Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs

CVPR 2024

Learning to Count without Annotations

CVPR 2024

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

CVPR 2024

Any-Shift Prompting for Generalization over Distributions

CVPR 2024

VeRA: Vector-based Random Matrix Adaptation

ICLR 2024

Skip-Attention: Improving Vision Transformers by Paying Less Attention

ICLR 2024

R-MAE: Regions Meet Masked Autoencoders

ICLR 2024

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

ICLR 2024

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

ICLR 2024

Protect Your Score: Contact-tracing With Differential Privacy Guarantees

AAAI 2024

Parameter-free Neural Field-based Optimal Design of Nonuniform Transmission Lines

ICECS 2023

Visual Perception in the Human Brain: How the Brain Perceives and Understands Real-World Scenes

Oxford Research Encyclopedia of Neuroscience 2023

Infinite Class Mixup

BMVC 2023

Rotating Features for Object Discovery

NeurIPS 2023

ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion

NeurIPS 2023

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

NeurIPS 2023

Modulated Neural ODEs

NeurIPS 2023

Learning Unseen Modality Interaction

NeurIPS 2023

Latent Field Discovery in Interacting Dynamical Systems with Neural Fields

NeurIPS 2023

HypLL: The Hyperbolic Learning Library

ACM MM 2023

Query by Activity Video in the Wild

ICIP 2023

Towards Open-Vocabulary Video Instance Segmentation

ICCV 2023

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

ICCV 2023

Self-Ordering Point Clouds

ICCV 2023

Poincaré ResNet

ICCV 2023

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

ICCV 2023

Detecting Objects with Context-Likelihood Graphs and Graph Refinement

ICCV 2023

Bayesian Prompt Learning for Image-Language Model Generalization

ICCV 2023

Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization

ICCV 2023

Precise Spatial Tuning of Visually Driven Alpha Oscillations in Human Visual Cortex

ELife 2023

Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation

ICMR 2023

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

CoLLAs 2023

Unlocking Slot Attention by Changing Optimal Transport Costs

ICML 2023

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

ICML 2023

Graph Switching Dynamical Systems

ICML 2023

No time to waste: practical statistical contact tracing with few low-bit messages

AAAI 2023

Test of Time: Instilling Video-Language Models with a Sense of Time

CVPR 2023

SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail

CVPR 2023

Self-Guided Diffusion Models

CVPR 2023

BISCUIT: Causal Representation Learning from Binary Interactions

UAI 2023

Spatio-temporal physics-informed learning: A novel approach to CT perfusion analysis in acute ischemic stroke

MIA 2023

PerfU-Net: Baseline infarct estimation from CT perfusion source data for acute ischemic stroke

MIA 2023

Scalable Subset Sampling with Neural Conditional Poisson Networks

ICLR 2023

Robust Scheduling with GFlowNets

ICLR 2023

Modelling Long Range Dependencies in N-D: From Task-Specific to a General Purpose CNN

ICLR 2023

Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection

ICLR 2023

Energy-Based Test Sample Adaptation for Domain Generalization

ICLR 2023

Differentiable Mathematical Programming for Object-Centric Representation Learning

ICLR 2023

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

ICLR 2023

A generalized midpoint-based boundary value method for unstable partial differential equations

Journal of Computational and Applied Mathematics 2023

WeakSTIL: weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need

SPIE Medical Imaging 2022

In silico evaluation of limited sampling strategies for individualized dosing of extended half-life factor IX concentrates in hemophilia B patients

European Journal of Clinical Pharmacology 2022

HRD-related morphology discovery in breast cancer by controlling for confounding factors

Cell Reports Medicine 2022

Dynamic Transformer for Few-shot Instance Segmentation

ACMMM 2022

DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer

Medical Image Analysis 2022

Complex-Valued Autoencoders for Object Discovery

TMLR 2022

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

Transactions on Machine Learning Research (TMLR) 2022

Temporal dynamics of neural responses in human visual cortex

The Journal of Neuroscience 2022

Pruning Edges and Gradients to Learn Hypergraphs from Larger Sets

LOG 2022

Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs

BMVC 2022

LifeLonger: A Benchmark for Continual Disease Classification

MICCAI 2022

Intracranial recordings show evidence of numerosity tuning in human parietal cortex

PLOS ONE 2022

Hyperbolic Graph Codebooks

International Conference on Machine Learning, Optimization, and Data Science 2022

Diversely-Supervised Visual Product Search

ACM Transactions on Multimedia Computing, Communications, and Application 2022

Are 3D convolutional networks inherently biased towards appearance?

