Related papers: Optimizing Camera Configurations for Multi-View Pe…

The use of intelligent automation is growing significantly in the automotive industry, as it assists drivers and fleet management companies, thus increasing their productivity. Dash cams are now been used for this purpose which enables the…

Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics. In this paper, we focus on contextual affordance learning, i.e., using…

Visual localization remains challenging in dynamic environments where fluctuating lighting, adverse weather, and moving objects disrupt appearance cues. Despite advances in feature representation, current absolute pose regression methods…

Multi-view image generation in autonomous driving demands consistent 3D scene understanding across camera views. Most existing methods treat this problem as a 2D image set generation task, lacking explicit 3D modeling. However, we argue…

Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…

Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high…

Sensor configuration, including the sensor selections and their installation locations, serves a crucial role in autonomous driving. A well-designed sensor configuration significantly improves the performance upper bound of the perception…

Feature generation is a critical step in machine learning, aiming to enhance model performance by capturing complex relationships within the data and generating meaningful new features. Traditional feature generation methods heavily rely on…

This paper addresses fully automated multi-person tracking in complex environments with challenging occlusion and extensive pose variations. Our solution combines multiple detectors for a set of different regions of interest (e.g.,…

Change detection in remote sensing imagery is essential for a variety of applications such as urban planning, disaster management, and climate research. However, existing methods for identifying semantically changed areas overlook the…

Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of single camera as…

This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through…

We address the task of identifying distracted driving by analyzing in-car videos using efficient transformers. Although transformer models have achieved outstanding performance in human action recognition tasks, their high computational…

Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this…

Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…

Recently, transformers have shown strong ability as visual feature extractors, surpassing traditional convolution-based models in various scenarios. However, the success of vision transformers largely owes to their capacity to accommodate…

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of…

Multiple pedestrian tracking is crucial for enhancing safety and efficiency in intelligent transport and autonomous driving systems by predicting movements and enabling adaptive decision-making in dynamic environments. It optimizes traffic…

Generating 3D shapes from single RGB images is essential in various applications such as robotics. Current approaches typically target images containing clear and complete visual descriptions of the object, without considering common…

We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed…