Video Segmentation
104 papers with code • 1 benchmarks • 9 datasets
Benchmarks
These leaderboards are used to track progress in Video Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Datasets
BDD100K
SegTrack-v2
Dynamic Replica
PP-HumanSeg14K
PETRAW
EgoProceL
TikTok Dataset
ConferenceVideoSegmentationDataset
Infinity Spills Basic Dataset
Subtasks
Latest papers
Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues.
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion.
Towards Temporally Consistent Referring Video Object Segmentation
bo-miao/HTR
•
•
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects.
UniVS: Unified and Universal Video Segmentation with Prompts as Queries
minghanli/univs
•
•
Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge.
PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM
Our primary novelty lies in PolypNextLSTM, which stands out as the leanest in parameters and the fastest model, surpassing the performance of five state-of-the-art image and video-based deep learning models.
We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline
simarkareer/unifiedvideoda
•
•
While the vast majority of prior work has studied this as a frame-level Image-DAS problem, a few Video-DAS works have sought to additionally leverage the temporal signal present in adjacent frames.
RAP-SAM: Towards Real-Time All-Purpose Segment Anything
Segment Anything Model (SAM) is one remarkable model that can achieve generalized segmentation.
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
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 (VSS), and video panoptic segmentation (VPS).
AutoVisual Fusion Suite: A Comprehensive Evaluation of Image Segmentation and Voice Conversion Tools on HuggingFace Platform
This study presents a comprehensive evaluation of tools available on the HuggingFace platform for two pivotal applications in artificial intelligence: image segmentation and voice conversion.
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
nust-machine-intelligence-laboratory/hgpu
•
•
However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene.
