Related papers: Quantifying and Learning Static vs. Dynamic Inform…

Explaining the decision of a multi-modal decision-maker requires to determine the evidence from both modalities. Recent advances in XAI provide explanations for models trained on still images. However, when it comes to modeling multiple…

In video action recognition, shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution (OOD) generalization. The video background is clearly a source of static bias, but the video…

Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic…

Spatio-temporal action detection (STAD) aims to classify the actions present in a video and localize them in space and time. It has become a particularly active area of research in computer vision because of its explosively emerging…

Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the…

The ability to accurately predict the surrounding environment is a foundational principle of intelligence in biological and artificial agents. In recent years, a variety of approaches have been proposed for learning to predict the physical…

The traditional Simultaneous Localization And Mapping (SLAM) systems rely on the assumption of a static environment and fail to accurately estimate the system's location when dynamic objects are present in the background. While…

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

Delving into the realm of egocentric vision, the advancement of referring video object segmentation (RVOS) stands as pivotal in understanding human activities. However, existing RVOS task primarily relies on static attributes such as object…

Traditional Visual Simultaneous Localization and Mapping (VSLAM) systems assume a static environment, which makes them ineffective in highly dynamic settings. To overcome this, many approaches integrate semantic information from deep…

This paper addresses the challenge of Lidar-Inertial Odometry (LIO) in dynamic environments, where conventional methods often fail due to their static-world assumptions. Traditional LIO algorithms perform poorly when dynamic objects…

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often…

Learning identifiable representations and models from low-level observations is helpful for an intelligent spacecraft to complete downstream tasks reliably. For temporal observations, to ensure that the data generating process is provably…

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…

In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade…

The task of action recognition or action detection involves analyzing videos and determining what action or motion is being performed. The primary subject of these videos are predominantly humans performing some action. However, this…

Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very little about how its internal representations change during…

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Mainstream visual object tracking frameworks predominantly rely on template matching paradigms. Their performance heavily depends on the quality of template features, which becomes increasingly challenging to maintain in complex scenarios…