Related papers: Traj-MAE: Masked Autoencoders for Trajectory Predi…

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…

Informed machine learning methods allow the integration of prior knowledge into learning systems. This can increase accuracy and robustness or reduce data needs. However, existing methods often assume hard constraining knowledge, that does…

As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends…

We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions…

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D…

Self-supervised pre-training has proven highly effective for many computer vision tasks, particularly when labelled data are scarce. In the context of Earth Observation (EO), foundation models and various other Vision Transformer…

In the trajectory planning of automated driving, data-driven statistical artificial intelligence (AI) methods are increasingly established for predicting the emergent behavior of other road users. While these methods achieve exceptional…

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to…

Trajectory prediction aims to forecast agents' possible future locations considering their observations along with the video context. It is strongly needed by many autonomous platforms like tracking, detection, robot navigation, and…

Vision-based trajectory prediction is an important task that supports safe and intelligent behaviours in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction.…

The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair data from different modalities and sensors automatically based…

Human emotion recognition holds a pivotal role in facilitating seamless human-computer interaction. This paper delineates our methodology in tackling the Valence-Arousal (VA) Estimation Challenge, Expression (Expr) Classification Challenge,…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…

Spatio-temporal trajectories provide valuable information about movement and travel behavior, enabling various downstream tasks that in turn power real-world applications. Learning trajectory embeddings can improve task performance but may…

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a…

We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities,…