Related papers: Attention Allocation Aid for Visual Search
Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data. Recently, significant efforts have been made to exploit attention schemes to advance computer vision…
Bird's-eye view (BEV) object detection has become important for advanced automotive 3D radar-based perception systems. However, the inherently sparse and non-deterministic nature of radar data limits the effectiveness of traditional…
Both appearance cue and constraint cue are vital for human pose estimation. However, there is a tendency in most existing works to overfitting the former and overlook the latter. In this paper, we propose Augmentation by Information…
This dissertation advances the state of the art for AR/VR tracking systems by increasing the tracking frequency by orders of magnitude and proposes an efficient algorithm for the problem of edge-aware optimization. AR/VR is a natural way of…
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…
Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…
How people look at visual information reveals fundamental information about themselves, their interests and their state of mind. While previous visual attention models output static 2-dimensional saliency maps, saccadic models aim to…
Visual Question and Answering (VQA) problems are attracting increasing interest from multiple research disciplines. Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented…
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual…
Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information. Existing methods typically rely on the attention mechanism…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
In various scientific and engineering domains, where data acquisition is costly--such as in medical imaging, environmental monitoring, or remote sensing--strategic sampling from unobserved regions, guided by prior observations, is essential…
Visual Search is referred to the task of finding a target object among a set of distracting objects in a visual display. In this paper, based on an independent analysis of the COCO-Search18 dataset, we investigate how the performance of…
We present a novel visual attention tracking technique based on Shared Attention modeling. Our proposed method models the viewer as a participant in the activity occurring in the scene. We go beyond image salience and instead of only…
We introduce new adaptive artificial anti-diffusion (AAAD) methods for one- and two-dimensional hyperbolic systems of conservation laws. The key idea is to reduce the amount of numerical dissipation present in a given numerical method by…
The question tackled here is the time allocation of radars in a multitarget environment. At a given time radars can only observe a limited part of the space; it is therefore necessary to move their axis with respect to time, in order to be…
We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interacting pathways: identity and control, intended to mirror the…
Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…
This work investigates the integration of spatially aligned aerial imagery into perception tasks for automated vehicles (AVs). As a central contribution, we present AID4AD, a publicly available dataset that augments the nuScenes dataset…
We present an algorithm, Fourier Activity Recognition (FAR), for UAV video activity recognition. Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the…