相关论文: Exploiting Multimodal Spatial-temporal Patterns fo…

Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success,…

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in…

Tracking multiple objects is a challenging task when objects move in groups and occlude each other. Existing methods have investigated the problems of group division and group energy-minimization; however, lacking overall object-group…

Efficient trackers achieve faster runtime by reducing computational complexity and model parameters. However, this efficiency often compromises the expense of weakened feature representation capacity, thus limiting their ability to…

3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is…

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…

With the rapid development of location based services, multimodal spatio-temporal (ST) data including trajectories, transportation modes, traffic flow and social check-ins are being collected for deep learning based methods. These deep…

Compared to images, videos better reflect real-world acquisition and possess valuable temporal cues. However, existing multi-sensor fusion research predominantly integrates complementary context from multiple images rather than videos due…

Object tracking based on the fusion of visible and thermal im-ages, known as RGB-T tracking, has gained increasing atten-tion from researchers in recent years. How to achieve a more comprehensive fusion of information from the two…

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…

This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning…

Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that simultaneously reconstructs and tracks dynamic video content…

Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often…

Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…

Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time. Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging…

We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast…

Multi-Camera Multi-Target Tracking (MCMT) is a computer vision technique that involves tracking multiple targets simultaneously across multiple cameras. MCMT in urban traffic visual analysis faces great challenges due to the complex and…

Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer from quadratic computational complexity, temporal…

Robotic motor control necessitates the ability to predict the dynamics of environments and interaction objects. However, advanced self-supervised pre-trained visual representations in robotic motor control, leveraging large-scale egocentric…

Visual object tracking in real-world scenarios presents numerous challenges including occlusion, interference from similar objects and complex backgrounds-all of which limit the effectiveness of RGB-based trackers. Multispectral imagery,…