{"total":167,"rows":[{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265,"area":null},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196,"area":null},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178,"area":null},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83,"area":null},{"id":"2110.09936","title":"NeuralDiff: Segmenting 3D objects that move in egocentric videos","created":"2021-10-19","cited_by_count":57,"area":null},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2303.12930","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","created":"2023-03-22","cited_by_count":46,"area":null},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45,"area":null},{"id":"2107.04259","title":"Unity Perception: Generate Synthetic Data for Computer Vision","created":"2021-07-09","cited_by_count":43,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2103.16481","title":"Read and Attend: Temporal Localisation in Sign Language Videos","created":"2021-03-30","cited_by_count":34,"area":null},{"id":"2107.00396","title":"MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis","created":"2021-07-01","cited_by_count":32,"area":null},{"id":"2105.02351","title":"Content4All Open Research Sign Language Translation Datasets","created":"2021-05-05","cited_by_count":30,"area":null},{"id":"2111.03635","title":"BBC-Oxford British Sign Language Dataset","created":"2021-11-05","cited_by_count":28,"area":null},{"id":"2105.02359","title":"MODS -- A USV-oriented object detection and obstacle segmentation benchmark","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2105.02877","title":"Aligning Subtitles in Sign Language Videos","created":"2021-05-06","cited_by_count":26,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2401.10224","title":"The Manga Whisperer: Automatically Generating Transcriptions for Comics","created":"2024-01-18","cited_by_count":21,"area":null},{"id":"2104.08885","title":"A survey of image labelling for computer vision applications","created":"2021-04-18","cited_by_count":18,"area":null},{"id":"2206.06657","title":"The Open Kidney Ultrasound Data Set","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2103.14098","title":"Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles","created":"2021-03-25","cited_by_count":16,"area":null},{"id":"2309.16782","title":"Surgical Tattoos in Infrared: A Dataset for Quantifying Tissue Tracking and Mapping","created":"2023-09-28","cited_by_count":15,"area":null},{"id":"2405.10266","title":"A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision","created":"2024-05-16","cited_by_count":15,"area":null},{"id":"2107.05255","title":"AutoFB: Automating Fetal Biometry Estimation from Standard Ultrasound Planes","created":"2021-07-12","cited_by_count":14,"area":null},{"id":"2310.13398","title":"OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data","created":"2023-10-20","cited_by_count":14,"area":null},{"id":"2104.04518","title":"Chest X-Ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findings","created":"2021-04-09","cited_by_count":13,"area":null},{"id":"2205.04152","title":"Scaling up sign spotting through sign language dictionaries","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2506.15368","title":"Open-World Object Counting in Videos","created":"2025-06-18","cited_by_count":11,"area":null},{"id":"2211.08954","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","created":"2022-11-16","cited_by_count":10,"area":null},{"id":"2104.14964","title":"Deep learning with self-supervision and uncertainty regularization to count fish in underwater images","created":"2021-04-30","cited_by_count":9,"area":null},{"id":"2107.00700","title":"Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2110.08935","title":"InfAnFace: Bridging the infant-adult domain gap in facial landmark estimation in the wild","created":"2021-10-17","cited_by_count":9,"area":null},{"id":"2203.14227","title":"OneLabeler: A Flexible System for Building Data Labeling Tools","created":"2022-03-27","cited_by_count":9,"area":null},{"id":"2206.14678","title":"BiometryNet: Landmark-based Fetal Biometry Estimation from Standard Ultrasound Planes","created":"2022-06-29","cited_by_count":9,"area":null},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2203.09589","title":"Video-based Formative and Summative Assessment of Surgical Tasks using Deep Learning","created":"2022-03-17","cited_by_count":8,"area":null},{"id":"2401.12039","title":"Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2410.11860","title":"Comparing Zealous and Restrained AI Recommendations in a Real-World Human-AI Collaboration Task","created":"2024-10-06","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2212.13924","title":"Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches","created":"2022-12-12","cited_by_count":7,"area":null},{"id":"2303.04884","title":"O2RNet: Occluder-Occludee Relational Network for Robust Apple Detection in Clustered Orchard Environments","created":"2023-03-08","cited_by_count":7,"area":null},{"id":"2105.00374","title":"Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes","created":"2021-05-02","cited_by_count":6,"area":null},{"id":"2106.15828","title":"Semantic Segmentation of Periocular Near-Infra-Red Eye Images Under Alcohol Effects","created":"2021-06-30","cited_by_count":6,"area":null},{"id":"2205.13583","title":"Harnessing Artificial Intelligence to Infer Novel Spatial Biomarkers for the Diagnosis of Eosinophilic Esophagitis","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2506.08220","title":"Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2508.21675","title":"Is this chart lying to me? Automating the detection of misleading visualizations","created":"2025-08-29","cited_by_count":6,"area":null},{"id":"2103.04019","title":"Indoor Future Person Localization from an Egocentric Wearable Camera","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2105.01456","title":"Computer vision for liquid samples in hospitals and medical labs using hierarchical image segmentation and relations prediction","created":"2021-05-04","cited_by_count":5,"area":null},{"id":"2109.12474","title":"EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography","created":"2021-09-26","cited_by_count":5,"area":null},{"id":"2412.21205","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2508.18425","title":"LPLC: A Dataset for License Plate Legibility Classification","created":"2025-08-25","cited_by_count":5,"area":null},{"id":"2111.11397","title":"Lebanon