-
MonoSelfRecon
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views -
FlowStep3D: Model unrolling for self-supervised scene flow estimation.
Model unrolling for self-supervised scene flow estimation. -
Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hal...
Dyna-LfLH is a self-supervised machine learning method for mobile robot navigation in dynamic environments. -
Self-supervised temporal analysis of spatiotemporal data
Small, publicly available GPS trajectory datasets (e.g., [51, 55, 80]) have varying sampling rates with incomplete trajectories, (ii) are geographically incomplete, (iii) have... -
SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets
Geospatial datasets are diverse, naturally spatiotemporal, and inherently multimodal (composed of two or more distinct signal types or modalities) e.g., satellite/aerial imagery... -
EAT: Enhanced ASR-TTS for Self-Supervised Speech Recognition
Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS model that incorporates two main features: 1) The ASR→TTS direction... -
Partial2Complete
Point cloud completion aims to recover the complete shape based on a partial observation. The proposed Partial2Complete (P2C) framework completes point cloud objects using... -
Zero-Shot Automatic Pronunciation Assessment
Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition... -
Prototypical Contrastive Learning
Self-supervised learning of pretext-invariant representations. -
Geography-aware self-supervised learning
Geography-aware self-supervised learning -
Training transitive and commutative multimodal transformers with LoReTTa
Training transitive and commutative multimodal transformers with LoReTTa -
T-Drive: Driving Directions Based on Taxi Trajectories
T-Drive dataset for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories -
Probe Data and Privacy
Probe data for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories -
Reachability Embeddings: Scalable Self-Supervised Representation Learning fro...
GPS trajectory dataset for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories -
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the ImageNet, Places205, and VOC07 datasets for evaluation. -
MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model
MonoDiffusion: A novel self-supervised monocular depth estimation framework by reformulating it as an iterative denoising process. -
Self-Distillation Prototypes Network: Learning Robust Speaker Representations...
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new... -
A simple data mixing prior for improving self-supervised learning
A simple data mixing prior for improving self-supervised learning.
