Related papers: HIMap: HybrId Representation Learning for End-to-e…
Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed…
High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions…
Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e.g., new research areas in citation networks, or new types of…
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a…
Acquisition and maintenance are central problems in deploying high-definition (HD) maps for autonomous driving, with two lines of research prevalent in current literature: Online HD map generation and HD map change detection. However, the…
We present a method for learning multiple scene representations given a small labeled set, by exploiting the relationships between such representations in the form of a multi-task hypergraph. We also show how we can use the hypergraph to…
High-definition (HD) semantic maps are crucial in enabling autonomous vehicles to navigate urban environments. The traditional method of creating offline HD maps involves labor-intensive manual annotation processes, which are not only…
A central challenge in high-energy nuclear physics is to extract informative features from the high-dimensional final-state data of heavy-ion collisions (HIC) in order to enable reliable downstream analyses. Traditional approaches often…
Recent studies have highlighted the limitations of message-passing based graph neural networks (GNNs), e.g., limited model expressiveness, over-smoothing, over-squashing, etc. To alleviate these issues, Graph Transformers (GTs) have been…
3D object detection is a key perception component in autonomous driving. Most recent approaches are based on Lidar sensors only or fused with cameras. Maps (e.g., High Definition Maps), a basic infrastructure for intelligent vehicles,…
Vectorized maps are indispensable for precise navigation and the safe operation of autonomous vehicles. Traditional methods for constructing these maps fall into two categories: offline techniques, which rely on expensive, labor-intensive…
The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To…
We propose HyMoERec, a novel sequential recommendation framework that addresses the limitations of uniform Position-wise Feed-Forward Networks in existing models. Current approaches treat all user interactions and items equally, overlooking…
Three-dimensional feature extraction is a critical component of autonomous driving systems, where perception tasks such as 3D object detection, bird's-eye-view (BEV) semantic segmentation, and occupancy prediction serve as important…
Accurate environmental representations are essential for autonomous driving, providing the foundation for safe and efficient navigation. Traditionally, high-definition (HD) maps are providing this representation of the static road…
Online High-Definition (HD) maps have emerged as the preferred option for autonomous driving, overshadowing the counterpart offline HD maps due to flexible update capability and lower maintenance costs. However, contemporary online HD map…
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for efficiently generating HD map of large-scale driving scene.…
Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g. trajectory prediction. The driving scene often involves heterogeneous elements such as the…
Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between…
Heterogeneous graphs provide a compact, efficient, and scalable way to model data involving multiple disparate modalities. This makes modeling audiovisual data using heterogeneous graphs an attractive option. However, graph structure does…