Related papers: TIVE: A Toolbox for Identifying Video Instance Seg…
In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method. The first step performs instance segmentation for each frame to get a large number of instance mask proposals. The…
There is limited understanding of the information captured by deep spatiotemporal models in their intermediate representations. For example, while evidence suggests that action recognition algorithms are heavily influenced by visual…
Existing learning-based solutions to medical image segmentation have two important shortcomings. First, for most new segmentation task, a new model has to be trained or fine-tuned. This requires extensive resources and machine learning…
We present an approach to semi-supervised video object segmentation, in the context of the DAVIS 2017 challenge. Our approach combines category-based object detection, category-independent object appearance segmentation and temporal object…
Referring Image Segmentation (RIS) aims to segment a target object described by a natural language expression. Existing methods have evolved by leveraging the vision information into the language tokens. To more effectively exploit visual…
Video Instance Segmentation (VIS) fundamentally struggles with pervasive challenges including object occlusions, motion blur, and appearance variations during temporal association. To overcome these limitations, this work introduces…
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, time-consuming in training…
Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a videos. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown robust zero-shot…
Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing. However, the recent success of online methods questions this…
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. However, since the…
Video foreground segmentation (VFS) is an important computer vision task wherein one aims to segment the objects under motion from the background. Most of the current methods are image-based, i.e., rely only on spatial cues while ignoring…
Video instance segmentation is a complex task in which we need to detect, segment, and track each object for any given video. Previous approaches only utilize single-frame features for the detection, segmentation, and tracking of objects…
Medical video segmentation gains increasing attention in clinical practice due to the redundant dynamic references in video frames. However, traditional convolutional neural networks have a limited receptive field and transformer-based…
Visible and Infrared Image Fusion (VIF) has garnered significant interest across a wide range of high-level vision tasks, such as object detection and semantic segmentation. However, the evaluation of VIF methods remains challenging due to…
In this work, we present a new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are…
Recently, transformer-based methods have achieved impressive results on Video Instance Segmentation (VIS). However, most of these top-performing methods run in an offline manner by processing the entire video clip at once to predict…
We propose a novel end-to-end solution for video instance segmentation (VIS) based on transformers. Recently, the per-clip pipeline shows superior performance over per-frame methods leveraging richer information from multiple frames.…
The recent advancement in Video Instance Segmentation (VIS) has largely been driven by the use of deeper and increasingly data-hungry transformer-based models. However, video masks are tedious and expensive to annotate, limiting the scale…
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is directly supervised by the contrastive loss computed upon the…
Multiple-instance learning (MIL) is a paradigm of machine learning that aims to classify a set (bag) of objects (instances), assigning labels only to the bags. This problem is often addressed by selecting an instance to represent each bag,…