{"list":"other","total":55,"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":"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"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":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2003.04390","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","created":"2020-03-09","cited_by_count":179},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133},{"id":"2204.07305","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","created":"2022-04-15","cited_by_count":126},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2010.00763","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","created":"2020-10-02","cited_by_count":63},{"id":"2203.00048","title":"Multi-modal Alignment using Representation Codebook","created":"2022-02-28","cited_by_count":63},{"id":"2204.04567","title":"Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification","created":"2022-04-09","cited_by_count":50},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"2201.06696","title":"ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues","created":"2022-01-18","cited_by_count":42},{"id":"2111.12853","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","created":"2021-11-25","cited_by_count":39},{"id":"2210.15138","title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","created":"2022-10-27","cited_by_count":39},{"id":"2210.04287","title":"Learning to Decompose Visual Features with Latent Textual Prompts","created":"2022-10-09","cited_by_count":28},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28},{"id":"2112.09331","title":"Contrastive Vision-Language Pre-training with Limited Resources","created":"2021-12-17","cited_by_count":25},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23},{"id":"2208.13628","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","created":"2022-08-29","cited_by_count":19},{"id":"2210.05392","title":"TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning","created":"2022-10-11","cited_by_count":16},{"id":"2104.12709","title":"Rich Semantics Improve Few-shot Learning","created":"2021-04-26","cited_by_count":15},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14},{"id":"2307.15460","title":"Cross-Modal Concept Learning and Inference for Vision-Language Models","created":"2023-07-28","cited_by_count":12},{"id":"2308.11507","title":"Unsupervised Prototype Adapter for Vision-Language Models","created":"2023-08-22","cited_by_count":5}],"next_cursor":null}