Related papers: MFTIQ: Multi-Flow Tracker with Independent Matchin…
Existing event stream based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios…
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability. Although traditional filter-based methods can achieve better results, they are difficult to be endowed with optimal…
Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…
In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach…
Video frame interpolation (VFI) that leverages the bio-inspired event cameras as guidance has recently shown better performance and memory efficiency than the frame-based methods, thanks to the event cameras' advantages, such as high…
Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement…
This paper presents a fast and modular framework for Multi-Object Tracking (MOT) based on the Markov descision process (MDP) tracking-by-detection paradigm. It is designed to allow its various functional components to be replaced by…
Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this…
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching…
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by…
In recent years visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year. It is because tracking has wide applications in various real world problems such as…
Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art trackers typically rely on cost volumes to match features across frames, but this…
Efficient and accurate motion prediction is crucial for ensuring safety and informed decision-making in autonomous driving, particularly under dynamic real-world conditions that necessitate multi-modal forecasts. We introduce TrajFlow, a…
Recent approaches to point tracking are able to recover the trajectory of any scene point through a large portion of a video despite the presence of occlusions. They are, however, too slow in practice to track every point observed in a…
Phytoplankton are a crucial component of aquatic ecosystems, and effective monitoring of them can provide valuable insights into ocean environments and ecosystem changes. Traditional phytoplankton monitoring methods are often complex and…
Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on…
How important are training details and datasets to recent optical flow models like RAFT? And do they generalize? To explore these questions, rather than develop a new model, we revisit three prominent models, PWC-Net, IRR-PWC and RAFT, with…
The Fast Tracker (FTK) is a proposed upgrade to the ATLAS trigger system that will operate at full Level-1 output rates and provide high quality tracks reconstructed over the entire detector by the start of processing in Level-2. FTK solves…
This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios. In this paper, FaceTrack is proposed that utilizes multiple appearance models with its long-term…