Referring Expression Segmentation On J Hmdb

评估指标

IoU mean

IoU overall

Precision@0.5

Precision@0.6

Precision@0.7

Precision@0.8

Precision@0.9

评测结果

各个模型在此基准测试上的表现结果

									Paper Title	Repository
SgMg (Video-Swin-B)	0.450	0.725	0.737	0.972	0.917	0.714	0.225	0.003	Spectrum-guided Multi-granularity Referring Video Object Segmentation
SOC (Video-Swin-B)	0.446	0.723	0.736	0.969	0.914	0.711	0.213	0.001	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
SOC (Video-Swin-T)	0.397	0.701	0.707	0.947	0.864	0.627	0.179	0.001	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
MTTR (w=10)	0.392	0.698	0.701	0.939	0.852	0.616	0.166	0.001	End-to-End Referring Video Object Segmentation with Multimodal Transformers
MTTR (w=8)	0.366	0.679	0.674	0.91	0.815	0.57	0.144	0.001	End-to-End Referring Video Object Segmentation with Multimodal Transformers
ClawCraneNet	-	0.655	0.644	0.880	0.796	0.566	0.147	0.002	ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation	-
VLIDE	0.441	0.666	0.68	0.874	0.791	0.586	0.182	0.30	Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation	-
HINet	-	0.627	0.652	0.819	0.736	0.542	0.168	0.4	Hierarchical interaction network for video object segmentation from referring expressions	-
CMPC-V	0.342	0.617	0.616	0.813	0.657	0.371	0.07	0.000	Cross-Modal Progressive Comprehension for Referring Segmentation
Hui et al.	0.335	0.604	0.598	0.783	0.639	0.378	0.076	0.000	Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation	-
AAMN	0.321	0.576	0.583	0.773	0.627	0.360	0.044	0.000	Actor and Action Modular Network for Text-based Video Segmentation	-
CMSA+CFSA	-	0.581	0.628	0.764	0.625	0.389	0.09	0.001	Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network	-
ACGA	0.289	0.584	0.576	0.756	0.564	0.287	0.034	0.000	Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query	-
CMDy	0.301	0.576	0.554	0.742	0.587	0.316	0.047	0.000	Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries	-
RefVOS	-	0.568	0.606	0.731	0.62	0.392	0.088	0.0	Hierarchical interaction network for video object segmentation from referring expressions	-
Gavrilyuk et al. (Optical flow)	0.267	0.570	0.555	0.712	0.518	0.264	0.030	0.000	Actor and Action Video Segmentation from a Sentence
Gavrilyuk et al.	0.233	0.542	0.541	0.699	0.460	0.173	0.014	0.000	Actor and Action Video Segmentation from a Sentence
VT-Capsule	0.261	0.550	0.535	0.677	0.513	0.283	0.051	0.000	Visual-Textual Capsule Routing for Text-Based Video Segmentation	-
Hu et al.	0.178	0.528	0.546	0.633	0.350	0.085	0.002	0.000	Segmentation from Natural Language Expressions
Li et al.	0.173	0.491	0.529	0.578	0.335	0.103	0.060	0.000	Tracking by Natural Language Specification	-

0 of 21 row(s) selected.

Command Palette

Referring Expression Segmentation On J Hmdb

评估指标

评测结果