{"total":198,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864,"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651,"area":null},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602,"area":null},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"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":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"id":"2104.12836","title":"Multimodal Contrastive Training for Visual Representation Learning","created":"2021-04-26","cited_by_count":124,"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":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"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":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"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":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"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":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67,"area":"mllm"},{"id":"2303.14302","title":"VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining","created":"2023-03-24","cited_by_count":65,"area":"mllm"},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64,"area":null},{"id":"2305.18203","title":"Concept Decomposition for Visual Exploration and Inspiration","created":"2023-05-29","cited_by_count":61,"area":null},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"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":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"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":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","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":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"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":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","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":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2211.13224","title":"Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors","created":"2022-11-23","cited_by_count":34,"area":"diffusion"},{"id":"2204.07441","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","created":"2022-04-15","cited_by_count":33,"area":"mllm"},{"id":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2305.03347","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"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":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","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":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","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":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","cited_by_count":20,"area":null},{"id":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20,"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":"2301.05372","title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","created":"2023-01-13","cited_by_count":20,"area":null},{"id":"2409.18991","title":"Surveying the MLLM Landscape: A Meta-Review of Current Surveys","created":"2024-09-17","cited_by_count":20,"area":"mllm"},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2201.07366","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","created":"2022-01-19","cited_by_count":18,"area":null},{"id":"2301.12644","title":"Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","cited_by_count":17,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15,"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":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2210.15110","title":"Masked Vision-Language Transformer in Fashion","created":"2022-10-27","cited_by_count":14,"area":null},{"id":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","cited_by_count":14,"area":"mllm"},{"id":"2105.13033","title":"SSAN: Separable Self-Attention Network for Video Representation Learning","created":"2021-05-27","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":"2209.03648","title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","created":"2022-09-08","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":"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":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2111.15015","title":"Neural Attention for Image Captioning: Review of Outstanding Methods","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2202.08806","title":"Grammar-Based Grounded Lexicon Learning","created":"2022-02-17","cited_by_count":11,"area":null},{"id":"2209.11388","title":"LGDN: Language-Guided Denoising Network for Video-Language Modeling","created":"2022-09-23","cited_by_count":11,"area":null},{"id":"2305.04195","title":"Cross-Modal Retrieval for Motion and Text via DropTriple Loss","created":"2023-05-07","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":"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":"2203.05465","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","created":"2022-03-10","cited_by_count":9,"area":null},{"id":"2510.02292","title":"From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens","created":"2025-10-02","cited_by_count":9,"area":"mllm"},{"id":"2604.23950","title":"LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models","created":"2026-04-27","cited_by_count":9,"area":"lr"},{"id":"2105.08106","title":"Multi-Modal Image Captioning for the Visually Impaired","created":"2021-05-17","cited_by_count":8,"area":null},{"id":"2212.11790","title":"Normalized Contrastive Learning for Text-Video Retrieval","created":"2022-11-30","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":"2409.06535","title":"PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation","created":"2024-09-10","cited_by_count":8,"area":null},{"id":"2103.14517","title":"On the hidden treasure of dialog in video question answering","created":"2021-03-26","cited_by_count":7,"area":null},{"id":"2104.03337","title":"Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning","created":"2021-04-07","cited_by_count":7,"area":null},{"id":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2210.15028","title":"FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2505.12473","title":"Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables","created":"2025-05-18","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":"2210.05039","title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling","created":"2022-10-10","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":"2303.05093","title":"Improving Video Retrieval by Adaptive Margin","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2409.19865","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","created":"2024-09-30","cited_by_count":6,"area":null}],"next_cursor":"100"}