A holistic learning framework for Novel Class Discovery (NCD), which adopts contrastive learning to learn discriminate features with both the labeled and unlabeled data. The Neighborhood Contrastive Learning (NCL) framework effectively leverages the local... read more of Neighborhood Contrastive Learning for Novel Class Discovery

PyTorch implementation of Intrinsic-Extrinsic Preserved Generative Adversarial Network (IEP-GAN) for both intrinsic (i.e., shape) and extrinsic (i.e., pose) information preservation. Extrinsically, a co-occurrence discriminator is used to capture the stru... read more of IEP-GAN: Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

A tool to allow Visual Transformers (VTs) to learn spatial relations within an image making the VT training much more robust when training data is scarce. The tool can be used jointly with the standard (supervised) training and it does not depend on speci... read more of Efficient Training of Visual Transformers with Small Datasets

Python implementation of novel Cycle In Cycle Generative Adversarial Network (C2GAN) for the task of keypoint-guided image generation. The C2GAN is a cross-modal framework exploring a joint exploitation of the keypoint and the image data in an interactive... read more of Cycle-In-Cycle GANs

A novel unsupervised domain adaptation approach for action recognition from videos, inspired by recent literature on contrastive learning. It comprises a novel two-headed deep architecture that simultaneously adopts cross-entropy and contrastive losses fr... read more of CO2A - Contrastive Conditional domain Alignment

PyTorch implementation of a Geometry-Contrastive Transformer for Generalized 3D Pose Transfer. The novel GC-Transformer can freely conduct robust pose transfer on LARGE meshes at no cost, which could be a boost to Transformers in 3D fields. read more of CGTransformer

Novel two-stage framework with a new Cascaded Cross MLP-Mixer (CrossMLP) sub-network in the first stage and one refined pixel-level loss in the second stage. In the first stage, the CrossMLP sub-network learns the latent transformation cues between image ... read more of Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation

PyTorch implementation of AniFormer, a novel Transformer-based architecture, that generates animated 3D sequences by directly taking the raw driving sequences and arbitrary same-type target meshes as inputs. The Transformer architecture is customised for ... read more of AniFormer

Optimisation of the design and operation of ship energy systems in terms of energy efficiency and lifecycle costs read more of Ship energy system design optimisation

Model for port to port vessel route forecasting using massive Automatic Identification System (AIS) datasets read more of Detecting representative trajectories from global AIS datasets