{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2010.00904","title":"Autoregressive Entity Retrieval","created":"2020-10-02","cited_by_count":334},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"1906.07589","title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss","created":"2019-06-18","cited_by_count":185},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113},{"id":"2105.04663","title":"GSPMD: General and Scalable Parallelization for ML Computation Graphs","created":"2021-05-10","cited_by_count":111},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79},{"id":"1611.05013","title":"PixelVAE: A Latent Variable Model for Natural Images","created":"2016-11-15","cited_by_count":70},{"id":"2103.12236","title":"Instance-level Image Retrieval using Reranking Transformers","created":"2021-03-22","cited_by_count":63},{"id":"2009.11278","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","created":"2020-09-23","cited_by_count":59},{"id":"2108.02927","title":"DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features","created":"2021-08-06","cited_by_count":54},{"id":"2103.12528","title":"Multilingual Autoregressive Entity Linking","created":"2021-03-23","cited_by_count":50},{"id":"1412.6574","title":"Visual Instance Retrieval with Deep Convolutional Networks","created":"2014-12-20","cited_by_count":48},{"id":"2204.01458","title":"Correlation Verification for Image Retrieval","created":"2022-04-04","cited_by_count":47},{"id":"1604.07528","title":"Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification","created":"2016-04-26","cited_by_count":41},{"id":"1812.01584","title":"Detect-to-Retrieve: Efficient Regional Aggregation for Image Search","created":"2018-12-04","cited_by_count":39},{"id":"1905.06358","title":"Local Features and Visual Words Emerge in Activations","created":"2019-05-15","cited_by_count":37},{"id":"1908.09756","title":"Differentiable Product Quantization for End-to-End Embedding Compression","created":"2019-08-26","cited_by_count":36},{"id":"2108.00644","title":"Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance","created":"2021-08-02","cited_by_count":35},{"id":"1912.07863","title":"In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation","created":"2019-12-17","cited_by_count":34},{"id":"1411.2173","title":"Stacked Quantizers for Compositional Vector Compression","created":"2014-11-08","cited_by_count":30},{"id":"2109.02244","title":"Self-supervised Product Quantization for Deep Unsupervised Image Retrieval","created":"2021-09-06","cited_by_count":28},{"id":"1706.06064","title":"Recent Advance in Content-based Image Retrieval: A Literature Survey","created":"2017-06-19","cited_by_count":24},{"id":"1708.04150","title":"Binary Generative Adversarial Networks for Image Retrieval","created":"2017-08-08","cited_by_count":22},{"id":"1903.10663","title":"Combination of Multiple Global Descriptors for Image Retrieval","created":"2019-03-26","cited_by_count":21},{"id":"2109.03792","title":"Highly Parallel Autoregressive Entity Linking with Discriminative Correction","created":"2021-09-08","cited_by_count":21},{"id":"2002.11281","title":"Generalized Product Quantization Network for Semi-supervised Image Retrieval","created":"2020-02-26","cited_by_count":20},{"id":"1711.08589","title":"End-to-End Supervised Product Quantization for Image Search and Retrieval","created":"2017-11-23","cited_by_count":16},{"id":"1902.00153","title":"Deep Triplet Quantization","created":"2019-02-01","cited_by_count":16},{"id":"1405.4054","title":"Optimized Cartesian $K$-Means","created":"2014-05-16","cited_by_count":14},{"id":"1611.09502","title":"Deep Quantization: Encoding Convolutional Activations with Deep Generative Model","created":"2016-11-29","cited_by_count":11},{"id":"2105.03933","title":"Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index","created":"2021-05-09","cited_by_count":11},{"id":"2003.04094","title":"A Strong Baseline for Fashion Retrieval with Person Re-Identification Models","created":"2020-03-09","cited_by_count":7},{"id":"1712.00955","title":"Composite Quantization","created":"2017-12-04","cited_by_count":2}],"next_cursor":null}