CVIU 2022

Weakly supervised causal representation learning

NeurIPS 2022

Variational Model Perturbation for Source-Free Domain Adaptation

NeurIPS 2022

Maximum Class Separation as Inductive Bias in One Matrix

NeurIPS 2022

LieGG: Studying Learned Lie Group Generators

NeurIPS 2022

Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel

NeurIPS 2022

Association Graph Learning for Multi-Task Classification with Category Shifts

NeurIPS 2022

VTC: Improving Video-Text Retrieval with User Comments

ECCV 2022

Less than Few: Self-Shot Video Instance Segmentation

ECCV 2022

How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?

ECCV 2022

Delta Distillation for Efficient Video Processing

ECCV 2022

Contrasting quadratic assignments for set-based representation learning

ECCV 2022

3D Equivariant Graph Implicit Functions

ECCV 2022

Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

BMVC 2022

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

ICML 2022

CITRIS - Causal Identifiability from Temporal Intervened Sequences

ICML 2022

TubeR: Tubelet Transformer for Video Action Detection

CVPR 2022

Self-supervised object detection from audio-visual correspondence

CVPR 2022

NFormer: Robust Person Re-identification with Neighbor Transformer

CVPR 2022

Hyperbolic Image Segmentation

CVPR 2022

Dynamic Prototype Convolution Network for Few-shot Semantic Segmentation

CVPR 2022

BoxeR: Box-Attention for 2D and 3D Transformers

CVPR 2022

Audio-Adaptive Activity Recognition Across Video Domains

CVPR 2022

Stability Regularization for Discrete Representation Learning

ICLR 2022

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

ICLR 2022

Learning to Generalize across Domains on Single Test Samples

ICLR 2022

Hierarchical Variational Memory for Few-shot Learning Across Domains

ICLR 2022

Meta-learning for fast cross-lingual adaptation in dependency parsing

ACL 2022

On Measuring and Controlling the Spectral Bias of the Deep Image Prior

IJCV 2022

Visuospatial coding as ubiquitous scaffolding for human cognition

Trends in Cognitive Sciences 2022

Variational Abnormal Behavior Detection with Motion Consistency

IEEE Transactions on Image Processing 2021

WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need

SPIE Medical Imaging 2022

Safe Fakes: Evaluating Face Anonymizers for Face Detectors

IEEE International Conference on Automatic Face and Gesture Recognition 2021

Variational Multi-Task Learning with Gumbel-Softmax Priors

NeurIPS 2021

Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

NeurIPS 2021

PASS: An ImageNet replacement for self-supervised pretraining without humans

NeurIPS Datasets and Benchmarks 2021

Keeping Your Eye On the Ball: Trajectory Attention in Video Transformers

NeurIPS 2021

Hyperbolic Busemann Learning with Ideal Prototypes

NeurIPS 2021

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

NeurIPS 2021

Human-Object Interaction Detection via Weak Supervision

BMVC 2021

DISCO: accurate Discrete Scale Convolutions

BMVC 2021

Diagnosing Errors in Video Relation Detectors

BMVC 2021

Direct comparison of category and spatial selectivity in human occipitotemporal cortex

Brain Structure and Function 2021

Skeleton-Contrastive 3D Action Representation Learning

ACMMM 2021

Learning Hierarchical Embedding for Video Instance Segmentation

ACMMM 2021

Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

IJCV 2021

Sparse-Shot Learning With Exclusive Cross-Entropy for Extremely Many Localisations

