48 datasets found

SOGAR: Self-supervised spatiotemporal attention-based social group activity recognition.

Group activity recognition using self-supervised approach of spatiotemporal transformers.

The dataset used in the paper is a large-scale point cloud compression framework, which can organize sparse and un-structured point clouds in a memory-efficient way.

Self-supervised monocular depth estimation from monocular video sequences

A self-supervised learning method for learning histopathological patterns within cancerous tissue regions.

Self-supervised adversarial masking for 3D point cloud representation learning

MiniVox is an automatic framework to transform any speaker-into continuous speech datastream with labelled dataset episodically revealed label feedbacks.

This work profoundly analyzes discrete self-supervised speech representations (units) through the eyes of Generative Spoken Language Modeling (GSLM).

The dataset used for testing the OctoPath network, containing sequences of octrees and points from the reference path.

The dataset used for training the OctoPath network, containing sequences of octrees and points from the reference path.

The LeBenchmark7K dataset is a self-supervised representation of French speech.

Photometric stereo with two images using a self-supervised deep learning framework called DeepPS2.

PHIMO, a physics-informed motion correction method tailored to quantitative MRI, which utilises information from the MR signal evolution to detect motion events with a...

The dataset used in the paper is a multi-object environment with a robotic arm and multiple objects to manipulate. The agent learns to control the objects independently and...

The dataset is used for learning general and effective models for both audio and video analysis from self-supervised temporal synchronization.

Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention...

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art...

Contrastive learning is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented views of the same image as...

Self-supervised pre-training method with Swin Transformer for music classification, leveraging massive unlabeled music data to improve the performance of music classification...

A new approach for creating an animatable and photo-realistic 3D head model from multi-view video footage of a real actor, together with a neural animation model based on...