{"list":"other","total":131,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268},{"id":"2007.09062","title":"Multi-scale Interactive Network for Salient Object Detection","created":"2020-07-17","cited_by_count":212},{"id":"2412.03555","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","created":"2024-12-04","cited_by_count":207},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"1503.08677","title":"Label-Embedding for Image Classification","created":"2015-03-30","cited_by_count":165},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"2203.16513","title":"PromptDet: Towards Open-vocabulary Detection using Uncurated Images","created":"2022-03-30","cited_by_count":133},{"id":"2406.11832","title":"Unveiling Encoder-Free Vision-Language Models","created":"2024-06-17","cited_by_count":94},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84},{"id":"2406.04334","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","created":"2024-06-06","cited_by_count":75},{"id":"2008.00230","title":"RGB-D Salient Object Detection: A Survey","created":"2020-08-01","cited_by_count":73},{"id":"2108.08162","title":"Specificity-preserving RGB-D Saliency Detection","created":"2021-08-18","cited_by_count":70},{"id":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70},{"id":"2207.08455","title":"Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","created":"2022-07-18","cited_by_count":67}],"next_cursor":"100"}