{"total":70,"rows":[{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40,"area":null},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2111.08366","title":"Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity","created":"2021-11-16","cited_by_count":35,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33,"area":null},{"id":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2106.06509","title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching","created":"2021-06-11","cited_by_count":26,"area":null},{"id":"2104.08910","title":"Towards Open-World Text-Guided Face Image Generation and Manipulation","created":"2021-04-18","cited_by_count":25,"area":null},{"id":"2112.01832","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","created":"2021-12-03","cited_by_count":23,"area":null},{"id":"2309.17093","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","created":"2023-09-29","cited_by_count":23,"area":null},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"area":null},{"id":"2112.03162","title":"Embedding Arithmetic of Multimodal Queries for Image Retrieval","created":"2021-12-06","cited_by_count":21,"area":null},{"id":"2404.04231","title":"Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation","created":"2024-04-05","cited_by_count":21,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2110.02623","title":"Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2208.09843","title":"CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval","created":"2022-08-21","cited_by_count":13,"area":null},{"id":"2301.06844","title":"USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval","created":"2023-01-17","cited_by_count":13,"area":null},{"id":"2406.11820","title":"Composing Object Relations and Attributes for Image-Text Matching","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2208.08080","title":"Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides","created":"2022-08-17","cited_by_count":10,"area":null},{"id":"2302.01332","title":"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval","created":"2023-02-02","cited_by_count":10,"area":null},{"id":"2303.13371","title":"Plug-and-Play Regulators for Image-Text Matching","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2506.07471","title":"Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2312.05777","title":"Negative Pre-aware for Noisy Cross-modal Matching","created":"2023-12-10","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":"2402.15276","title":"CFIR: Fast and Effective Long-Text To Image Retrieval for Large Corpora","created":"2024-02-23","cited_by_count":8,"area":null},{"id":"2208.12510","title":"PRVR: Partially Relevant Video Retrieval","created":"2022-08-26","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":"2202.07901","title":"Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition","created":"2022-02-16","cited_by_count":6,"area":null},{"id":"2503.10526","title":"NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2203.01445","title":"LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2203.04668","title":"Towards Inadequately Pre-trained Models in Transfer Learning","created":"2022-03-09","cited_by_count":5,"area":null},{"id":"2207.13061","title":"NewsStories: Illustrating articles with visual summaries","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2207.14428","title":"Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2309.14999","title":"Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Features","created":"2023-09-26","cited_by_count":5,"area":null},{"id":"2402.13576","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2407.15613","title":"Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2410.15266","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2211.08657","title":"Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2309.08154","title":"Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking","created":"2023-09-15","cited_by_count":3,"area":null},{"id":"2407.12346","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2203.05349","title":"Two-stream Hierarchical Similarity Reasoning for Image-text Matching","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2207.01733","title":"Are metrics measuring what they should? An evaluation of image captioning task metrics","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2209.14667","title":"Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2210.04754","title":"Improving Visual-Semantic Embeddings by Learning Semantically-Enhanced Hard Negatives for Cross-modal Information Retrieval","created":"2022-10-10","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2508.21539","title":"HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2601.11393","title":"Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2103.15686","title":"Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2305.06141","title":"Active Semantic Localization with Graph Neural Embedding","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2403.19386","title":"PointCloud-Text Matching: Benchmark Datasets and a Baseline","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2105.04242","title":"T-EMDE: Sketching-based global similarity for cross-modal retrieval","created":"2021-05-10","cited_by_count":0,"area":null},{"id":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2210.08389","title":"Semantic Video Moments Retrieval at Scale: A New Task and a Baseline","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2211.11351","title":"Are All Combinations Equal? Combining Textual and Visual Features with Multiple Space Learning for Text-Based Video Retrieval","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2405.16301","title":"Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2406.16111","title":"Multi-Scale Temporal Difference Transformer for Video-Text Retrieval","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2505.09997","title":"Descriptive Image-Text Matching with Graded Contextual Similarity","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.20070","title":"Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2506.23605","title":"AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2605.15723","title":"GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective","created":"2026-05-15","cited_by_count":0,"area":null}],"next_cursor":null}