Solar Rooftop Potential Assessment using Buildings Segmentation from Aerial Images","created":"2021-11-22","cited_by_count":4,"area":null},{"id":"2204.02842","title":"Open-Source Tools for Behavioral Video Analysis: Setup, Methods, and Development","created":"2022-04-06","cited_by_count":4,"area":null},{"id":"2304.10439","title":"A Study on Reproducibility and Replicability of Table Structure Recognition Methods","created":"2023-04-20","cited_by_count":4,"area":null},{"id":"2307.14243","title":"Fluorescent Neuronal Cells v2: Multi-Task, Multi-Format Annotations for Deep Learning in Microscopy","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2311.04098","title":"DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2407.00267","title":"Learning a Clinically-Relevant Concept Bottleneck for Lesion Detection in Breast Ultrasound","created":"2024-06-29","cited_by_count":4,"area":null},{"id":"2409.16143","title":"Seeing Faces in Things: A Model and Dataset for Pareidolia","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2507.18374","title":"Towards Effective Human-in-the-Loop Assistive AI Agents","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2104.05125","title":"Shuffler: A Large Scale Data Management Tool for ML in Computer Vision","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2109.05078","title":"A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos","created":"2021-09-10","cited_by_count":3,"area":null},{"id":"2111.12764","title":"Towards an Efficient Semantic Segmentation Method of ID Cards for Verification Systems","created":"2021-11-24","cited_by_count":3,"area":null},{"id":"2302.09569","title":"SEMI-PointRend: Improved Semiconductor Wafer Defect Classification and Segmentation as Rendering","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2303.16867","title":"A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2508.14557","title":"Improving OCR using internal document redundancy","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2510.01362","title":"EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2512.16710","title":"A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2101.07606","title":"Deep Learning Models for Calculation of Cardiothoracic Ratio from Chest Radiographs for Assisted Diagnosis of Cardiomegaly","created":"2021-01-19","cited_by_count":2,"area":null},{"id":"2102.01059","title":"Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients","created":"2021-02-01","cited_by_count":2,"area":null},{"id":"2106.15320","title":"ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations","created":"2021-06-23","cited_by_count":2,"area":null},{"id":"2108.08109","title":"Image Collation: Matching illustrations in manuscripts","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2112.06809","title":"Persistent Animal Identification Leveraging Non-Visual Markers","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2207.06823","title":"DEXTER: An end-to-end system to extract table contents from electronic medical health documents","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2210.14287","title":"Combined Data and Deep Learning Model Uncertainties: An Application to the Measurement of Solid Fuel Regression Rate","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2307.13110","title":"Automatic Infant Respiration Estimation from Video: A Deep Flow-based Algorithm and a Novel Public Benchmark","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2309.17058","title":"Imagery Dataset for Condition Monitoring of Synthetic Fibre Ropes","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2403.10916","title":"FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation","created":"2024-03-16","cited_by_count":2,"area":null},{"id":"2410.03359","title":"An Enhanced Harmonic Densely Connected Hybrid Transformer Network Architecture for Chronic Wound Segmentation Utilising Multi-Colour Space Tensor Merging","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2410.06781","title":"Transesophageal Echocardiography Generation using Anatomical Models","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2507.17651","title":"CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts","created":"2025-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2509.04180","title":"VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2512.08094","title":"Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2605.01666","title":"IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2104.01268","title":"Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy","created":"2021-04-02","cited_by_count":1,"area":null},{"id":"2111.15581","title":"Automated Damage Inspection of Power Transmission Towers from UAV Images","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2204.14224","title":"Investigation of Neural Network Methods for Reconstruction and Classification of Texture Images Under Conditions of Incomplete Information","created":"2022-04-21","cited_by_count":1,"area":null},{"id":"2205.11563","title":"Accelerating the creation of instance segmentation training sets through bounding box annotation","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2207.04021","title":"ASL-Homework-RGBD Dataset: An annotated dataset of 45 fluent and non-fluent signers performing American Sign Language homeworks","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2208.09657","title":"Is Medieval Distant Viewing Possible? : Extending and Enriching Annotation of Legacy Image Collections using Visual Analytics","created":"2022-08-20","cited_by_count":1,"area":null},{"id":"2208.14295","title":"PanorAMS: Automatic Annotation for Detecting Objects in Urban Context","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2210.07436","title":"Smart Headset, Computer Vision and Machine Learning for Efficient Prawn Farm Management","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2304.05339","title":"Deep-learning Assisted Detection and Quantification of (oo)cysts of Giardia and Cryptosporidium on Smartphone Microscopy Images","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2307.01582","title":"IAdet: Simplest human-in-the-loop object detection","created":"2023-07-04","cited_by_count":1,"area":null},{"id":"2401.16937","title":"Segmentation and Characterization of Macerated Fibers and Vessels Using Deep Learning","created":"2024-01-30","cited_by_count":1,"area":null}],"next_cursor":"100"}