HyperAI초신경

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

한국어

시스템 설정

HyperAI초신경

Video Saliency Detection On Msu Video

평가 지표

AUC-J

CC

FPS

KLDiv

NSS

SIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AUC-J	CC	FPS	KLDiv	NSS	SIM	Paper Title	Repository
HD2S	0.844	0.707	24.51	0.545	1.89	0.615	Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction
ITTI	0.811	0.572	2.23	0.799	1.34	0.544	A model of saliency-based visual attention for rapid scene analysis	-
HFT	0.814	0.577	3.63	0.698	1.35	0.550	Visual Saliency Based on Scale-Space Analysis in the Frequency Domain	-
DINet	0.858	0.671	4.85	0.575	1.85	0.592	A Dilated Inception Network for Visual Saliency Prediction
GBVS	0.810	0.572	1.93	0.709	1.33	0.546	Graph-Based Visual Saliency	-
SalEMA	0.821	0.636	32.97	0.647	1.63	0.571	Simple vs complex temporal recurrences for video saliency prediction
STRA-Net	0.841	0.665	3.35	0.583	1.81	0.591	Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
ACLNet	0.839	0.651	4.18	0.593	1.71	0.586	Revisiting Video Saliency: A Large-scale Benchmark and a New Model
ViNet (dave)	0.864	0.733	1.10	0.497	2.13	0.627	ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction
TASED-Net	0.852	0.710	1.85	0.538	1.96	0.610	TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection
DeepVS	0.804	0.586	3.29	0.707	1.44	0.548	DeepVS: A Deep Learning Based Video Saliency Prediction Approach
UNISAL (videos)	0.858	0.707	70.46	0.536	2.03	0.609	Unified Image and Video Saliency Modeling
MSI-Net (dutomron)	0.852	0.690	1.28	0.537	1.82	0.607	Contextual Encoder-Decoder Network for Visual Saliency Prediction
GASP	0.810	0.613	3.77	0.687	1.57	0.557	GASP: Gated Attention For Saliency Prediction

0 of 14 row(s) selected.