Related papers: Human Insights Driven Latent Space for Different D…

This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most…

In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling of individual objects distinctly and their flexible use based…

The cornerstone of autonomous vehicles (AV) is a solid perception system, where camera encoders play a crucial role. Existing works usually leverage pre-trained Convolutional Neural Networks (CNN) or Vision Transformers (ViTs) designed for…

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been…

Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and…

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…

Traffic management in a city has become a major problem due to the increasing number of vehicles on roads. Intelligent Transportation System (ITS) can help the city traffic managers to tackle the problem by providing accurate traffic…

Emerging immersive display technologies efficiently utilize resources with perceptual graphics methods such as foveated rendering and denoising. Running multiple perceptual graphics methods challenges devices with limited power and…

Obstacle avoidance for unmanned aerial vehicles like quadrotors is a popular research topic. Most existing research focuses only on static environments, and obstacle avoidance in environments with multiple dynamic obstacles remains…

Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various…

Trajectory prediction has always been a challenging problem for autonomous driving, since it needs to infer the latent intention from the behaviors and interactions from traffic participants. This problem is intrinsically hard, because each…

Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we…

Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as object detection, semantic segmentation, depth estimation, trajectory prediction, motion prediction, and behaviour prediction, to ensure safe and…

Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a…

Accurately detecting lane lines in 3D space is crucial for autonomous driving. Existing methods usually first transform image-view features into bird-eye-view (BEV) by aid of inverse perspective mapping (IPM), and then detect lane lines…

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into…

For an autonomous vehicle, situation understand-ing is a key capability towards safe and comfortable decision-making and navigation. Information is in general provided bymultiple sources. Prior information about the road topology andtraffic…

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a representation that approximates the true joint distribution of contextual, social, and temporal…