{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"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":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"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":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2305.01644","title":"Key-Locked Rank One Editing for Text-to-Image Personalization","created":"2023-05-02","cited_by_count":194},{"id":"2211.13977","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","created":"2022-11-25","cited_by_count":181},{"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":"2109.02748","title":"Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP","created":"2021-09-06","cited_by_count":152},{"id":"1604.01325","title":"Deep Image Retrieval: Learning global representations for image search","created":"2016-04-05","cited_by_count":147},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","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":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79},{"id":"2312.08870","title":"Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens","created":"2023-12-12","cited_by_count":71},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65},{"id":"2209.14290","title":"FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation","created":"2022-09-28","cited_by_count":63},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53},{"id":"1903.09776","title":"Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification","created":"2019-03-23","cited_by_count":51},{"id":"2007.00145","title":"Modality-Agnostic Attention Fusion for visual search with text feedback","created":"2020-06-30","cited_by_count":51},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47},{"id":"2309.01151","title":"EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment","created":"2023-09-03","cited_by_count":44},{"id":"1705.08631","title":"Self-supervised learning of visual features through embedding images into text topic spaces","created":"2017-05-24","cited_by_count":43},{"id":"2205.06784","title":"KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning","created":"2022-05-13","cited_by_count":41},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2201.09680","title":"Relational Memory Augmented Language Models","created":"2022-01-24","cited_by_count":24},{"id":"2003.12299","title":"CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data","created":"2020-03-27","cited_by_count":21},{"id":"2201.00103","title":"Robust Region Feature Synthesizer for Zero-Shot Object Detection","created":"2022-01-01","cited_by_count":20},{"id":"2203.15310","title":"Hybrid Routing Transformer for Zero-Shot Learning","created":"2022-03-29","cited_by_count":20},{"id":"2301.07463","title":"Temporal Perceiving Video-Language Pre-training","created":"2023-01-18","cited_by_count":12}],"next_cursor":null}