相关论文: ReMOTS: Self-Supervised Refining Multi-Object Trac…
Learning a discriminative model that distinguishes the specified target from surrounding distractors across frames is essential for generic object tracking (GOT). Dynamic adaptation of target representation against distractors remains…
As a video task, Multiple Object Tracking (MOT) is expected to capture temporal information of targets effectively. Unfortunately, most existing methods only explicitly exploit the object features between adjacent frames, while lacking the…
Despite great recent advances in visual tracking, its further development, including both algorithm design and evaluation, is limited due to lack of dedicated large-scale benchmarks. To address this problem, we present LaSOT, a high-quality…
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…
Referring understanding is a fundamental task that bridges natural language and visual content by localizing objects described in free-form expressions. However, existing works are constrained by limited language expressiveness, lacking the…
Referring video object segmentation (RVOS) aims to segment the target instance referred by a given text expression in a video clip. The text expression normally contains sophisticated description of the instance's appearance, action, and…
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…
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…
This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to conventional visual instruction tuning approaches that…
Visual-based localization has made significant progress, yet its performance often drops in large-scale, outdoor, and long-term settings due to factors like lighting changes, dynamic scenes, and low-texture areas. These challenges degrade…
Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this…
Animals have evolved highly functional visual systems to understand motion, assisting perception even under complex environments. In this paper, we work towards developing a computer vision system able to segment objects by exploiting…
The task of video object segmentation with referring expressions (language-guided VOS) is to, given a linguistic phrase and a video, generate binary masks for the object to which the phrase refers. Our work argues that existing benchmarks…
Video object segmentation can be understood as a sequence-to-sequence task that can benefit from the curriculum learning strategies for better and faster training of deep neural networks. This work explores different schedule sampling and…
Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios. Both tasks benefit from decomposing a graphical model into an optimal…
Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2)…
Segmentation refinement aims to enhance the initial coarse masks generated by segmentation algorithms. The refined masks are expected to capture more details and better contours of the target objects. Research on segmentation refinement has…
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep…
Discriminative representation is essential to keep a unique identifier for each target in Multiple object tracking (MOT). Some recent MOT methods extract features of the bounding box region or the center point as identity embeddings.…
While multimodal large language models (MLLMs) have shown remarkable success across a wide range of tasks, long-form video understanding remains a significant challenge. In this study, we focus on video understanding by MLLMs. This task is…