Related papers: Self-supervised classification of dynamic obstacle…

Accurate online multiple-camera vehicle tracking is essential for intelligent transportation systems, autonomous driving, and smart city applications. Like single-camera multiple-object tracking, it is commonly formulated as a graph problem…

Unsupervised approaches for video anomaly detection may not perform as good as supervised approaches. However, learning unknown types of anomalies using an unsupervised approach is more practical than a supervised approach as annotation is…

As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…

We present a new paradigm for real-time object-oriented SLAM with a monocular camera. Contrary to previous approaches, that rely on object-level models, we construct category-level models from CAD collections which are now widely available.…

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Machine learning and in particular deep learning algorithms are the emerging approaches to data analysis. These techniques have transformed traditional data mining-based analysis radically into a learning-based model in which existing data…

Working with annotated data is the cornerstone of supervised learning. Nevertheless, providing labels to instances is a task that requires significant human effort. Several critical real-world applications make things more complicated…

In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised…

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…

Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation, and 2) the complexity of two-stage approaches. To resolve…

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video. There are some works on similar topics like detecting scene cuts in a video, but…

In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supervision provided by a robot traversing an environment to…

We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…

This paper shows how an uncertainty-aware, deep neural network can be trained to detect, recognise and localise objects in 2D RGB images, in applications lacking annotated train-ng datasets. We propose a self-supervising teacher-student…

Understanding the scene is key for autonomously navigating vehicles and the ability to segment the surroundings online into moving and non-moving objects is a central ingredient for this task. Often, deep learning-based methods are used to…

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…

Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-world deployments are challenged by limited labeled data, non-stationary traffic, and…