Related papers: HiM2SAM: Enhancing SAM2 with Hierarchical Motion E…
To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each…
The Segment Anything Model (SAM) has advanced interactive segmentation but is limited by the high computational cost on high-resolution images. This requires downsampling to meet GPU constraints, sacrificing the fine-grained details needed…
Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for…
The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling…
Tracking cells and detecting mitotic events in time-lapse microscopy image sequences is a crucial task in biomedical research. However, it remains highly challenging due to dividing objects, low signal-tonoise ratios, indistinct boundaries,…
Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer…
Wide Area Motion Imagery (WAMI) yields high-resolution images with a large number of extremely small objects. Target objects have large spatial displacements throughout consecutive frames. This nature of WAMI images makes object tracking…
Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…
Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in…
We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The baseline pre-trained short-term tracker is SuperDiMP which combines the bounding-box regressor of…
Current pandemic has caused the medical system to operate under high load. To relieve it, robots with high autonomy can be used to effectively execute contactless operations in hospitals and reduce cross-infection between medical staff and…
Human annotation is always considered as ground truth in video object tracking tasks. It is used in both training and evaluation purposes. Thus, ensuring its high quality is an important task for the success of trackers and evaluations…
Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…
With the development of multimedia technology, Video Copy Detection has been a crucial problem for social media platforms. Meta AI hold Video Similarity Challenge on CVPR 2023 to push the technology forward. In this report, we share our…
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…
Background: We evaluate SAM 2 for surgical scene understanding by examining its semantic segmentation capabilities for organs/tissues both in zero-shot scenarios and after fine-tuning. Methods: We utilized five public datasets to evaluate…
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine…
The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case loss using one-step…
Increasing the annotation efficiency of trajectory annotations from videos has the potential to enable the next generation of data-hungry tracking algorithms to thrive on large-scale datasets. Despite the importance of this task, there are…
Human motion prediction is an essential component for enabling closer human-robot collaboration. The task of accurately predicting human motion is non-trivial. It is compounded by the variability of human motion, both at a skeletal level…