{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"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":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1812.01866","title":"Few-shot Object Detection via Feature Reweighting","created":"2018-12-05","cited_by_count":265},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2203.03884","title":"Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels","created":"2022-03-08","cited_by_count":218},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168},{"id":"1908.07387","title":"NLNL: Negative Learning for Noisy Labels","created":"2019-08-19","cited_by_count":151},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150},{"id":"2007.12107","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","created":"2020-07-23","cited_by_count":142},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2007.09384","title":"Multi-Scale Positive Sample Refinement for Few-Shot Object Detection","created":"2020-07-18","cited_by_count":116},{"id":"2105.09491","title":"Generalized Few-Shot Object Detection without Forgetting","created":"2021-05-20","cited_by_count":88},{"id":"2103.05327","title":"BERTese: Learning to Speak to BERT","created":"2021-03-09","cited_by_count":82},{"id":"2103.04612","title":"Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection","created":"2021-03-08","cited_by_count":80},{"id":"2103.01903","title":"Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection","created":"2021-03-02","cited_by_count":79},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"1911.12529","title":"One-Shot Object Detection with Co-Attention and Co-Excitation","created":"2019-11-28","cited_by_count":67},{"id":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","cited_by_count":52},{"id":"2305.18980","title":"Multi-modal Queried Object Detection in the Wild","created":"2023-05-30","cited_by_count":47},{"id":"1907.07844","title":"Growing a Brain: Fine-Tuning by Increasing Model Capacity","created":"2019-07-18","cited_by_count":43},{"id":"2103.01077","title":"Universal-Prototype Enhancing for Few-Shot Object Detection","created":"2021-03-01","cited_by_count":43},{"id":"2211.08691","title":"Towards Long-Tailed 3D Detection","created":"2022-11-16","cited_by_count":40},{"id":"2112.11699","title":"Few-Shot Object Detection: A Comprehensive Survey","created":"2021-12-22","cited_by_count":29},{"id":"2303.09674","title":"DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection","created":"2023-03-16","cited_by_count":21},{"id":"2304.05096","title":"Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection","created":"2023-04-11","cited_by_count":21},{"id":"2310.09929","title":"Prompting Scientific Names for Zero-Shot Species Recognition","created":"2023-10-15","cited_by_count":14},{"id":"2210.04993","title":"Continual Learning with Evolving Class Ontologies","created":"2022-10-10","cited_by_count":13},{"id":"2209.13777","title":"An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning","created":"2022-09-28","cited_by_count":10},{"id":"2312.10986","title":"Long-Tailed 3D Detection via Multi-Modal Fusion","created":"2023-12-18","cited_by_count":10},{"id":"2306.14035","title":"Thinking Like an Annotator: Generation of Dataset Labeling Instructions","created":"2023-06-24","cited_by_count":4}],"next_cursor":null}