{"list":"other","total":85,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"1604.03169","title":"Using Deep Learning for Image-Based Plant Disease Detection","created":"2016-04-11","cited_by_count":219},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99},{"id":"1810.05726","title":"DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning","created":"2018-10-09","cited_by_count":69},{"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":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57},{"id":"2104.12137","title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","created":"2021-04-25","cited_by_count":56},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2005.02264","title":"LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery","created":"2020-05-05","cited_by_count":40},{"id":"2309.09067","title":"MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer","created":"2023-09-16","cited_by_count":29},{"id":"2106.12413","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","created":"2021-06-23","cited_by_count":28},{"id":"2410.08405","title":"AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning","created":"2024-10-10","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":"2105.01938","title":"Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset","created":"2021-05-05","cited_by_count":21},{"id":"1711.05458","title":"A Public Image Database for Benchmark of Plant Seedling Classification Algorithms","created":"2017-11-15","cited_by_count":20},{"id":"2004.11958","title":"The Plant Pathology 2020 challenge dataset to classify foliar disease of apples","created":"2020-04-24","cited_by_count":14},{"id":"2409.04038","title":"PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation","created":"2024-09-06","cited_by_count":14},{"id":"2410.01407","title":"AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment","created":"2024-10-02","cited_by_count":13},{"id":"2004.11848","title":"Deep learning for smart fish farming: applications, opportunities and challenges","created":"2020-04-06","cited_by_count":12},{"id":"2305.09418","title":"Leaf Only SAM: A Segment Anything Pipeline for Zero-Shot Automated Leaf Segmentation","created":"2023-05-16","cited_by_count":12},{"id":"2012.06712","title":"Internet of Underwater Things and Big Marine Data Analytics -- A Comprehensive Survey","created":"2020-12-12","cited_by_count":11},{"id":"2408.16176","title":"VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images","created":"2024-08-28","cited_by_count":10},{"id":"2005.07518","title":"Temperate Fish Detection and Classification: a Deep Learning based Approach","created":"2020-05-14","cited_by_count":8},{"id":"2410.05577","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","created":"2024-10-08","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":"2407.06298","title":"Multi-Label Plant Species Classification with Self-Supervised Vision Transformers","created":"2024-07-08","cited_by_count":7},{"id":"2502.01785","title":"AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis","created":"2025-02-03","cited_by_count":7},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6},{"id":"2305.10254","title":"SAM for Poultry Science","created":"2023-05-17","cited_by_count":6},{"id":"2406.17800","title":"Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Survey","created":"2024-06-20","cited_by_count":6},{"id":"2312.08764","title":"CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming","created":"2023-12-14","cited_by_count":5},{"id":"2401.05202","title":"Video-based automatic lameness detection of dairy cows using pose estimation and multiple locomotion traits","created":"2024-01-10","cited_by_count":5},{"id":"2501.05209","title":"MHAFF: Multi-Head Attention Feature Fusion of CNN and Transformer for Cattle Identification","created":"2025-01-09","cited_by_count":5},{"id":"2206.05394","title":"Applications of Deep Learning in Fish Habitat Monitoring: A Tutorial and Survey","created":"2022-06-11","cited_by_count":4},{"id":"2503.23422","title":"Improving underwater semantic segmentation with underwater image quality attention and muti-scale aggregation attention","created":"2025-03-30","cited_by_count":4},{"id":"2111.00801","title":"Livestock Monitoring with Transformer","created":"2021-11-01","cited_by_count":3},{"id":"2401.00814","title":"Agricultural 4.0 Leveraging on Technological Solutions: Study for Smart Farming Sector","created":"2024-01-01","cited_by_count":3},{"id":"2310.19830","title":"GalliformeSpectra: A Hen Breed Dataset","created":"2023-10-28","cited_by_count":2},{"id":"2309.02975","title":"FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching","created":"2023-09-06","cited_by_count":1},{"id":"2406.09711","title":"AnimalFormer: Multimodal Vision Framework for Behavior-based Precision Livestock Farming","created":"2024-06-14","cited_by_count":1},{"id":"2409.01148","title":"FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking","created":"2024-09-02","cited_by_count":1}],"next_cursor":null}