{"total":349,"rows":[{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424,"area":null},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"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":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191,"area":null},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"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":"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":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102,"area":null},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90,"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":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79,"area":null},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2204.09868","title":"Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval","created":"2022-04-21","cited_by_count":77,"area":null},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2203.11591","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","created":"2022-03-22","cited_by_count":70,"area":null},{"id":"2205.00272","title":"Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning","created":"2022-04-30","cited_by_count":69,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65,"area":null},{"id":"2101.03036","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","created":"2021-01-08","cited_by_count":62,"area":null},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62,"area":null},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57,"area":null},{"id":"2112.00656","title":"Object-aware Video-language Pre-training for Retrieval","created":"2021-12-01","cited_by_count":57,"area":null},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56,"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":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44,"area":null},{"id":"2108.01453","title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","created":"2021-07-06","cited_by_count":43,"area":null},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43,"area":null},{"id":"2304.01091","title":"Changes to Captions: An Attentive Network for Remote Sensing Change Captioning","created":"2023-04-03","cited_by_count":41,"area":null},{"id":"2204.09860","title":"Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information","created":"2022-04-21","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":"2208.14365","title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search","created":"2022-08-30","cited_by_count":38,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36,"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":"2205.13445","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","created":"2022-05-25","cited_by_count":35,"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":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"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":"2108.07073","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","created":"2021-08-16","cited_by_count":31,"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":"2103.11920","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","created":"2021-03-22","cited_by_count":28,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2208.03354","title":"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch","created":"2022-08-05","cited_by_count":28,"area":null},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27,"area":null},{"id":"2203.14817","title":"Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval","created":"2022-03-28","cited_by_count":27,"area":null},{"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":"2210.03416","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","created":"2022-10-07","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":"2104.08910","title":"Towards Open-World Text-Guided Face Image Generation and Manipulation","created":"2021-04-18","cited_by_count":25,"area":null},{"id":"2305.06002","title":"InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation","created":"2023-05-10","cited_by_count":25,"area":null},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"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":"2308.10172","title":"VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation","created":"2023-08-20","cited_by_count":23,"area":null},{"id":"2402.02045","title":"MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"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":"2105.13868","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","created":"2021-05-28","cited_by_count":21,"area":null},{"id":"2110.03094","title":"Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports","created":"2021-10-06","cited_by_count":21,"area":null},{"id":"2301.09017","title":"Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?","created":"2023-01-21","cited_by_count":21,"area":null},{"id":"2311.00519","title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","created":"2023-11-01","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":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20,"area":null},{"id":"2203.03853","title":"Where Does the Performance Improvement Come From? -- A Reproducibility Concern about Image-Text Retrieval","created":"2022-03-08","cited_by_count":19,"area":null},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19,"area":null},{"id":"2309.01420","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","created":"2023-09-04","cited_by_count":19,"area":null},{"id":"2105.13135","title":"Self-Supervised Multimodal Opinion Summarization","created":"2021-05-27","cited_by_count":18,"area":null},{"id":"2204.02547","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","created":"2022-04-06","cited_by_count":18,"area":null},{"id":"2212.11958","title":"Asymmetric Cross-Scale Alignment for Text-Based Person Search","created":"2022-11-26","cited_by_count":18,"area":null},{"id":"2308.10239","title":"From Global to Local: Multi-scale Out-of-distribution Detection","created":"2023-08-20","cited_by_count":18,"area":null},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17,"area":null},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2107.05176","title":"Zero-Shot Compositional Concept Learning","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2203.10852","title":"Multi-modal learning for predicting the genotype of glioma","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2212.00904","title":"Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning","created":"2022-12-01","cited_by_count":15,"area":null},{"id":"2409.13475","title":"PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2101.00265","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","created":"2021-01-01","cited_by_count":14,"area":null},{"id":"2107.01872","title":"Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"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}],"next_cursor":"100"}