Skip to search formSkip to main contentSkip to account menu

VGGFace2: A Dataset for Recognising Faces across Pose and Age

A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described.
View on IEEE (opens in a new tab)

Vggsound: A Large-Scale Audio-Visual Dataset

The goal is to collect a large-scale audio-visual dataset with low label noise from videos ‘in the wild’ using computer vision techniques and investigates various Convolutional Neural Network architectures and aggregation approaches to establish audio recognition baselines for this new dataset.
View on IEEE (opens in a new tab)

Voxceleb: Large-scale speaker verification in the wild

View via Publisher (opens in a new tab)

Utterance-level Aggregation for Speaker Recognition in the Wild

This paper proposes a powerful speaker recognition deep network, using a ‘thin-ResNet’ trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end.
View on IEEE (opens in a new tab)

Video Representation Learning by Dense Predictive Coding

With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101 and HMDB51, outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.
View on IEEE (opens in a new tab)

Self-supervised Co-training for Video Representation Learning

This paper investigates the benefit of adding semantic-class positives to instance-based Info Noise Contrastive Estimation (InfoNCE) training, and proposes a novel self-supervised co-training scheme to improve the popular infoNCE loss.
View PDF on arXiv (opens in a new tab)

Memory-augmented Dense Predictive Coding for Video Representation Learning

A new architecture and learning framework Memory-augmented Dense Predictive Coding (MemDPC) is proposed for the self-supervised learning from video, in particular for representations for action recognition, trained with a predictive attention mechanism over the set of compressed memories.
View PDF on arXiv (opens in a new tab)

Microscopy cell counting and detection with fully convolutional regression networks

A new state-of-the-art performance for cell count on standard synthetic image benchmarks is set and it is shown that the FCRNs trained entirely with synthetic data can generalise well to real microscopy images both for cell counting and detections for the case of overlapping cells.
View on Taylor & Francis (opens in a new tab)

NeRF-: Neural Radiance Fields Without Known Camera Parameters

It is shown that the camera parameters can be jointly optimised as learnable parameters with NeRF training, through a photometric reconstruction, and the joint optimisation pipeline can recover accurate camera parameters and achieve comparable novel view synthesis quality as those trained with COLMAP pre-computed camera parameters.
View PDF on arXiv (opens in a new tab)

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation and improves the performance over the state-of-the-art, especially for larger-scale datasets, thus demonstrating the effectiveness and scalability of Smooth-AP to real-world scenarios.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)