Computer Vision Lab
Computer Vision Lab
About
Members
Publications
Projects
Positions
Contact
Light
Dark
Automatic
Tomasz Trzciński
Principal Investigator
Latest
Towards More Realistic Membership Inference Attacks on Large Diffusion Models
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
BlendFields: Few-Shot Example-Driven Facial Modeling
Learning Data Representations with Joint Diffusion Models
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Selectively increasing the diversity of GAN-generated samples
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
CoNeRF: Controllable Neural Radiance Fields
Non-Gaussian Gaussian Processes for Few-Shot Regression
General hypernetwork framework for creating 3D point clouds
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
FetalNet: Multi-task deep learning framework for fetal ultrasound biometric measurements
On robustness of generative representations against catastrophic forgetting
Explaining Self-Supervised Image Representations with Visual Probing
MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
End-to-End Sinkhorn Autoencoder With Noise Generator
Machine Learning Methods for Preterm Birth Prediction: A Review
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning
Spontaneous Preterm Birth Prediction Using Convolutional Neural Networks
Adversarial autoencoders for compact representations of 3D point clouds
Understanding the robustness of deep neural network classifiers for breast cancer screening
Hypernetwork approach to generating point clouds
Plugin Networks for Inference under Partial Evidence
SuperNCN: Neighbourhood consensus network for robust outdoor scenes matching
Estimation of Preterm Birth Markers with U-Net Segmentation Network
Classifying and Visualizing Emotions with EmotionalDAN
Comixify: Transform video into a comics
DeepStyle: Multimodal Search Engine for Fashion and Interior Design
Random Binary Search Trees for approximate nearest neighbour search in binary spaces
Generative models for fast cluster simulations in the TPC for the ALICE experiment
Using Random Forest Classifier for particle identification in the ALICE Experiment
Understanding Multimodal Popularity Prediction of Social Media Videos With Self-Attention
BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
Siamese generative adversarial privatizer for biometric data
Estimating Achilles tendon healing progress with convolutional neural networks
Interest point detectors stability evaluation on ApolloScape dataset
SConE: Siamese Constellation Embedding Descriptor for Image Matching
I know how you feel: Emotion recognition with facial landmarks
Pay Attention to Virality: understanding popularity of social media videos with the attention mechanism
SocialML: machine learning for social media video creators
Deep Alignment Network: A convolutional neural network for robust face alignment
Predicting Popularity of Online Videos Using Support Vector Regression
Learning Image Descriptors with Boosting
Learning and Matching Binary Local Feature Descriptors
Receptive Fields Selection for Binary Feature Description
Boosting Binary Keypoint Descriptors
Learning Image Descriptors with the Boosting-Trick
Learning Image Descriptors with Boosting
Efficient Discriminative Projections for Compact Binary Descriptors
BRIEF: Computing a Local Binary Descriptor Very Fast
Enhancing global positioning by image recognition
EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale
Cite
×