Related papers: How Physics and Background Attributes Impact Video…

Predicting the future movements of surrounding vehicles is essential for ensuring the safe operation and efficient navigation of autonomous vehicles (AVs) in urban traffic environments. Existing vehicle trajectory prediction methods…

Foundation models have achieved remarkable success across video, image, and language domains. By scaling up the number of parameters and training datasets, these models acquire generalizable world knowledge and often surpass task-specific…

Object tracking in realistic scenarios is a difficult problem affected by various image factors such as occlusion, clutter, confusion, object shape, unstable speed, and zooming. While these conditions do affect tracking performance, there…

Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale "in-the-wild" video…

Machine learning models of visual action recognition are typically trained and tested on data from specific situations where actions are associated with certain objects. It is an open question how action-object associations in the training…

Rapid autonomous traversal of unstructured terrain is essential for scenarios such as disaster response, search and rescue, or planetary exploration. As a vehicle navigates at the limit of its capabilities over extreme terrain, its dynamics…

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

With increasing expressive power, deep neural networks have significantly improved the state-of-the-art on image classification datasets, such as ImageNet. In this paper, we investigate to what extent the increasing performance of deep…

Background modelling is a fundamental step for several real-time computer vision applications that requires security systems and monitoring. An accurate background model helps detecting activity of moving objects in the video. In this work,…

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

Video prediction aims to generate realistic future frames by learning dynamic visual patterns. One fundamental challenge is to deal with future uncertainty: How should a model behave when there are multiple correct, equally probable future?…

While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often neglect the structure and capacity of visual encoders, limiting…

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance…

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…

Multi-Object Tracking (MOT) is a critical problem in computer vision, essential for understanding how objects move and interact in videos. This field faces significant challenges such as occlusions and complex environmental dynamics,…

This research proposes a framework for signal processing and information fusion of spatial-temporal multi-sensor data pertaining to understanding patterns of humans physiological changes in an urban environment. The framework includes…

Accurate knowledge of object poses is crucial to successful robotic manipulation tasks, and yet most current approaches only work in laboratory settings. Noisy sensors and cluttered scenes interfere with accurate pose recognition, which is…