Related papers: TQD-Track: Temporal Query Denoising for 3D Multi-O…
Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding…
The monocular depth estimation task has recently revealed encouraging prospects, especially for the autonomous driving task. To tackle the ill-posed problem of 3D geometric reasoning from 2D monocular images, multi-frame monocular methods…
Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions,…
Adverse weather can cause noise to light detection and ranging (LiDAR) data. This is a problem since it is used in many outdoor applications, e.g. object detection and mapping. We propose the task of multi-echo denoising, where the goal is…
Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…
Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D detectors is not explored mainly due to two reasons: (1) the…
One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries…
In the recent literature, on the one hand, many 3D multi-object tracking (MOT) works have focused on tracking accuracy and neglected computation speed, commonly by designing rather complex cost functions and feature extractors. On the other…
Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…
Recent advancements in deep-learning methods for object detection in point-cloud data have enabled numerous roadside applications, fostering improvements in transportation safety and management. However, the intricate nature of point-cloud…
Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…
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…
Accurate 3D geometry acquisition is essential for a wide range of applications, such as computer graphics, autonomous driving, robotics, and augmented reality. However, raw point clouds acquired in real-world environments are often…
Passive multi-target tracking (MTT) aims to infer the kinematic states of multiple targets from noisy sensor data in which contributions from unknown target-emitted signals are superposed. Track-before-detect (TBD) methods improve…
Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract…
Eye-tracking has potential to provide rich behavioral data about human cognition in ecologically valid environments. However, analyzing this rich data is often challenging. Most automated analyses are specific to simplistic artificial…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…
With the advent of depth sensing technologies, the extraction of object contours in images---a common and important pre-processing step for later higher-level computer vision tasks like object detection and human action recognition---has…
Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen categories (novel…