{"total":151,"rows":[{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2303.11916","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","created":"2023-03-21","cited_by_count":85,"area":"diffusion"},{"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":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73,"area":"mllm"},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57,"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":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45,"area":null},{"id":"2210.05335","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","created":"2022-10-11","cited_by_count":41,"area":"mllm"},{"id":"2111.14581","title":"Learning Fair Classifiers with Partially Annotated Group Labels","created":"2021-11-29","cited_by_count":40,"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":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","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":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"area":null},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"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":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29,"area":null},{"id":"2302.02865","title":"Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs","created":"2023-02-06","cited_by_count":29,"area":null},{"id":"2310.19001","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","created":"2023-10-29","cited_by_count":27,"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":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"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":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20,"area":null},{"id":"2207.03784","title":"A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning","created":"2022-07-08","cited_by_count":19,"area":null},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17,"area":null},{"id":"2303.11086","title":"Pluralistic Aging Diffusion Autoencoder","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2304.00779","title":"Probabilistic Prompt Learning for Dense Prediction","created":"2023-04-03","cited_by_count":17,"area":"mllm"},{"id":"2307.03810","title":"URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2407.04458","title":"Robust Multimodal Learning via Representation Decoupling","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2410.18857","title":"Probabilistic Language-Image Pre-Training","created":"2024-10-24","cited_by_count":16,"area":"mllm"},{"id":"2202.08985","title":"Out of Distribution Data Detection Using Dropout Bayesian Neural Networks","created":"2022-02-18","cited_by_count":15,"area":null},{"id":"2312.06179","title":"Dynamic Weighted Combiner for Mixed-Modal Image Retrieval","created":"2023-12-11","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":"2403.05261","title":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","created":"2024-03-08","cited_by_count":13,"area":null},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13,"area":null},{"id":"2412.06014","title":"Post-hoc Probabilistic Vision-Language Models","created":"2024-12-08","cited_by_count":13,"area":"mllm"},{"id":"2408.06010","title":"DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation","created":"2024-08-12","cited_by_count":12,"area":null},{"id":"2404.00974","title":"Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping","created":"2024-04-01","cited_by_count":11,"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":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"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":"2210.06980","title":"Probabilistic Integration of Object Level Annotations in Chest X-ray Classification","created":"2022-10-13","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":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","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":"2403.18260","title":"Toward Interactive Regional Understanding in Vision-Large Language Models","created":"2024-03-27","cited_by_count":9,"area":"mllm"},{"id":"2412.12492","title":"DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation","created":"2024-12-17","cited_by_count":9,"area":"mllm"},{"id":"2502.15682","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","created":"2025-02-21","cited_by_count":9,"area":null},{"id":"2507.07620","title":"ViLU: Learning Vision-Language Uncertainties for Failure Prediction","created":"2025-07-10","cited_by_count":9,"area":"mllm"},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"area":"mllm"},{"id":"2307.00398","title":"ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models","created":"2023-07-01","cited_by_count":7,"area":"mllm"},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","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":"2304.07747","title":"Language Guided Local Infiltration for Interactive Image Retrieval","created":"2023-04-16","cited_by_count":6,"area":null},{"id":"2402.06150","title":"Domain Generalization with Small Data","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2403.01437","title":"GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features","created":"2024-03-03","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":"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":"2304.01961","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2308.08131","title":"Ranking-aware Uncertainty for Text-guided Image Retrieval","created":"2023-08-16","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":"2310.15624","title":"GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2409.05405","title":"A Survey of Multimodal Composite Editing and Retrieval","created":"2024-09-09","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":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2607.02403","title":"ACID: Action Consistency via Inverse Dynamics for Planning with World Models","created":"2026-07-02","cited_by_count":5,"area":"wm"},{"id":"2111.05814","title":"SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval","created":"2021-11-10","cited_by_count":4,"area":null},{"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":"2212.04114","title":"Group Generalized Mean Pooling for Vision Transformer","created":"2022-12-08","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":"2407.15396","title":"Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation","created":"2024-07-22","cited_by_count":4,"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":"2408.05503","title":"Disentangled Noisy Correspondence Learning","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2408.07050","title":"PSM: Learning Probabilistic Embeddings for Multi-scale Zero-Shot Soundscape Mapping","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2505.11029","title":"Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere","created":"2025-05-16","cited_by_count":4,"area":"mllm"},{"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":"2509.25791","title":"EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2511.08480","title":"Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding","created":"2025-11-11","cited_by_count":4,"area":"mllm"},{"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":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","cited_by_count":3,"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":"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":"2408.05955","title":"Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization","created":"2024-08-12","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":"2509.01383","title":"Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2204.09268","title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2211.08349","title":"Probabilistic Deep Metric Learning for Hyperspectral Image Classification","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2404.12216","title":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2407.21740","title":"Beyond Spectral Decomposition: Bayesian Contrastive Learning and its Non-negative Formulation via Factor Analysis","created":"2024-07-31","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}],"next_cursor":"100"}