HyperAIHyperAI초신경

Command Palette

Search for a command to run...

플랫폼

Visual Object Tracking On Davis 2017

평가 지표

F-measure (Mean)
Ju0026F
Jaccard (Mean)
Params(M)
Speed (FPS)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
SAM2-90.7-224.4-SAM 2: Segment Anything in Images and Videos
Cutie+ (base)93.490.587.517.9-Putting the Object Back into Video Object Segmentation
ISVOS (BL30K, MS)93.089.886.7--Look Before You Match: Instance Understanding Matters in Video Object Segmentation
XMem (BL30K, MS)92.689.586.3--XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
ISVOS (MS)-88.685.8--Look Before You Match: Instance Understanding Matters in Video Object Segmentation
XMem (MS)91.088.285.4--XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
ISVOS (BL30K)91.988.284.5--Look Before You Match: Instance Understanding Matters in Video Object Segmentation
Cutie+ (base, MEGA)90.888.185.5-17.9Putting the Object Back into Video Object Segmentation
JIMD91.088.185.2--Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation
Cutie (base)91.187.984.636.4-Putting the Object Back into Video Object Segmentation
XMem (BL30K)91.487.784.0-22.6XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
DEVA91.087.684.2-25.3Tracking Anything with Decoupled Video Segmentation
SwinB-AOTv2-L (MS)89.887.084.265.61.3Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOST (L'=3, MS)89.586.783.865.61.3Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOTv2-L89.486.383.165.612.0Scalable Video Object Segmentation with Identification Mechanism
XMem89.586.282.9-22.6XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
SwinB-DeAOT-L89.286.283.170.315.4Decoupling Features in Hierarchical Propagation for Video Object Segmentation
RAVOS89.386.182.9-42 (on 3090)Region Aware Video Object Segmentation with Deep Motion Modeling
QDMN88.685.682.5--Learning Quality-aware Dynamic Memory for Video Object Segmentation
R50-AOST (L'=3)88.585.682.615.417.5Scalable Video Object Segmentation with Identification Mechanism
0 of 82 row(s) selected.
Visual Object Tracking On Davis 2017 | SOTA | HyperAI초신경