{"list":"other","total":92,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1809.09478","title":"Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation","created":"2018-09-25","cited_by_count":295},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"1510.02192","title":"Simultaneous Deep Transfer Across Domains and Tasks","created":"2015-10-08","cited_by_count":206},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"1809.02176","title":"Multi-Adversarial Domain Adaptation","created":"2018-09-04","cited_by_count":196},{"id":"1811.08585","title":"Progressive Feature Alignment for Unsupervised Domain Adaptation","created":"2018-11-21","cited_by_count":183},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"2002.07953","title":"Universal Domain Adaptation through Self Supervision","created":"2020-02-19","cited_by_count":172},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"2002.11361","title":"Understanding Self-Training for Gradual Domain Adaptation","created":"2020-02-26","cited_by_count":149},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"2008.01392","title":"Learning Visual Representations with Caption Annotations","created":"2020-08-04","cited_by_count":123},{"id":"2103.03571","title":"Cycle Self-Training for Domain Adaptation","created":"2021-03-05","cited_by_count":120},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1711.01575","title":"Adversarial Dropout Regularization","created":"2017-11-05","cited_by_count":106},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2104.03344","title":"OVANet: One-vs-All Network for Universal Domain Adaptation","created":"2021-04-07","cited_by_count":92},{"id":"1903.09980","title":"Cluster Alignment with a Teacher for Unsupervised Domain Adaptation","created":"2019-03-24","cited_by_count":88},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80},{"id":"2106.05528","title":"Cross-domain Contrastive Learning for Unsupervised Domain Adaptation","created":"2021-06-10","cited_by_count":76},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2106.04151","title":"Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation","created":"2021-06-08","cited_by_count":67},{"id":"2204.03838","title":"Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation","created":"2022-04-08","cited_by_count":66},{"id":"2204.07683","title":"Safe Self-Refinement for Transformer-based Domain Adaptation","created":"2022-04-16","cited_by_count":61},{"id":"2303.13434","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","created":"2023-03-23","cited_by_count":54},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46},{"id":"2108.05720","title":"Semantic Concentration for Domain Adaptation","created":"2021-08-12","cited_by_count":42},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"2309.12530","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","created":"2023-09-21","cited_by_count":40},{"id":"1811.05443","title":"Co-regularized Alignment for Unsupervised Domain Adaptation","created":"2018-11-13","cited_by_count":39},{"id":"2111.12853","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","created":"2021-11-25","cited_by_count":39},{"id":"2210.09520","title":"Using Language to Extend to Unseen Domains","created":"2022-10-18","cited_by_count":34},{"id":"2106.10812","title":"ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation","created":"2021-06-21","cited_by_count":33},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32},{"id":"2207.10285","title":"Grounding Visual Representations with Texts for Domain Generalization","created":"2022-07-21","cited_by_count":30},{"id":"2006.10297","title":"Joint Contrastive Learning for Unsupervised Domain Adaptation","created":"2020-06-18","cited_by_count":25},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25},{"id":"2012.01806","title":"Attribute-Guided Adversarial Training for Robustness to Natural Perturbations","created":"2020-12-03","cited_by_count":23},{"id":"2104.01286","title":"Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation","created":"2021-04-03","cited_by_count":21},{"id":"2208.07365","title":"Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective","created":"2022-08-15","cited_by_count":21},{"id":"2104.08313","title":"Does language help generalization in vision models?","created":"2021-04-16","cited_by_count":19},{"id":"2303.15443","title":"GeoNet: Benchmarking Unsupervised Adaptation across Geographies","created":"2023-03-27","cited_by_count":17},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17},{"id":"2207.12389","title":"MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation","created":"2022-07-25","cited_by_count":15},{"id":"2401.14148","title":"LanDA: Language-Guided Multi-Source Domain Adaptation","created":"2024-01-25","cited_by_count":13},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11},{"id":"2204.11122","title":"Can domain adaptation make object recognition work for everyone?","created":"2022-04-23","cited_by_count":8},{"id":"2208.02804","title":"Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels","created":"2022-08-04","cited_by_count":7},{"id":"2305.12717","title":"TADA: Efficient Task-Agnostic Domain Adaptation for Transformers","created":"2023-05-22","cited_by_count":6},{"id":"2311.18572","title":"Source-free Video Domain Adaptation by Learning from Noisy Labels","created":"2023-11-30","cited_by_count":6},{"id":"2308.09931","title":"TDG: Text-guided Domain Generalization","created":"2023-08-19","cited_by_count":3}],"next_cursor":null}