketching","created":"2022-02-11","cited_by_count":57,"area":null},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"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":"2303.09429","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","created":"2023-03-16","cited_by_count":46,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2205.11631","title":"Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer","created":"2022-05-23","cited_by_count":45,"area":null},{"id":"2309.16649","title":"FLIP: Cross-domain Face Anti-spoofing with Language Guidance","created":"2023-09-28","cited_by_count":45,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2403.14333","title":"CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing","created":"2024-03-21","cited_by_count":39,"area":null},{"id":"2412.17007","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","created":"2024-12-22","cited_by_count":38,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31,"area":null},{"id":"2307.01981","title":"A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis","created":"2023-07-05","cited_by_count":31,"area":null},{"id":"2410.02811","title":"SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs","created":"2024-09-22","cited_by_count":31,"area":null},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29,"area":null},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28,"area":null},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2205.11578","title":"BolT: Fused Window Transformers for fMRI Time Series Analysis","created":"2022-05-23","cited_by_count":23,"area":null},{"id":"2304.06133","title":"Towards Evaluating Explanations of Vision Transformers for Medical Imaging","created":"2023-04-12","cited_by_count":23,"area":null},{"id":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2303.03052","title":"Masked Images Are Counterfactual Samples for Robust Fine-tuning","created":"2023-03-06","cited_by_count":20,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2212.04098","title":"EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder","created":"2022-12-08","cited_by_count":18,"area":null},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2304.00058","title":"Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding","created":"2023-03-31","cited_by_count":16,"area":null},{"id":"2412.11576","title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","created":"2024-12-16","cited_by_count":16,"area":null},{"id":"2404.01331","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2505.21862","title":"Towards Scalable Language-Image Pre-training for 3D Medical Imaging","created":"2025-05-28","cited_by_count":14,"area":null},{"id":"2303.01871","title":"Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification","created":"2023-03-03","cited_by_count":13,"area":null},{"id":"2303.14377","title":"Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation","created":"2023-03-25","cited_by_count":13,"area":null},{"id":"2311.06786","title":"Explainability of Vision Transformers: A Comprehensive Review and New Perspectives","created":"2023-11-12","cited_by_count":12,"area":null},{"id":"2411.00715","title":"B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2503.14640","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2207.05358","title":"eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation","created":"2022-07-12","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2208.08263","title":"Multimodal foundation models are better simulators of the human brain","created":"2022-08-17","cited_by_count":10,"area":null},{"id":"2308.15939","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","created":"2023-08-30","cited_by_count":10,"area":null},{"id":"2310.15368","title":"Deep Integrated Explanations","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2312.02364","title":"Class-Discriminative Attention Maps for Vision Transformers","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2208.06612","title":"Interpreting BERT-based Text Similarity via Activation and Saliency Maps","created":"2022-08-13","cited_by_count":9,"area":null},{"id":"2305.01486","title":"ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2312.06716","title":"Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations","created":"2023-12-11","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"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":"2502.15682","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","created":"2025-02-21","cited_by_count":9,"area":null},{"id":"2112.02841","title":"GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2112.06888","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2303.02128","title":"TRUSformer: Improving Prostate Cancer Detection from Micro-Ultrasound Using Attention and Self-Supervision","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2411.10922","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2207.02327","title":"TractoFormer: A Novel Fiber-level Whole Brain Tractography Analysis Framework Using Spectral Embedding and Vision Transformers","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2211.05120","title":"Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2406.18836","title":"Zero-shot Composed Image Retrieval Considering Query-target Relationship Leveraging Masked Image-text Pairs","created":"2024-06-27","cited_by_count":7,"area":null},{"id":"2407.03251","title":"ACTRESS: Active Retraining for Semi-supervised Visual Grounding","created":"2024-07-03","cited_by_count":7,"area":null},{"id":"2504.04470","title":"Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2209.15261","title":"Minimalistic Unsupervised Learning with the Sparse Manifold Transform","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2210.03899","title":"Multi-Scale Wavelet Transformer for Face Forgery Detection","created":"2022-10-08","cited_by_count":6,"area":null},{"id":"2305.16192","title":"Explainability Techniques for Chemical Language Models","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2406.02625","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2406.12649","title":"Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2408.01076","title":"Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2410.11374","title":"Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2506.02138","title":"Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2507.04388","title":"Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2406.04612","title":"Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2503.20318","title":"EditCLIP: Representation Learning for Image Editing","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2505.07496","title":"DocVXQA: Context-Aware Visual Explanations for Document Question Answering","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2309.00252","title":"Interpretable Medical Imagery Diagnosis with Self-Attentive Transformers: A Review of Explainable AI for Health Care","created":"2023-09-01","cited_by_count":4,"area":null}],"next_cursor":"100"}