{"total":47,"rows":[{"id":"2209.11345","title":"Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration","created":"2022-09-22","cited_by_count":73,"area":null},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2205.14304","title":"Multimodal Fake News Detection via CLIP-Guided Learning","created":"2022-05-28","cited_by_count":42,"area":null},{"id":"2402.17417","title":"CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification","created":"2024-02-27","cited_by_count":40,"area":null},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36,"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":"2307.07135","title":"MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System","created":"2023-07-14","cited_by_count":31,"area":null},{"id":"2402.19387","title":"SeD: Semantic-Aware Discriminator for Image Super-Resolution","created":"2024-02-29","cited_by_count":26,"area":null},{"id":"2206.05741","title":"Bootstrapping Multi-view Representations for Fake News Detection","created":"2022-06-12","cited_by_count":25,"area":null},{"id":"2503.19296","title":"Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval","created":"2025-03-25","cited_by_count":18,"area":null},{"id":"2305.18169","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","created":"2023-05-29","cited_by_count":16,"area":null},{"id":"2304.00827","title":"Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion","created":"2023-04-03","cited_by_count":15,"area":null},{"id":"2503.15949","title":"CausalCLIPSeg: Unlocking CLIP's Potential in Referring Medical Image Segmentation with Causal Intervention","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2302.09554","title":"Mixed Hierarchy Network for Image Restoration","created":"2023-02-19","cited_by_count":14,"area":null},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","cited_by_count":14,"area":null},{"id":"2209.09502","title":"GAMA: Generative Adversarial Multi-Object Scene Attacks","created":"2022-09-20","cited_by_count":13,"area":null},{"id":"2310.15105","title":"FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2401.00701","title":"Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning","created":"2024-01-01","cited_by_count":12,"area":null},{"id":"2308.15284","title":"ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques","created":"2023-08-29","cited_by_count":10,"area":null},{"id":"2303.12997","title":"FER-former: Multi-modal Transformer for Facial Expression Recognition","created":"2023-03-23","cited_by_count":8,"area":null},{"id":"2307.08789","title":"Generative AI in Agriculture: Creating Image Datasets Using DALL.E's Advanced Large Language Model Capabilities","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2406.00423","title":"Multimodal Metadata Assignment for Cultural Heritage Artifacts","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2402.16350","title":"Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2403.17173","title":"Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2408.05955","title":"Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2508.12668","title":"WP-CLIP: Leveraging CLIP to Predict W\\\"olfflin's Principles in Visual Art","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2210.11141","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2409.01109","title":"SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2211.15672","title":"ExpNet: A unified network for Expert-Level Classification","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2408.12953","title":"State-of-the-Art Fails in the Art of Damage Detection","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2412.17601","title":"AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2507.09242","title":"PPJudge: Towards Human-Aligned Assessment of Artistic Painting Process","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2211.13130","title":"A Brief Overview of AI Governance for Responsible Machine Learning Systems","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2307.12445","title":"SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces","created":"2023-07-23","cited_by_count":0,"area":null},{"id":"2403.03408","title":"Scene Depth Estimation from Traditional Oriental Landscape Paintings","created":"2024-03-06","cited_by_count":0,"area":null},{"id":"2403.05703","title":"Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2404.18695","title":"Dual-Modal Prompting for Sketch-Based Image Retrieval","created":"2024-04-29","cited_by_count":0,"area":null},{"id":"2408.01827","title":"ST-SACLF: Style Transfer Informed Self-Attention Classifier for Bias-Aware Painting Classification","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2412.04580","title":"ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2505.17096","title":"TAGS: 3D Tumor-Adaptive Guidance for SAM","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.18884","title":"LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2509.08618","title":"CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.08624","title":"UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2603.12227","title":"Interpreting Contrastive Embeddings in Specific Domains with Fuzzy Rules","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.18974","title":"Harnessing Self-Supervised Features for Art Classification","created":"2026-05-18","cited_by_count":0,"area":null}],"next_cursor":null}