Showing 1–20 of 59 results
/ Date/ Name
Feb 12, 2024Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised LearningApr 2, 2014Thoughts on a Recursive Classifier Graph: a Multiclass Network for Deep Object RecognitionDec 1, 2015Labeling the Features Not the Samples: Efficient Video Classification with Minimal SupervisionFeb 16, 2012Generalized Boundaries from Multiple Image InterpretationsNov 27, 2014Features in Concert: Discriminative Feature Selection meets Unsupervised ClusteringMay 26, 2016Aerial image geolocalization from recognition and matching of roads and intersectionsMay 18, 2016Dual Local-Global Contextual Pathways for Recognition in Aerial ImageryNov 20, 2015Stories in the Eye: Contextual Visual Interactions for Efficient Video to Language TranslationDec 28, 2025With Great Context Comes Great Prediction Power: Classifying Objects via Geo-Semantic Scene GraphsOct 7, 2019Learning Navigation by Visual Localization and Trajectory PredictionAug 21, 2023Multi-Task Hypergraphs for Semi-supervised Learning using Earth ObservationsMar 31, 2017Unsupervised learning from video to detect foreground objects in single imagesMay 23, 2017How hard can it be? Estimating the difficulty of visual search in an imageJul 7, 2025From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised ApproachOct 22, 2019Towards Automatic Annotation for Semantic Segmentation in Drone VideosSep 17, 2020Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural NetworksJul 27, 2020A regime switching on Covid19 analysis and prediction in RomaniaApr 16, 2021TEACHTEXT: CrossModal Generalized Distillation for Text-Video RetrievalJun 26, 2024"Vorbeşti Româneşte?" A Recipe to Train Powerful Romanian LLMs with English InstructionsAug 15, 2025Inside Knowledge: Graph-based Path Generation with Explainable Data Augmentation and Curriculum Learning for Visual Indoor Navigation