{"list":"other","total":120,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"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":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"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":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"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":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"1606.00185","title":"A Survey on Learning to Hash","created":"2016-06-01","cited_by_count":119},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"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":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"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":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"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":"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":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52},{"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":"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":"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":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38},{"id":"1909.04101","title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","created":"2019-09-09","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":"2009.09399","title":"DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition","created":"2020-09-20","cited_by_count":32},{"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":"2412.11077","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval","created":"2024-12-15","cited_by_count":32},{"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":"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":"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":"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},{"id":"2009.01485","title":"SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval","created":"2020-09-03","cited_by_count":23},{"id":"2312.08924","title":"Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking","created":"2023-12-14","cited_by_count":23},{"id":"2305.09979","title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","created":"2023-05-17","cited_by_count":22},{"id":"2405.19149","title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval","created":"2024-05-29","cited_by_count":21},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21},{"id":"2404.11317","title":"Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives","created":"2024-04-17","cited_by_count":20},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18},{"id":"1805.00313","title":"Neural Compatibility Modeling with Attentive Knowledge Distillation","created":"2018-04-17","cited_by_count":17},{"id":"2408.11305","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","created":"2024-08-21","cited_by_count":17},{"id":"2312.06179","title":"Dynamic Weighted Combiner for Mixed-Modal Image Retrieval","created":"2023-12-11","cited_by_count":15},{"id":"2306.02092","title":"Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations","created":"2023-06-03","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":"2412.11087","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","created":"2024-12-15","cited_by_count":13},{"id":"2403.07222","title":"You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval","created":"2024-03-12","cited_by_count":12}],"next_cursor":"100"}