Larlus, D.[Diane]
Co Author Listing * AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching
* Assessing the aesthetic quality of photographs using generic image descriptors
* Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval
* Capturing the Geometry of Object Categories from Video Supervision
* Category Level Object Segmentation by Combining Bag-of-Words Models with Dirichlet Processes and Random Fields
* Combining appearance models and Markov Random Fields for category level object segmentation
* Combining Visible and Near-Infrared Cues for image Categorisation
* Concept Generalization in Visual Representation Learning
* Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning
* Data-Driven Detection of Prominent Objects
* Deep Image Retrieval: Learning Global Representations for Image Search
* End-to-End Learning of Deep Visual Representations for Image Retrieval
* Extracting Structures in Image Collections for Object Recognition
* Fake it Till You Make it: Learning Transferable Representations from Synthetic ImageNet Clones
* Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings
* Fisher vectors meet Neural Networks: A hybrid classification architecture
* Granularity-Aware Adaptation for Image Retrieval Over Multiple Tasks
* I Have Seen Enough: Transferring Parts Across Categories
* Latent Mixture Vocabularies for Object Categorization
* Latent mixture vocabularies for object categorization and segmentation
* Learning 3D Object Categories by Looking Around Them
* Learning Color Names for Real-World Applications
* Learning Color Names from Real-World Images
* Learning the Structure of Objects from Web Supervision
* Learning Visual Representations with Caption Annotations
* NeuralDiff: Segmenting 3D objects that move in egocentric videos
* On the Road to Online Adaptation for Semantic Image Segmentation
* Predicting an Object Location Using a Global Image Representation
* Probabilistic Embeddings for Cross-Modal Retrieval
* Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
* Semantic Image Segmentation Using Visible and Near-Infrared Channels
* Semi-convolutional Operators for Instance Segmentation
* SLACK: Stable Learning of Augmentations with Cold-Start and KL Regularization
* StacMR: Scene-Text Aware Cross-Modal Retrieval
* Unsupervised Meta-Domain Adaptation for Fashion Retrieval
* Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors
* What is a good evaluation measure for semantic segmentation?
Includes: Larlus, D.[Diane] Larlus, D.
37 for Larlus, D.