{"list":"other","total":66,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"1903.09766","title":"Fast Underwater Image Enhancement for Improved Visual Perception","created":"2019-03-23","cited_by_count":183},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116},{"id":"1702.07392","title":"WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images","created":"2017-02-23","cited_by_count":112},{"id":"2111.11843","title":"U-shape Transformer for Underwater Image Enhancement","created":"2021-11-23","cited_by_count":112},{"id":"2004.01241","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","created":"2020-04-02","cited_by_count":95},{"id":"2202.13065","title":"An End-to-End Transformer Model for Crowd Localization","created":"2022-02-26","cited_by_count":74},{"id":"2303.09101","title":"Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank","created":"2023-03-16","cited_by_count":71},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60},{"id":"1911.07933","title":"Dont Even Look Once: Synthesizing Features for Zero-Shot Detection","created":"2019-11-18","cited_by_count":58},{"id":"2008.12603","title":"A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis","created":"2020-08-28","cited_by_count":57},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54},{"id":"2307.11661","title":"Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts","created":"2023-07-21","cited_by_count":50},{"id":"2007.08097","title":"TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris","created":"2020-07-16","cited_by_count":45},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36},{"id":"2108.01971","title":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection","created":"2021-08-04","cited_by_count":34},{"id":"2109.14646","title":"FathomNet: A global image database for enabling artificial intelligence in the ocean","created":"2021-09-29","cited_by_count":25},{"id":"1804.01079","title":"Robotic Detection of Marine Litter Using Deep Visual Detection Models","created":"2018-04-03","cited_by_count":24},{"id":"2310.13596","title":"MarineGPT: Unlocking Secrets of Ocean to the Public","created":"2023-10-20","cited_by_count":23},{"id":"2404.04996","title":"Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM","created":"2024-04-07","cited_by_count":23},{"id":"2011.06252","title":"SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots","created":"2020-11-12","cited_by_count":20},{"id":"2003.01446","title":"A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing","created":"2020-03-03","cited_by_count":16},{"id":"2302.07344","title":"Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles","created":"2023-02-14","cited_by_count":16},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15},{"id":"2203.06951","title":"Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey","created":"2022-03-14","cited_by_count":14},{"id":"2304.11677","title":"RGB-D Indiscernible Object Counting in Underwater Scenes","created":"2023-04-23","cited_by_count":9},{"id":"2310.01946","title":"CoralVOS: Dataset and Benchmark for Coral Video Segmentation","created":"2023-10-03","cited_by_count":9},{"id":"2401.02147","title":"Exploring Boundary of GPT-4V on Marine Analysis: A Preliminary Case Study","created":"2024-01-04","cited_by_count":9},{"id":"2202.09942","title":"Multiscale Crowd Counting and Localization By Multitask Point Supervision","created":"2022-02-21","cited_by_count":8},{"id":"2106.09178","title":"The Fishnet Open Images Database: A Dataset for Fish Detection and Fine-Grained Categorization in Fisheries","created":"2021-06-16","cited_by_count":7},{"id":"2301.01482","title":"Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles","created":"2023-01-04","cited_by_count":7},{"id":"2212.04132","title":"Combining Photogrammetric Computer Vision and Semantic Segmentation for Fine-grained Understanding of Coral Reef Growth under Climate Change","created":"2022-12-08","cited_by_count":5},{"id":"2310.01931","title":"MarineDet: Towards Open-Marine Object Detection","created":"2023-10-03","cited_by_count":5},{"id":"2206.05390","title":"Overcoming Annotation Bottlenecks in Underwater Fish Segmentation: A Robust Self-Supervised Learning Approach","created":"2022-06-11","cited_by_count":2},{"id":"2403.05930","title":"Deep learning for multi-label classification of coral conditions in the Indo-Pacific via underwater photogrammetry","created":"2024-03-09","cited_by_count":2},{"id":"2403.03461","title":"A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video","created":"2024-03-06","cited_by_count":1}],"next_cursor":null}