Related papers: DATAP-SfM: Dynamic-Aware Tracking Any Point for Ro…

This paper proposes a novel approach to create an automated visual surveillance system which is very efficient in detecting and tracking moving objects in a video captured by moving camera without any apriori information about the captured…

Obstacle avoidance for Unmanned Aerial Vehicles (UAVs) in cluttered environments is significantly challenging. Existing obstacle avoidance for UAVs either focuses on fully static environments or static environments with only a few dynamic…

Given a single labeled example, in-context segmentation aims to segment corresponding objects. This setting, known as one-shot segmentation in few-shot learning, explores the segmentation model's generalization ability and has been applied…

Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically…

Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…

Detecting actions in videos is an important yet challenging task. Previous works usually utilize (a) sliding window paradigms, or (b) per-frame action scoring and grouping to enumerate the possible temporal locations. Their performances are…

3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically deficient LiDAR point clouds. While motion paradigm…

Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point…

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…

Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…

Robot person following (RPF) is a core capability in human-robot interaction, enabling robots to assist users in daily activities, collaborative work, and other service scenarios. However, achieving practical RPF remains challenging due to…

Comprehensive understanding of dynamic scenes is a critical prerequisite for intelligent robots to autonomously operate in their environment. Research in this domain, which encompasses diverse perception problems, has primarily been focused…

This paper presents a novel approach for optimizing the scheduling and control of Pan-Tilt-Zoom (PTZ) cameras in dynamic surveillance environments. The proposed method integrates Kalman filters for motion prediction with a dynamic network…

In this endeavor, we developed a comprehensive system that processes integrated visual features derived from video frames captured by a regular camera, along with depth details obtained from a point cloud scanner. This system is designed to…

3D multi-object tracking is a critical and challenging task in the field of autonomous driving. A common paradigm relies on modeling individual object motion, e.g., Kalman filters, to predict trajectories. While effective in simple…

Recent advancements in diffusion models have made fine-tuning text-to-image models for personalization increasingly accessible, but have also raised significant concerns regarding unauthorized data usage and privacy infringement. Current…

In this paper, we propose an accurate and robust perception module for Autonomous Vehicles (AVs) for drivable space extraction. Perception is crucial in autonomous driving, where many deep learning-based methods, while accurate on benchmark…

Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos. However, they mainly focus on better matching between the…