Related papers: ODAM: Gradient-based instance-specific visual expl…
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each…
In this paper, we propose a novel framework for enhancing visual comprehension in autonomous driving systems by integrating visual language models (VLMs) with additional visual perception module specialised in object detection. We extend…
The Grad-CAM algorithm provides a way to identify what parts of an image contribute most to the output of a classifier deep network. The algorithm is simple and widely used for localization of objects in an image, although some researchers…
Perception is a key element for enabling intelligent autonomous navigation. Understanding the semantics of the surrounding environment and accurate vehicle pose estimation are essential capabilities for autonomous vehicles, including…
Extreme amodal detection is the task of inferring the 2D location of objects that are not fully visible in the input image but are visible within an expanded field-of-view. This differs from amodal detection, where the object is partially…
Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the…
With the great achievement of artificial intelligence, vehicle technologies have advanced significantly from human centric driving towards fully automated driving. An intelligent vehicle should be able to understand the driver's perception…
Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our understanding of…
We propose a unified framework that integrates object detection (OD) and visual grounding (VG) for remote sensing (RS) imagery. To support conventional OD and establish an intuitive prior for VG task, we fine-tune an open-set object…
Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category, such as 200 subcategories belonging to the bird, which is highly challenging due to large variance in the same…
Temporal action segmentation is typically achieved by discovering the dramatic variances in global visual descriptors. In this paper, we explore the merits of local features by proposing the unsupervised framework of Object-centric Temporal…
The efficiency of object detectors depends on factors like detection accuracy, processing time, and computational resources. Processing time is crucial for real-time applications, particularly for autonomous vehicles (AVs), where…
In recent years, deep neural networks (DNNs) have gained widespread adoption for continuous mobile object detection (OD) tasks, particularly in autonomous systems. However, a prevalent issue in their deployment is the one-size-fits-all…
Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete…
In autonomous driving, 3D object detection provides more precise information for downstream tasks, including path planning and motion estimation, compared to 2D object detection. In this paper, we propose SeSame: a method aimed at enhancing…
Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased…
Salient object detection is inherently a subjective problem, as observers with different priors may perceive different objects as salient. However, existing methods predominantly formulate it as an objective prediction task with a single…
We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy and low detection…
Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…
Deep learning based approaches to Computer Aided Diagnosis (CAD) typically pose the problem as an image classification (Normal or Abnormal) problem. These systems achieve high to very high accuracy in specific disease detection for which…