HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Video Salient Object Detection On Davis 2016

평가 지표

AVERAGE MAE

MAX F-MEASURE

S-Measure

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AVERAGE MAE	MAX F-MEASURE	S-Measure	Paper Title	Repository
RCRNet+NER	0.028	0.859	0.884	Semi-Supervised Video Salient Object Detection Using Pseudo-Labels	-
SAGM	0.105	-	0.664	Saliency-Aware Geodesic Video Object Segmentation	-
UFO	0.015	0.906	0.918	A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection	-
MSTM	0.174	-	0.566	Real-Time Salient Object Detection With a Minimum Spanning Tree
MB+M	0.173	-	0.600	Minimum Barrier Salient Object Detection at 80 FPS	-
TIMP	0.185	-	0.574	Time-Mapping Using Space-Time Saliency	-
MBNM	0.031	0.862	0.887	Unsupervised Video Object Segmentation with Motion-based Bilateral Networks	-
FGRN	0.043	0.783	0.838	Flow Guided Recurrent Neural Encoder for Video Salient Object Detection	-
RealFlow	0.010	0.939	0.945	Transforming Static Images Using Generative Models for Video Salient Object Detection	-
PDB	0.028	-	0.882	Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection	-
SSAV	0.028	0.861	0.893	Shifting More Attention to Video Salient Object Detection

0 of 11 row(s) selected.

Video Salient Object Detection On Davis 2016 | SOTA | HyperAI초신경