ICCV 2021

Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning

ICCV 2021

Social Fabric: Tubelet Compositions for Video Relation Detection

ICCV 2021

Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation

ICCV 2021

Motion-Augmented Self-Training for Video Recognition at Smaller Scale

ICCV 2021

On Compositions of Transformations in Contrastive Self-Supervised Learning

ICCV 2021

Learning to Adapt with Memory for Probabilistic Few-Shot Learning

IEEE Transactions on Circuits and Systems for Video Technology 2021

Memory Attention Networks for Skeleton-Based Action Recognition

TNNLS 2021

The Hateful Memes Challenge: Competition Report

Proceedings of Machine Learning Research 2021

Emergent inequality and business cycles in a simple behavioral macroeconomic model

Proceedings of the National Academy of Sciences (PNAS), 2021

Neural Feature Matching in Implicit 3D Representations

ICML 2021

Kernel Continual Learning

ICML 2021

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

ICML 2021

Arae: Adversarially robust training of autoencoders improves novelty detection

Neural Networks 2021

Learning to Learn Dense Gaussian Processes for Few-Shot Learning

NeurIPS 2021

Learning Regression and Verification Networks for Robust Long-term Tracking

IJCV 2021

Variational Topic Inference for Chest X-Ray Report Generation

MICCAI 2021

Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation

ACL 2021

Unsharp Mask Guided Filtering

IEEE Transactions on Image Processing 2021

Deep 3D human pose estimation: A review

CVIU 2021

Variational prototype inference for few-shot semantic segmentation

WACV 2021

Rotation Equivariant Siamese Networks for Tracking

CVPR 2021

Repetitive Activity Counting by Sight and Sound

CVPR 2021

On Semantic Similarity in Video Retrieval

CVPR 2021

Multiresolution Knowledge Distillation for Anomaly Detection

CVPR 2021

Few-Shot Transformation of Common Actions into Time and Space

CVPR 2021

Support-set bottlenecks for video-text representation learning

ICLR 2021

MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond

ICLR 2021

MetaNorm: Learning to Normalize Few-Shot Batches Across Domains

ICLR 2021

LiftPool: Bidirectional ConvNet Pooling

ICLR 2021

Object Priors for Classifying and Localizing Unseen Actions

IJCV 2021

Counterfactual attribute-based visual explanations for classification

International Journal of Multimedia Information Retrieval 2021

Variational Knowledge Distillation for Disease Classification in Chest X-Rays

IPMI 2021

Domain- and task-specific transfer learning for medical segmentation tasks

Computer Methods and Programs in Biomedicine 2021

Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning

Diagnostics 2021

Scale Equivariance Improves Siamese Tracking

WACV 2021

Tackling Occlusion in Siamese Tracking with Structured Dropouts

ICPR 2020

Self-Selective Context for Interaction Recognition

ICPR 2020

Quasibinary Classifier for Images with Zero and Multiple Labels

ICPR 2020

Model Decay in Long-Term Tracking

ICPR 2020

Feature-Supervised Action Modality Transfer

ICPR 2020

Automatic Triage of 12‐Lead ECGs Using Deep Convolutional Neural Networks

Journal of the American Heart Association 2020

Learning to Learn Variational Semantic Memory

NeurIPS 2020

Adversarial Self-Supervised Scene Flow Estimation

International Conference on 3D Vision 2020

A Dynamic, Self Supervised, Large Scale AudioVisual Dataset for Stuttered Speech

ACM Multimedia 2020 MuCaI

Social Navigation with Human Empowerment Driven Deep Reinforcement Learning

International Conference on Artificial Neural Networks 2020

Pixel-level non-local image smoothing with objective evaluation

TMM 2020

Modeling the temporal dynamics of neural responses in human visual cortex

Journal of Vision 2020

Scale-Equivariant Steerable Networks

ICLR 2020

Low‐level image statistics in natural scenes infuence perceptual decision‐making

Scientific Reports 2020

Electrocorticography Evidence of Tactile Responses in Visual Cortices

Brain Topography 2020

Learning to Learn with Variational Information Bottleneck for Domain Generalization

