{"list":"other","total":60,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"1908.06903","title":"Multi-Garment Net: Learning to Dress 3D People from Images","created":"2019-08-19","cited_by_count":245},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"id":"1611.07865","title":"Controlling Perceptual Factors in Neural Style Transfer","created":"2016-11-23","cited_by_count":100},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"1912.04070","title":"Synthetic Humans for Action Recognition from Unseen Viewpoints","created":"2019-12-09","cited_by_count":46},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44},{"id":"1904.06539","title":"HAKE: Human Activity Knowledge Engine","created":"2019-04-13","cited_by_count":32},{"id":"1612.00881","title":"Procedural Generation of Videos to Train Deep Action Recognition Networks","created":"2016-12-02","cited_by_count":31},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26},{"id":"2212.09068","title":"Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization","created":"2022-12-18","cited_by_count":22},{"id":"2204.00172","title":"A Unified Framework for Domain Adaptive Pose Estimation","created":"2022-04-01","cited_by_count":20},{"id":"2211.09790","title":"ConStruct-VL: Data-Free Continual Structured VL Concepts Learning","created":"2022-11-17","cited_by_count":20},{"id":"2112.09290","title":"PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision","created":"2021-12-17","cited_by_count":11},{"id":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8}],"next_cursor":null}