{"list":"other","total":65,"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":"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":"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":"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"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":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"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":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"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":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"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":"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":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"2103.03571","title":"Cycle Self-Training for Domain Adaptation","created":"2021-03-05","cited_by_count":120},{"id":"1711.01575","title":"Adversarial Dropout Regularization","created":"2017-11-05","cited_by_count":106},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"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":"2004.12615","title":"Maximum Density Divergence for Domain Adaptation","created":"2020-04-27","cited_by_count":76},{"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":"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":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47},{"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":"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":"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":"2207.10285","title":"Grounding Visual Representations with Texts for Domain Generalization","created":"2022-07-21","cited_by_count":30},{"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":"2310.01211","title":"From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication","created":"2023-10-02","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":"2403.06946","title":"Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation","created":"2024-03-11","cited_by_count":13},{"id":"2407.02309","title":"Semantically Guided Representation Learning For Action Anticipation","created":"2024-07-02","cited_by_count":10},{"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":"2403.05535","title":"Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos","created":"2024-03-08","cited_by_count":4}],"next_cursor":null}