ECCV 2020

Interactivity Proposals for Surveillance Videos

ICMR 2020

Explaining with Counter Visual Attributes and Examples

ICMR 2020

Pixelated Semantic Colorization

IJCV 2020

Learning to Learn Kernels with Variational Random Features

ICML 2020

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

ECCV 2020

Open Cross-Domain Visual Search

CVIU 2020

Heterogeneous Non-Local Fusion for Multimodal Activity Recognition

ICMR 2020

Shuffled ImageNet-Banks for Video Event Detection and Search

ACM Transactions on Multimedia Computing, Communications, and Applications 2020

Localizing the Common Action Among a Few Videos

ECCV 2020

PointMixup: Augmentation for Point Clouds

ECCV 2020

Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks

ICML 2020

Siamese Tracking of Cell Behaviour Patterns

MIDL 2020

Few-Shot Semantic Segmentation with Democratic Attention Networks

ECCV 2020

Few-Shot Ensemble Learning for Video Classification with SlowFast Memory Networks

ACMMM 2020

Searching for Actions on the Hyperbole

CVPR 2020

Guess Where? Actor-Supervision for Spatiotemporal Video Action Localization

CVIU 2020

Cloth in the Wind: A Case Study of Physical Measurement through Simulation

CVPR 2020

Actor-Transformers for Group Activity Recognition

CVPR 2020

ActionBytes: Learning from Trimmed Videos to Localize Actions

CVPR 2020

Training a Spiking Neural Network with Equilibrium Propagation

AISTAT 2019

Timeception for Complex Action Recognition

CVPR 2019

SILCO: Show a Few Images, Localize the Common Object

ICCV 2019

Repetition Estimation

IJCV 2019

Relaxed quantization for discretized neural networks

ICLR 2019

Pointly-Supervised Action Localization

IJCV 2019

New Modality: Emoji Challenges in Prediction, Anticipation, and Retrieval

TMM 2019

Multidimensional Balance-Based Cluster Boundary Detection for High-Dimensional Data

IEEE Transactions on Neural Networks and Learning Systems 2019

Interactive Exploration of Journalistic Video Footage through Multimodal Semantic Matching

ACMMM 2019

Initialized Equilibrium Propagation for Backprop-Free Training

ICLR 2019

Hyperspherical Prototype Networks

NeurIPS 2019

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

ICML 2019

Dance with Flow: Two-in-One Stream Action Detection

CVPR 2019

Counting with Focus for Free

ICCV 2019

Combinatorial Bayesian Optimization using the Graph Cartesian Product

NeurIPS 2019

Attention-based Multi-Context Guiding for Few-Shot Semantic Segmentation

AAAI 2019

Accelerating Convolutional Neural Networks with Dynamic Channel Pruning

Data Compression Conference 2019

A Layer-Based Sequential Framework for Scene Generation with GANs

AAAI 2019

3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation

International Conference on 3D Vision 2019

Pixel-level Semantics Guided Image Colorization

BMVC 2018

VideoLSTM Convolves, Attends and Flows for Action Recognition

CVIU 2018

Video Time: Properties, Encoders and Evaluation

BMVC 2018

Temporally Efficient Deep Learning with Spikes

ICLR 2018

Searching and Matching Texture-free 3D Shapes in Images

ICMR 2018

Reflectance and natural illumination from single-material specular objects using deep learning

PAMI 2018

Real-World Repetition Estimation by Div, Grad and Curl

CVPR 2018

Long-Term Tracking in the Wild: A Benchmark

ECCV 2018

Improving Word Embedding Compositionality using Lexicographic Definitions

WWW 2018

i-RevNet: Deep Invertible Networks

ICLR 2018

Estimating small differences in car-pose from orbits

BMVC 2018

Crowd Counting With Deep Negative Correlation Learning

CVPR 2018

Cheat me not: automated proctoring of digital exams on Bring-Your-Own-Device

ACM Conference on Innovation and Technology in Computer Science Education

BOCK: Bayesian Optimization with Cylindrical Kernels

ICML 2018

Actor and Action Video Segmentation From a Sentence

CVPR 2018

Action recognition with dynamic image networks

PAMI 2018