Related papers: StreamMOTP: Streaming and Unified Framework for Jo…
Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds…
Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and…
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…
The ability of intelligent systems to predict human behaviors is crucial, particularly in fields such as autonomous vehicle navigation and social robotics. However, the complexity of human motion have prevented the development of a…
To track the 3D locations and trajectories of the other traffic participants at any given time, modern autonomous vehicles are equipped with multiple cameras that cover the vehicle's full surroundings. Yet, camera-based 3D object tracking…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we…
This study provides a detailed analysis of current advancements in dynamic object tracking (DOT) and trajectory prediction (TP) methodologies, including their applications and challenges. It covers various approaches, such as feature-based,…
Object motion and object appearance are commonly used information in multiple object tracking (MOT) applications, either for associating detections across frames in tracking-by-detection methods or direct track predictions for…
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…
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…
Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference…
With growing real-world demands, efficient tracking has received increasing attention. However, most existing methods are limited to RGB inputs and struggle in multi-modal scenarios. Moreover, current multi-modal tracking approaches…
Multi-Object Tracking (MOT) is a fundamental task in computer vision, aiming to track targets across video frames. Existing MOT methods perform well in general visual scenes, but face significant challenges and limitations when extended to…
Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures…
Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods…
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…
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field. Most existing approaches are not able to properly handle multi-object tracking challenges such as…
Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time. Existing methods rely on depth sensors (e.g., LiDAR) to detect and track…
Multi-object tracking (MOT) is a critical and challenging task in computer vision, particularly in situations involving objects with similar appearances but diverse movements, as seen in team sports. Current methods, largely reliant on…
Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…