{"list":"other","total":69,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1511.06452","title":"Deep Metric Learning via Lifted Structured Feature Embedding","created":"2015-11-19","cited_by_count":449},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156},{"id":"1604.01325","title":"Deep Image Retrieval: Learning global representations for image search","created":"2016-04-05","cited_by_count":147},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86},{"id":"2303.11916","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","created":"2023-03-21","cited_by_count":85},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"1904.03451","title":"Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval","created":"2019-04-06","cited_by_count":79},{"id":"1807.11724","title":"A Zero-Shot Framework for Sketch-based Image Retrieval","created":"2018-07-31","cited_by_count":71},{"id":"1908.10534","title":"Adversarial Representation Learning for Text-to-Image Matching","created":"2019-08-28","cited_by_count":65},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"1903.03372","title":"Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval","created":"2019-03-08","cited_by_count":57},{"id":"1505.07922","title":"Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network","created":"2015-05-29","cited_by_count":53},{"id":"2309.16137","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","created":"2023-09-28","cited_by_count":52},{"id":"2303.16604","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","created":"2023-03-29","cited_by_count":43},{"id":"2309.14289","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","created":"2023-09-25","cited_by_count":39},{"id":"1708.02412","title":"Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition","created":"2017-08-08","cited_by_count":37},{"id":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27},{"id":"2204.03647","title":"Adapting CLIP For Phrase Localization Without Further Training","created":"2022-04-07","cited_by_count":21},{"id":"2207.09721","title":"Feature Representation Learning for Unsupervised Cross-domain Image Retrieval","created":"2022-07-20","cited_by_count":17},{"id":"2311.01458","title":"Detecting Deepfakes Without Seeing Any","created":"2023-11-02","cited_by_count":17},{"id":"1709.01784","title":"Cross-Domain Image Retrieval with Attention Modeling","created":"2017-09-06","cited_by_count":14},{"id":"2311.07622","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","created":"2023-11-13","cited_by_count":14},{"id":"2403.01431","title":"Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval","created":"2024-03-03","cited_by_count":14},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14},{"id":"2404.15516","title":"Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval","created":"2024-04-23","cited_by_count":13},{"id":"2302.06081","title":"Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval","created":"2023-02-13","cited_by_count":11},{"id":"2108.08356","title":"Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains","created":"2021-08-18","cited_by_count":6},{"id":"2104.11130","title":"Sketch-QNet: A Quadruplet ConvNet for Color Sketch-based Image Retrieval","created":"2021-04-22","cited_by_count":5},{"id":"2309.02169","title":"Dual Relation Alignment for Composed Image Retrieval","created":"2023-09-05","cited_by_count":5},{"id":"2310.16400","title":"Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models","created":"2023-10-25","cited_by_count":4},{"id":"2105.08237","title":"Towards Unsupervised Sketch-based Image Retrieval","created":"2021-05-18","cited_by_count":3}],"next_cursor":null}