Related papers: GTAD: Global Temporal Aggregation Denoising Learni…
Representing a dynamic scene using a structured spatial-temporal scene graph is a novel and particularly challenging task. To tackle this task, it is crucial to learn the temporal interactions between objects in addition to their spatial…
Heterogeneous temporal graphs (HTGs) are ubiquitous data structures in the real world. Recently, to enhance representation learning on HTGs, numerous attention-based neural networks have been proposed. Despite these successes, existing…
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further…
We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry.…
Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While…
Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph…
Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…
Clustering high-dimensional multivariate spatiotemporal climate data is challenging due to complex temporal dependencies, evolving spatial interactions, and non-stationary dynamics. Conventional clustering methods, including recurrent and…
Accurate traffic prediction is a challenging task in intelligent transportation systems because of the complex spatio-temporal dependencies in transportation networks. Many existing works utilize sophisticated temporal modeling approaches…
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic…
We tackle the task of learning dynamic 3D semantic radiance fields given a single monocular video as input. Our learned semantic radiance field captures per-point semantics as well as color and geometric properties for a dynamic 3D scene,…
Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…
Trajectory anomaly detection is essential for identifying unusual and unexpected movement patterns in applications ranging from intelligent transportation systems to urban safety and fraud prevention. Existing methods only consider limited…
The strong demand of autonomous driving in the industry has lead to strong interest in 3D object detection and resulted in many excellent 3D object detection algorithms. However, the vast majority of algorithms only model single-frame data,…
Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., the point cloud videos. We empirically…
3D semantic occupancy prediction is one of the crucial tasks of autonomous driving. It enables precise and safe interpretation and navigation in complex environments. Reliable predictions rely on effective sensor fusion, as different…
Accurate prediction of driving scene is a challenging task due to uncertainty in sensor data, the complex behaviors of agents, and the possibility of multiple feasible futures. Existing prediction methods using occupancy grid maps primarily…
Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…
Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might…
Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…