Related papers: Find First, Track Next: Decoupling Identification …
Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous…
The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…
Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language…
Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond synthesis. In this work, we investigate their self-attention…
Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first…
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation…
Tracking is one of the most important but still difficult tasks in computer vision and pattern recognition. The main difficulties in the tracking field are appearance variation and occlusion. Most traditional tracking methods set the…
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-rate as a strict requirement for performance. This is…
Interactive video object segmentation is a crucial video task, having various applications from video editing to data annotating. However, current approaches struggle to accurately segment objects across diverse domains. Recently, Segment…
Personal robots and driverless cars need to be able to operate in novel environments and thus quickly and efficiently learn to recognise new object classes. We address this problem by considering the task of video object segmentation.…
The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative…
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on…
Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive…
Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…
Multi-object Tracking (MOT) generally can be split into two sub-tasks, i.e., detection and association. Many previous methods follow the tracking by detection paradigm, which first obtain detections at each frame and then associate them…
We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of…
This paper presents a novel hierarchical approach for the simultaneous tracking of multiple targets in a video. We use a network flow approach to link detections in low-level and tracklets in high-level. At each step of the hierarchy, the…
Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative…
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…
Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other,…