{"list":"other","total":62,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71},{"id":"2401.02361","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","created":"2024-01-04","cited_by_count":65},{"id":"1811.08965","title":"Low-Resolution Face Recognition","created":"2018-11-21","cited_by_count":64},{"id":"1812.04098","title":"The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery","created":"2018-12-10","cited_by_count":58},{"id":"2401.02460","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","created":"2024-01-04","cited_by_count":54},{"id":"2107.11627","title":"Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform","created":"2021-07-24","cited_by_count":50},{"id":"2404.09216","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","created":"2024-04-14","cited_by_count":48},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46},{"id":"2008.05402","title":"DAWN: Vehicle Detection in Adverse Weather Nature Dataset","created":"2020-08-12","cited_by_count":41},{"id":"2503.12329","title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era","created":"2025-03-16","cited_by_count":41},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36},{"id":"1805.11529","title":"On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques","created":"2018-05-29","cited_by_count":34},{"id":"2307.12730","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","created":"2023-07-24","cited_by_count":34},{"id":"2311.17518","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding","created":"2023-11-29","cited_by_count":29},{"id":"2308.06412","title":"Taming Self-Training for Open-Vocabulary Object Detection","created":"2023-08-11","cited_by_count":25},{"id":"2204.03934","title":"Does Robustness on ImageNet Transfer to Downstream Tasks?","created":"2022-04-08","cited_by_count":20},{"id":"2312.15043","title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection","created":"2023-12-22","cited_by_count":20},{"id":"2211.04656","title":"MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification","created":"2022-11-09","cited_by_count":16},{"id":"2304.10066","title":"Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation","created":"2023-04-20","cited_by_count":16},{"id":"2312.08875","title":"What, How, and When Should Object Detectors Update in Continually Changing Test Domains?","created":"2023-12-12","cited_by_count":15},{"id":"2403.01680","title":"Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection","created":"2024-03-04","cited_by_count":15},{"id":"2306.09278","title":"Robustness Analysis on Foundational Segmentation Models","created":"2023-06-15","cited_by_count":13},{"id":"2503.15892","title":"UMIT: Unifying Medical Imaging Tasks via Vision-Language Models","created":"2025-03-20","cited_by_count":12},{"id":"2412.16583","title":"REO-VLM: Transforming VLM to Meet Regression Challenges in Earth Observation","created":"2024-12-21","cited_by_count":9},{"id":"2507.07230","title":"Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement","created":"2025-07-09","cited_by_count":6},{"id":"2505.12580","title":"Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReID","created":"2025-05-19","cited_by_count":5},{"id":"2510.22127","title":"Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions","created":"2025-10-25","cited_by_count":5},{"id":"2405.14874","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","created":"2024-04-01","cited_by_count":4},{"id":"2502.03950","title":"LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models","created":"2025-02-06","cited_by_count":3},{"id":"2302.05621","title":"Dive into the Resolution Augmentations and Metrics in Low Resolution Face Recognition: A Plain yet Effective New Baseline","created":"2023-02-11","cited_by_count":2},{"id":"2508.10171","title":"SynSpill: Improved Industrial Spill Detection With Synthetic Data","created":"2025-08-13","cited_by_count":1}],"next_cursor":null}