Related papers: Continual Object Detection via Prototypical Task C…

Multi-Object Tracking (MOT) is a crucial computer vision task that aims to predict the bounding boxes and identities of objects simultaneously. While state-of-the-art methods have made remarkable progress by jointly optimizing the…

The ever-increasing use of artificial intelligence in autonomous systems has significantly contributed to advance the research on multi-object tracking, adopted in several real-time applications (e.g., autonomous driving, surveillance…

Feature-based anomaly detection is widely adopted in industrial inspection due to the strong representational power of large pre-trained vision encoders. While most existing methods focus on improving within-category anomaly scoring,…

Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to…

Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…

Existing referring understanding tasks tend to involve the detection of a single text-referred object. In this paper, we propose a new and general referring understanding task, termed referring multi-object tracking (RMOT). Its core idea is…

Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO - a Robust Continuous…

Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…

The primary objective of Continual Anomaly Detection (CAD) is to learn the normal patterns of new tasks under dynamic data distribution assumptions while mitigating catastrophic forgetting. Existing embedding-based CAD approaches…

Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be consistent. We propose…

Object tracking can be formulated as "finding the right object in a video". We observe that recent approaches for class-agnostic tracking tend to focus on the "finding" part, but largely overlook the "object" part of the task, essentially…

We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment. Specifically, we construct a 'coreset' representation of streaming data using a…

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

The recently emerging research area in robotics, ground view change detection, suffers from its ill-posed-ness because of visual uncertainty combined with complex nonlinear perspective projection. To regularize the ill-posed-ness, the…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a result, there is a proliferation of distinct architectures and…

Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide…

Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may…

Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. The paper…

Object counting is an important task in computer vision due to its growing demand in applications such as traffic monitoring or surveillance. In this paper, we consider object counting as a learning problem of a joint feature extraction and…