{"list":"other","total":65,"rows":[{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1909.04939","title":"InceptionTime: Finding AlexNet for Time Series Classification","created":"2019-09-11","cited_by_count":387},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"1608.08242","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","created":"2016-08-29","cited_by_count":199},{"id":"1611.07450","title":"Grad-CAM: Why did you say that?","created":"2016-11-22","cited_by_count":161},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"2112.06725","title":"Computational bioacoustics with deep learning: a review and roadmap","created":"2021-12-13","cited_by_count":78},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"1911.07451","title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","created":"2019-11-18","cited_by_count":49},{"id":"1909.11229","title":"Pretraining boosts out-of-domain robustness for pose estimation","created":"2019-09-24","cited_by_count":47},{"id":"2012.02952","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","created":"2020-12-05","cited_by_count":47},{"id":"1805.09707","title":"Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation","created":"2018-05-24","cited_by_count":44},{"id":"1909.13868","title":"Deep learning tools for the measurement of animal behavior in neuroscience","created":"2019-09-30","cited_by_count":44},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2306.00576","title":"MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding","created":"2023-06-01","cited_by_count":36},{"id":"1705.00389","title":"Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation","created":"2017-04-30","cited_by_count":35},{"id":"1704.00389","title":"Hidden Two-Stream Convolutional Networks for Action Recognition","created":"2017-04-02","cited_by_count":24},{"id":"1310.4249","title":"Mapping the stereotyped behaviour of freely-moving fruit flies","created":"2013-10-16","cited_by_count":21},{"id":"2104.08029","title":"T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information","created":"2021-04-16","cited_by_count":15},{"id":"1504.07159","title":"Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation","created":"2015-04-27","cited_by_count":14},{"id":"1811.02275","title":"NIPS4Bplus: a richly annotated birdsong audio dataset","created":"2018-11-06","cited_by_count":14},{"id":"2305.13210","title":"Learning to detect an animal sound from five examples","created":"2023-05-22","cited_by_count":14},{"id":"2303.15023","title":"ScarceNet: Animal Pose Estimation with Scarce Annotations","created":"2023-03-27","cited_by_count":13},{"id":"2112.01987","title":"Leaving Flatland: Advances in 3D behavioral measurement","created":"2021-12-03","cited_by_count":10},{"id":"2206.12078","title":"Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data","created":"2022-06-24","cited_by_count":10},{"id":"2111.12295","title":"Animal behavior classification via deep learning on embedded systems","created":"2021-11-24","cited_by_count":9},{"id":"1707.02439","title":"Self Adversarial Training for Human Pose Estimation","created":"2017-07-08","cited_by_count":8},{"id":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8},{"id":"2212.00266","title":"Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary","created":"2022-12-01","cited_by_count":7},{"id":"2309.08971","title":"Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection","created":"2023-09-16","cited_by_count":7},{"id":"1906.02831","title":"Detection and Tracking of Multiple Mice Using Part Proposal Networks","created":"2019-06-06","cited_by_count":5},{"id":"2011.02451","title":"Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model","created":"2020-11-04","cited_by_count":5},{"id":"2002.03267","title":"Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning","created":"2020-02-09","cited_by_count":4},{"id":"2101.10445","title":"Dairy Cow rumination detection: A deep learning approach","created":"2021-01-07","cited_by_count":4},{"id":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","cited_by_count":4},{"id":"1911.00417","title":"Long-distance Detection of Bioacoustic Events with Per-channel Energy Normalization","created":"2019-11-01","cited_by_count":3},{"id":"2002.09821","title":"A Multi-view CNN-based Acoustic Classification System for Automatic Animal Species Identification","created":"2020-02-23","cited_by_count":3},{"id":"2103.07276","title":"Modelling Animal Biodiversity Using Acoustic Monitoring and Deep Learning","created":"2021-03-12","cited_by_count":3},{"id":"2011.14070","title":"Movement Tracks for the Automatic Detection of Fish Behavior in Videos","created":"2020-11-28","cited_by_count":2},{"id":"2204.07072","title":"SemiMultiPose: A Semi-supervised Multi-animal Pose Estimation Framework","created":"2022-04-14","cited_by_count":2},{"id":"2108.09394","title":"Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarms","created":"2021-08-20","cited_by_count":1},{"id":"2111.08259","title":"Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning","created":"2021-11-16","cited_by_count":1}],"next_cursor":null}