{"list":"other","total":65,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"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":"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":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"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},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"id":"1703.07220","title":"Improving Person Re-identification by Attribute and Identity Learning","created":"2017-03-21","cited_by_count":96},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93},{"id":"2302.03298","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","created":"2023-02-07","cited_by_count":81},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"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":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65},{"id":"1906.09610","title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","created":"2019-06-23","cited_by_count":64},{"id":"2101.03036","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","created":"2021-01-08","cited_by_count":62},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57},{"id":"2204.09331","title":"NFormer: Robust Person Re-identification with Neighbor Transformer","created":"2022-04-20","cited_by_count":57},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54},{"id":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44},{"id":"2112.06714","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","created":"2021-12-13","cited_by_count":40},{"id":"2209.05773","title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval","created":"2022-09-13","cited_by_count":39},{"id":"2209.06209","title":"Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold","created":"2022-09-13","cited_by_count":38},{"id":"2307.16489","title":"BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models","created":"2023-07-31","cited_by_count":37},{"id":"2101.08238","title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification","created":"2021-01-19","cited_by_count":34},{"id":"2006.04569","title":"Parameter-Efficient Person Re-identification in the 3D Space","created":"2020-06-08","cited_by_count":33},{"id":"1808.01571","title":"Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association","created":"2018-08-05","cited_by_count":29},{"id":"2309.03558","title":"Region Generation and Assessment Network for Occluded Person Re-Identification","created":"2023-09-07","cited_by_count":20},{"id":"2307.08424","title":"Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model","created":"2023-07-17","cited_by_count":14},{"id":"2411.17776","title":"Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search","created":"2024-11-26","cited_by_count":11},{"id":"2203.05465","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","created":"2022-03-10","cited_by_count":9},{"id":"2211.10933","title":"Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification","created":"2022-11-20","cited_by_count":4}],"next_cursor":null}