{"list":"other","total":79,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"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":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"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":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"1803.11365","title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","created":"2018-03-30","cited_by_count":218},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"1812.05418","title":"DLOW: Domain Flow for Adaptation and Generalization","created":"2018-12-13","cited_by_count":177},{"id":"2008.12197","title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","created":"2020-08-27","cited_by_count":177},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","cited_by_count":164},{"id":"2103.05346","title":"ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection","created":"2021-03-09","cited_by_count":159},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2110.03374","title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","created":"2021-10-07","cited_by_count":152},{"id":"1910.13049","title":"Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation","created":"2019-10-29","cited_by_count":151},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"id":"2103.03571","title":"Cycle Self-Training for Domain Adaptation","created":"2021-03-05","cited_by_count":120},{"id":"1909.00169","title":"Imbalance Problems in Object Detection: A Review","created":"2019-08-31","cited_by_count":118},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"id":"2012.08548","title":"Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection","created":"2020-12-15","cited_by_count":99},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"1909.00597","title":"Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection","created":"2019-09-02","cited_by_count":83},{"id":"2103.16765","title":"Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation","created":"2021-03-31","cited_by_count":83},{"id":"2104.13613","title":"Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-04-28","cited_by_count":80},{"id":"2012.05400","title":"A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data","created":"2020-12-10","cited_by_count":79},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"2007.02424","title":"Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation","created":"2020-07-05","cited_by_count":70},{"id":"2006.10032","title":"Self-training Avoids Using Spurious Features Under Domain Shift","created":"2020-06-17","cited_by_count":69},{"id":"2106.02885","title":"Category Contrast for Unsupervised Domain Adaptation in Visual Tasks","created":"2021-06-05","cited_by_count":65},{"id":"2303.05892","title":"Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection","created":"2023-03-10","cited_by_count":63},{"id":"2102.01066","title":"Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details","created":"2021-02-01","cited_by_count":57},{"id":"2203.15793","title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":55},{"id":"2211.06612","title":"Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning","created":"2022-11-12","cited_by_count":53},{"id":"2108.07507","title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","created":"2021-08-17","cited_by_count":51},{"id":"2303.17132","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","created":"2023-03-30","cited_by_count":50},{"id":"2106.02874","title":"RDA: Robust Domain Adaptation via Fourier Adversarial Attacking","created":"2021-06-05","cited_by_count":48},{"id":"2301.13381","title":"When Source-Free Domain Adaptation Meets Learning with Noisy Labels","created":"2023-01-31","cited_by_count":47},{"id":"2008.05676","title":"Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation","created":"2020-08-13","cited_by_count":41},{"id":"2103.02584","title":"Cross-View Regularization for Domain Adaptive Panoptic Segmentation","created":"2021-03-03","cited_by_count":41},{"id":"2211.07609","title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","created":"2022-11-14","cited_by_count":41},{"id":"2204.02811","title":"BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation","created":"2022-04-06","cited_by_count":39},{"id":"2207.08485","title":"Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation","created":"2022-07-18","cited_by_count":37},{"id":"1607.07295","title":"Learning Aligned Cross-Modal Representations from Weakly Aligned Data","created":"2016-07-25","cited_by_count":34},{"id":"2108.09169","title":"Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds","created":"2021-08-20","cited_by_count":31},{"id":"2008.09150","title":"VisualSem: A High-quality Knowledge Graph for Vision and Language","created":"2020-08-20","cited_by_count":30},{"id":"2103.17084","title":"DA-DETR: Domain Adaptive Detection Transformer with Information Fusion","created":"2021-03-31","cited_by_count":24},{"id":"2311.13930","title":"Periodically Exchange Teacher-Student for Source-Free Object Detection","created":"2023-11-23","cited_by_count":24},{"id":"2105.14370","title":"BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China","created":"2021-05-29","cited_by_count":19},{"id":"1908.05217","title":"Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes","created":"2019-08-14","cited_by_count":17},{"id":"2003.12383","title":"End-to-End Entity Classification on Multimodal Knowledge Graphs","created":"2020-03-25","cited_by_count":12},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12},{"id":"2303.14361","title":"Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation","created":"2023-03-25","cited_by_count":10},{"id":"2112.11366","title":"Contrastive Object Detection Using Knowledge Graph Embeddings","created":"2021-12-21","cited_by_count":6},{"id":"2208.12853","title":"Domain Adaptation with Adversarial Training on Penultimate Activations","created":"2022-08-26","cited_by_count":5}],"next_cursor":null}