Related papers: The 2nd Solution for LSVOS Challenge RVOS Track: S…
Audio-based Referring Video Object Segmentation (ARVOS) requires grounding audio queries into pixel-level object masks over time, posing challenges in bridging acoustic signals with spatio-temporal visual representations. In this report, we…
Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…
Video object segmentation (VOS) is a critical task in the development of video perception and understanding. The Segment-Anything Model 2 (SAM 2), released by Meta AI, is the current state-of-the-art architecture for end-to-end VOS. SAM 2…
Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately trimmed videos, with text-referred objects always appearing…
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…
Complex video object segmentation serves as a fundamental task for a wide range of downstream applications such as video editing and automatic data annotation. Here we present the 2nd place solution in the MOSE track of PVUW 2024. To…
Motion expression video segmentation is designed to segment objects in accordance with the input motion expressions. In contrast to the conventional Referring Video Object Segmentation (RVOS), it places emphasis on motion as well as…
Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment…
We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to…
Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we…
Audio-based video object segmentation aims to locate and segment objects in videos conditioned on audio cues, requiring precise understanding of both appearance and motion. Recent audio-driven video segmentation methods extend MLLMs by…
Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video, emphasizing modeling dense text-video relations. The current RVOS methods typically use independently pre-trained vision…
Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear motion. Recent vision…
Large vision models like the Segment Anything Model (SAM) exhibit significant limitations when applied to downstream tasks in the wild. Consequently, reference segmentation, which leverages reference images and their corresponding masks to…
Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal…
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report, we present further improvements to the SOTA VIS method,…
Conventional approaches to video segmentation are confined to predefined object categories and cannot identify out-of-vocabulary objects, let alone objects that are not identified explicitly but only referred to implicitly in complex text…
Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference. Previous methods typically tackle RVOS through directly grounding linguistic reference over the image lattice. Such…
We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations. Towards this goal, we present…
Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency…