Related papers: Robust Promptable Video Object Segmentation
Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segmentation requiring reasoning with world knowledge. In this…
We introduce a one-shot learning approach for video object tracking. The proposed algorithm requires seeing the object to be tracked only once, and employs an external memory to store and remember the evolving features of the foreground…
Given an object mask, Semi-supervised Video Object Segmentation (SVOS) technique aims to track and segment the object across video frames, serving as a fundamental task in computer vision. Although recent memory-based methods demonstrate…
We target at the task of weakly-supervised video object grounding (WSVOG), where only video-sentence annotations are available during model learning. It aims to localize objects described in the sentence to visual regions in the video,…
Complex video object segmentation continues to face significant challenges in small object recognition, occlusion handling, and dynamic scene modeling. This report presents our solution, which ranked second in the MOSE track of CVPR 2025…
This paper strives for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. Existing referring video object datasets typically focus on…
The robustness of object detection models is a major concern when applied to real-world scenarios. The performance of most models tends to degrade when confronted with images affected by corruptions, since they are usually trained and…
Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the…
Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…
We introduce the challenging problem of multi-object system identification from videos, for which prior methods are ill-suited due to their focus on single-object scenes or discrete material classification with a fixed set of material…
In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in dense prediction tasks such as spatial-temporal video grounding…
Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc. Instead of addressing these nuances separately, we focus on building a generalizable solution…
Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world…
Video Object Segmentation and Tracking (VOST) presents a complex yet critical challenge in computer vision, requiring robust integration of segmentation and tracking across temporally dynamic frames. Traditional methods have struggled with…
Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks. Recent work has shown to perform on par with weaker levels of supervision in terms of…
A basic algorithmic task in automated video surveillance is to separate background and foreground objects. Camera tampering, noisy videos, low frame rate, etc., pose difficulties in solving the problem. A general approach that classifies…
Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this…
The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual…
This paper proposes a large-scale multi-modal dataset for referring motion expression video segmentation, focusing on segmenting and tracking target objects in videos based on language description of objects' motions. Existing referring…
The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks. Many existing defenses against these attacks, such as adversarial training, rely on full-model fine-tuning to induce robustness…