{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"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":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"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":"2008.05659","title":"What Should Not Be Contrastive in Contrastive Learning","created":"2020-08-13","cited_by_count":226},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"2003.13911","title":"Proxy Anchor Loss for Deep Metric Learning","created":"2020-03-31","cited_by_count":195},{"id":"1803.11285","title":"Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking","created":"2018-03-29","cited_by_count":191},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"1906.07589","title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss","created":"2019-06-18","cited_by_count":185},{"id":"2108.00946","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","created":"2021-08-02","cited_by_count":164},{"id":"1406.4773","title":"Deep Learning Face Representation by Joint Identification-Verification","created":"2014-06-18","cited_by_count":162},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2002.08473","title":"Revisiting Training Strategies and Generalization Performance in Deep Metric Learning","created":"2020-02-19","cited_by_count":100},{"id":"2007.12163","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","created":"2020-07-23","cited_by_count":98},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"1902.05509","title":"MultiGrain: a unified image embedding for classes and instances","created":"2019-02-14","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":"1707.05691","title":"Learning Fashion Compatibility with Bidirectional LSTMs","created":"2017-07-18","cited_by_count":69},{"id":"1803.09196","title":"Learning Type-Aware Embeddings for Fashion Compatibility","created":"2018-03-25","cited_by_count":61},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61},{"id":"2006.11149","title":"Compositional Learning of Image-Text Query for Image Retrieval","created":"2020-06-19","cited_by_count":57},{"id":"1905.12794","title":"Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback","created":"2019-05-30","cited_by_count":43},{"id":"2011.12982","title":"Grafit: Learning fine-grained image representations with coarse labels","created":"2020-11-25","cited_by_count":43},{"id":"1912.08967","title":"Fashion Outfit Complementary Item Retrieval","created":"2019-12-19","cited_by_count":42},{"id":"1905.13258","title":"A survey of advances in vision-based vehicle re-identification","created":"2019-05-30","cited_by_count":36},{"id":"1908.08589","title":"Learning Similarity Conditions Without Explicit Supervision","created":"2019-08-22","cited_by_count":36},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"id":"1508.01722","title":"Unconstrained Face Verification using Deep CNN Features","created":"2015-08-07","cited_by_count":13},{"id":"2008.00348","title":"Self-supervised Visual Attribute Learning for Fashion Compatibility","created":"2020-08-01","cited_by_count":12},{"id":"2105.01695","title":"Effectively Leveraging Attributes for Visual Similarity","created":"2021-05-04","cited_by_count":9},{"id":"1912.10154","title":"Measuring Dataset Granularity","created":"2019-12-21","cited_by_count":8},{"id":"2205.01668","title":"End-to-End Visual Editing with a Generatively Pre-Trained Artist","created":"2022-05-03","cited_by_count":7}],"next_cursor":null}