Events

Vision Foundation Model-Driven Semantic Segmentation under Limited Supervision

Finding Patterns in Multimodal Data

Audio-Visual Speaker Localization and Tracking

Generative Models for High Dynamic Range Panorama Outpainting from a Single-View Image

Discrete Representation Learning for Retrieval and Generation

Data Driven Detection of Developmental Disorders in Dogs

Sensing with multimode optical fibres: A machine learning perspective

Style Analysis of Image Diffusion LoRAs in Weight Space

Sign Language Representation Learning in Low-Resource Settings: From Recognition to Translation

Leveraging Multimodality for Controllable Image Generation

Unsupervised Anomaly Detection in Sensor-based Remote Healthcare Monitoring

When Physics Meets AI: Modelling High-Density Crowds In Videos with Deep Learning

Creative Vector Drawing Generation

Machine Learning for Depression Detection and Emotion Recognition

Audio Source Separation and Creation Empowered by Natural Language Intelligence

Structured Generative Models for 3D Vision

Multimodal Representation Learning and Image Interpretation with Applications in the Medical Domain

Intelligent Perception and Mapping: Machine Learning for Mobile Robotics

Visual Content Provenance and Change Summarisation

Unveiling the Potential of Synthetic Data for Animal Pose Estimation

Distributed Audio-Visual Multi-Target Tracking

Co-creation of Meaning in Sign Language Interaction: Can AI technologies capture not only movement features but also meanings?

On the Interpretability of Reinforcement Learning

Sound to Text: Automated Audio Captioning using Deep Learning

Fine-Grained Vision-Language Learning

Computational Techniques for Digital Mapping and Correction of Metamorphopsia

Improving 3D Scene Reconstruction: from Per-Scene to Generalizable

Attribute-Aware Face Recognition

Shaping the future of gaming with HUMAIN’s AI-generated digital characters

Reasonable Suspicion of Misbehaviour of Aerial Platforms

Audio-Visual Detection and Localisation of Speech and Sound Events

Learning Natural Vector Sketch Models

Shape and Appearance Super-resolution for 3D Humans

AI hardware and real-world AI

Structured Representations for Scene Understanding

Towards 3D VR Sketch

Learned representations of artistic style for image retrieval, description and stylization

Diffusing light and analogies

Fine-grained video understanding and generation

Self-supervised 3D reconstruction in general complex dynamic scenes

Vehicle state estimation for autonomous driving

Machine learning for video coding and quality assessment

Machine learning methods to analyse dynamic and incomplete data

Person re-identification using vision and language

Sound in 6 degrees-of-freedom VR/AR

Multi-task autonomy for robotics

Work inspiration trip - CVSSP and Sensus Futuris

AI UK 2023

Computer vision applications: challenges with domain adaptation, active learning and open set classification

Validation of texture analysis

Pose estimation and novel view synthesis of humans

Active Sampling for Computer Vision

Defocus Modelling for 3D Reconstruction and Rendering

Deep Domain Adaptation for Visual Recognition with Unlabeled Data

Towards Practicality of Sketch-Based Visual Understanding

Parametric Human Modelling for Shape and Texture Representation from Video

Integrating Structure and Causality into Machine Learning

Deep Learning with Limited Annotated Data

Automatic Sign Language Production

The Challenges of Anomaly Detection

Sketching and Streaming based Subspace Clustering for Large-scale Data Classification

Cognitive tools for visual communication

Sketching Fast and Slow: Cognition, Heuristics, and the Challenge of Intuitive Workflows

Multi-View Multiple People Detection, Labelling and Tracking

Neural Reconstruction and Rendering of 3D Humans from Video

3D scene reconstruction using RGB-D cameras and AI: from static to dynamic scenes

QoE Aware VVC Based Omnidirectional and Screen Content Coding

Temporal Self-Supervision for Unsupervised Video Representation Learning

Face presentation attack detection

Combined Learning Models for Analysing Dynamic Time-series Data in Healthcare

Learning Generic Deep Feature Representations

Continuous learning of inverse problems with applications to structure from motion

Spherical based human tracking and 3D pose estimation for immersive entertainment production

Interpreting drawings for 3D design - a semi-discrete optimization problem

Robust learning-based methods for shape correspondence

Machine learning for robotic grasping

Delving deep into the sketch and photo relation

Machine learning applied to video monitoring of sleep

Methods for autonomous calibration, mapping and navigation of vehicles

Adaptation and generalization across domains in visual recognition with deep neural networks

Motion capture and animation research at CAMERA: From digital humans to digital dogs

Artificial emotional intelligence for well-being

Deep generative models for images and 3D shapes (183689)

3D indoor semantic scene completion from a single point-of-view

An affordable real-time volumetric capture system

Rapid 3D avatar creation using commodity depth cameras

Weakly supervised crowd counting and conditional rotation prediction based semi-supervised learning

AI@Surrey Summer School 2019

Inverse graphics for 3D object modeling and reconstruction: From face to generic objects

Can machines think?

Voice security in the conversational economy

Scientific and academic research: A survival guide

Deep learning based speech signal processing

Faculty Research Focus (FRF) for CVSSP and Maths

Artificial intelligence for automating space data processing

Blind source separation based on unsupervised and semi-supervised learning for multichannel audio data

14th International Conference on Latent Variable Analysis and Signal Separation

Audio Day 2018

G3 Futures Annual Conference

What is research software engineering?

Particle filtering with invertible particle flow

Reconstructing and perceiving humans in motion