{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"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":"1610.01983","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","created":"2016-10-06","cited_by_count":194},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150},{"id":"1910.11319","title":"Progressive Domain Adaptation for Object Detection","created":"2019-10-24","cited_by_count":134},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"2302.11803","title":"A Comprehensive Survey on Source-free Domain Adaptation","created":"2023-02-23","cited_by_count":104},{"id":"2105.13502","title":"Unsupervised Domain Adaptation of Object Detectors: A Survey","created":"2021-05-27","cited_by_count":93},{"id":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87},{"id":"2003.13261","title":"Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning","created":"2020-03-30","cited_by_count":71},{"id":"2308.05659","title":"AD-CLIP: Adapting Domains in Prompt Space Using CLIP","created":"2023-08-10","cited_by_count":62},{"id":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60},{"id":"2203.15793","title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":55},{"id":"2108.05137","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","created":"2021-08-11","cited_by_count":47},{"id":"2212.04196","title":"Learning Domain Invariant Prompt for Vision-Language Models","created":"2022-12-08","cited_by_count":36},{"id":"2302.09251","title":"StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization","created":"2023-02-18","cited_by_count":36},{"id":"1707.01922","title":"Zero-Shot Deep Domain Adaptation","created":"2017-07-06","cited_by_count":35},{"id":"2403.08506","title":"DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning","created":"2024-03-11","cited_by_count":32},{"id":"2404.07155","title":"Unified Language-driven Zero-shot Domain Adaptation","created":"2024-04-10","cited_by_count":30},{"id":"2405.14497","title":"Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment","created":"2024-05-23","cited_by_count":29},{"id":"2405.15225","title":"Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection","created":"2024-05-24","cited_by_count":29},{"id":"2210.11539","title":"ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing","created":"2022-10-20","cited_by_count":28},{"id":"2307.01750","title":"SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection","created":"2023-07-04","cited_by_count":28},{"id":"2402.18447","title":"Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization","created":"2024-02-28","cited_by_count":24},{"id":"2310.07730","title":"Domain-Controlled Prompt Learning","created":"2023-09-30","cited_by_count":22},{"id":"2312.12133","title":"Object-Aware Domain Generalization for Object Detection","created":"2023-12-19","cited_by_count":21},{"id":"2306.05718","title":"Learning Domain-Aware Detection Head with Prompt Tuning","created":"2023-06-09","cited_by_count":18},{"id":"2505.19866","title":"HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation","created":"2025-05-26","cited_by_count":18},{"id":"2312.01220","title":"Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation","created":"2023-12-02","cited_by_count":17},{"id":"2402.04672","title":"G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection","created":"2024-02-07","cited_by_count":17},{"id":"2309.14950","title":"Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher","created":"2023-09-26","cited_by_count":13},{"id":"2403.18360","title":"Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation","created":"2024-03-27","cited_by_count":12},{"id":"2009.05228","title":"Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation","created":"2020-09-11","cited_by_count":10},{"id":"2307.08779","title":"Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation","created":"2023-07-17","cited_by_count":10},{"id":"2410.09004","title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","created":"2024-10-11","cited_by_count":8},{"id":"2009.05214","title":"Adversarial Learning for Zero-shot Domain Adaptation","created":"2020-09-11","cited_by_count":7},{"id":"2312.12276","title":"POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning","created":"2023-12-19","cited_by_count":6},{"id":"2503.02101","title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","created":"2025-03-03","cited_by_count":6},{"id":"2403.13652","title":"ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer","created":"2024-03-20","cited_by_count":5},{"id":"2406.00777","title":"Diffusion Features to Bridge Domain Gap for Semantic Segmentation","created":"2024-06-02","cited_by_count":5}],"next_cursor":null}