{"list":"other","total":146,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"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},{"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":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"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":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1604.01325","title":"Deep Image Retrieval: Learning global representations for image search","created":"2016-04-05","cited_by_count":147},{"id":"1511.06078","title":"Learning Deep Structure-Preserving Image-Text Embeddings","created":"2015-11-19","cited_by_count":139},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103},{"id":"1706.03424","title":"PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval","created":"2017-06-11","cited_by_count":97},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2004.00277","title":"Graph Structured Network for Image-Text Matching","created":"2020-04-01","cited_by_count":93},{"id":"2303.11916","title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","created":"2023-03-21","cited_by_count":85},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"1906.04402","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","created":"2019-06-11","cited_by_count":83},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"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},{"id":"2012.00641","title":"A Decade Survey of Content Based Image Retrieval using Deep Learning","created":"2020-11-23","cited_by_count":72},{"id":"2003.02683","title":"SketchyCOCO: Image Generation from Freehand Scene Sketches","created":"2020-03-05","cited_by_count":67},{"id":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","cited_by_count":67},{"id":"1910.05134","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","created":"2019-10-11","cited_by_count":66},{"id":"1806.08317","title":"Fashion-Gen: The Generative Fashion Dataset and Challenge","created":"2018-06-21","cited_by_count":65},{"id":"1607.06215","title":"A Comprehensive Survey on Cross-modal Retrieval","created":"2016-07-21","cited_by_count":62},{"id":"1803.09196","title":"Learning Type-Aware Embeddings for Fashion Compatibility","created":"2018-03-25","cited_by_count":61},{"id":"2007.08883","title":"Consensus-Aware Visual-Semantic Embedding for Image-Text Matching","created":"2020-07-17","cited_by_count":59},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2006.11149","title":"Compositional Learning of Image-Text Query for Image Retrieval","created":"2020-06-19","cited_by_count":57},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52},{"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":"2007.00145","title":"Modality-Agnostic Attention Fusion for visual search with text feedback","created":"2020-06-30","cited_by_count":51},{"id":"1909.11416","title":"Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matching","created":"2019-09-25","cited_by_count":49},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49},{"id":"2306.07969","title":"GeneCIS: A Benchmark for General Conditional Image Similarity","created":"2023-06-13","cited_by_count":47},{"id":"2303.09429","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","created":"2023-03-16","cited_by_count":46},{"id":"1907.09748","title":"Position Focused Attention Network for Image-Text Matching","created":"2019-07-23","cited_by_count":45},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45},{"id":"2405.00571","title":"Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval","created":"2024-05-01","cited_by_count":44},{"id":"2303.16604","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","created":"2023-03-29","cited_by_count":43},{"id":"2008.02693","title":"Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards","created":"2020-08-06","cited_by_count":38},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38},{"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},{"id":"1909.04101","title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","created":"2019-09-09","cited_by_count":36},{"id":"2309.01366","title":"Target-Guided Composed Image Retrieval","created":"2023-09-04","cited_by_count":36},{"id":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36},{"id":"2305.16304","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","created":"2023-05-25","cited_by_count":35},{"id":"2010.03403","title":"Universal Weighting Metric Learning for Cross-Modal Matching","created":"2020-10-07","cited_by_count":34},{"id":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33},{"id":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","cited_by_count":32},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2010.11550","title":"Learning Dual Semantic Relations with Graph Attention for Image-Text Matching","created":"2020-10-22","cited_by_count":30},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30},{"id":"2106.04128","title":"Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback","created":"2021-06-08","cited_by_count":29},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"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},{"id":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27},{"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},{"id":"2003.03669","title":"Adaptive Offline Quintuplet Loss for Image-Text Matching","created":"2020-03-07","cited_by_count":26},{"id":"2106.06509","title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching","created":"2021-06-11","cited_by_count":26},{"id":"2204.11212","title":"Progressive Learning for Image Retrieval with Hybrid-Modality Queries","created":"2022-04-24","cited_by_count":26},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26},{"id":"2305.20062","title":"Chatting Makes Perfect: Chat-based Image Retrieval","created":"2023-05-31","cited_by_count":25},{"id":"2404.15875","title":"Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval","created":"2024-04-24","cited_by_count":24},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24}],"next_cursor":"100"}