OpenCodePapers

referring-expression-segmentation-on-davis

Referring Expression Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeJ&F 1st frameJ&F Full videoZero-Shot TransferJ&F scoreModelNameReleaseDate
Universal Instance Perception as Object Discovery and Retrieval✓ Link72.5UNINEXT-H2023-03-12
HyperSeg: Towards Universal Visual Segmentation with Large Language Model✓ Link71.2HyperSeg2024-11-26
Tracking Anything with Decoupled Video Segmentation✓ Link66.3DEVA (ReferFormer)2023-09-07
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory✓ Link65.6HTR2024-03-28
Spectrum-guided Multi-granularity Referring Video Object Segmentation✓ Link63.3SgMg2023-07-25
SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation61.3trueSafaRi-B2024-07-02
Language as Queries for Referring Video Object Segmentation✓ Link61.1ReferFormer2022-01-03
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation✓ Link60.9truePolyFormer-B2023-02-14
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark✓ Link51.63URVOS + Refer-Youtube-VOS + ft. DAVIS
Hierarchical interaction network for video object segmentation from referring expressions50.247.9HINet2021-11-22
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark✓ Link46.85URVOS + Refer-Youtube-VOS
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation✓ Link45.344.8RefVOS + SynthRef-YouTube-VIS2021-06-08
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation✓ Link45.1RefVOS2021-06-08
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation✓ Link44.545.1RefVOS2020-10-01
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark✓ Link44.1URVOS
Video Object Segmentation with Language Referring Expressions39.337.1Khoreva et al.2018-03-21
UniVS: Unified and Universal Video Segmentation with Prompts as Queries✓ Link59.4?59.4UniVS(Swin-L)2024-02-28
Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding✓ Link65.4VATEX2024-04-12
Check out how to contribute new results.