{"total":115,"rows":[{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121,"area":null},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112,"area":null},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110,"area":null},{"id":"2307.14061","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","created":"2023-07-26","cited_by_count":108,"area":"mllm"},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68,"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":"2205.08536","title":"Disentangling Visual Embeddings for Attributes and Objects","created":"2022-05-17","cited_by_count":55,"area":null},{"id":"2403.12445","title":"Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory","created":"2024-03-19","cited_by_count":36,"area":"mllm"},{"id":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33,"area":null},{"id":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29,"area":null},{"id":"2402.10805","title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond","created":"2024-02-16","cited_by_count":28,"area":"mllm"},{"id":"2303.12419","title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","created":"2023-03-22","cited_by_count":27,"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":"2304.06275","title":"Noisy Correspondence Learning with Meta Similarity Correction","created":"2023-04-13","cited_by_count":26,"area":null},{"id":"2112.09331","title":"Contrastive Vision-Language Pre-training with Limited Resources","created":"2021-12-17","cited_by_count":25,"area":"mllm"},{"id":"2311.08245","title":"TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition","created":"2023-11-14","cited_by_count":25,"area":null},{"id":"2108.02417","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","created":"2021-08-05","cited_by_count":23,"area":null},{"id":"2206.11134","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","created":"2022-06-22","cited_by_count":23,"area":null},{"id":"2310.17468","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","created":"2023-10-26","cited_by_count":22,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","cited_by_count":20,"area":null},{"id":"2411.02669","title":"Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack","created":"2024-11-04","cited_by_count":18,"area":"mllm"},{"id":"2107.05176","title":"Zero-Shot Compositional Concept Learning","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14,"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":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2102.04980","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","created":"2021-02-09","cited_by_count":12,"area":null},{"id":"2403.05105","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","created":"2024-03-08","cited_by_count":11,"area":null},{"id":"2404.17785","title":"Temporal Scaling Law for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2106.02206","title":"Stochastic Iterative Graph Matching","created":"2021-06-04","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":"2306.08789","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2308.04380","title":"Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination","created":"2023-08-08","cited_by_count":10,"area":null},{"id":"2407.09541","title":"MATE: Meet At The Embedding -- Connecting Images with Long Texts","created":"2024-06-26","cited_by_count":10,"area":"mllm"},{"id":"2304.12570","title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","created":"2023-04-25","cited_by_count":9,"area":null},{"id":"2412.20645","title":"YOLO-UniOW: Efficient Universal Open-World Object Detection","created":"2024-12-30","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":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2308.04343","title":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2308.14009","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2309.16127","title":"Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation","created":"2023-09-28","cited_by_count":8,"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":"2503.06974","title":"Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment","created":"2025-03-10","cited_by_count":8,"area":null},{"id":"2306.10563","title":"Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2106.02400","title":"A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval","created":"2021-06-04","cited_by_count":6,"area":null},{"id":"2109.01295","title":"Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning","created":"2021-09-03","cited_by_count":6,"area":null},{"id":"2110.11338","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","created":"2021-10-20","cited_by_count":6,"area":null},{"id":"2210.05991","title":"Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2212.08281","title":"HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval","created":"2022-12-16","cited_by_count":6,"area":null},{"id":"2404.17273","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2407.17274","title":"Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2408.12292","title":"Towards Deconfounded Image-Text Matching with Causal Inference","created":"2024-08-22","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":"2312.16478","title":"Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation","created":"2023-12-27","cited_by_count":5,"area":null},{"id":"2412.10761","title":"Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation","created":"2024-12-14","cited_by_count":5,"area":null},{"id":"2503.14953","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","created":"2025-03-19","cited_by_count":5,"area":"distill"},{"id":"2201.02772","title":"A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval","created":"2022-01-08","cited_by_count":4,"area":"mllm"},{"id":"2205.12105","title":"HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval","created":"2022-05-24","cited_by_count":4,"area":"mllm"},{"id":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2404.18114","title":"Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2405.11971","title":"Data Augmentation for Text-based Person Retrieval Using Large Language Models","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2405.18959","title":"Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval","created":"2024-05-29","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":"2202.07474","title":"Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2204.13382","title":"Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2306.14460","title":"Hierarchical Matching and Reasoning for Multi-Query Image Retrieval","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2308.09599","title":"Language-Guided Diffusion Model for Visual Grounding","created":"2023-08-18","cited_by_count":3,"area":"diffusion"},{"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":"2408.01349","title":"PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2502.19962","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2608.20810","title":"When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2105.05636","title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2112.08117","title":"Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos","created":"2021-12-15","cited_by_count":2,"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":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2303.00181","title":"Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2307.09942","title":"TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network","created":"2023-07-19","cited_by_count":2,"area":null},{"id":"2404.10838","title":"Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning","created":"2024-04-16","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":"2209.13869","title":"Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2210.11319","title":"Image-Text Retrieval with Binary and Continuous Label Supervision","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2211.16208","title":"SLAN: Self-Locator Aided Network for Cross-Modal Understanding","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2212.14322","title":"BagFormer: Better Cross-Modal Retrieval via bag-wise interaction","created":"2022-12-29","cited_by_count":1,"area":null},{"id":"2303.00448","title":"The style transformer with common knowledge optimization for image-text retrieval","created":"2023-03-01","cited_by_count":1,"area":null},{"id":"2304.07567","title":"CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Structure for Vision-Language Retrieval","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2304.10254","title":"Image-text Retrieval via Preserving Main Semantics of Vision","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2312.01656","title":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","created":"2023-12-04","cited_by_count":1,"area":"mllm"},{"id":"2407.16248","title":"Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2409.06285","title":"Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2507.09256","title":"Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2510.11175","title":"Reliable Cross-modal Alignment via Prototype Iterative Construction","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2602.19096","title":"The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers","created":"2026-02-22","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}],"next_cursor":"100"}