Action Classification On Moments In Time

评估指标

Top 1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
OmniVec2	53.1	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
InternVideo2-1B	50.9	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
UMT-L (ViT-L/16)	48.7	Unmasked Teacher: Towards Training-Efficient Video Foundation Models
UniFormerV2-L	47.8	UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer	-
MTV-H (WTS 60M)	47.2	Multiview Transformers for Video Recognition
CoVeR(JFT-3B)	46.1	Co-training Transformer with Videos and Images Improves Action Recognition	-
CoVeR(JFT-300M)	45.0	Co-training Transformer with Videos and Images Improves Action Recognition	-
VATT-Large	41.1	VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
MoViNet-A6	40.2	MoViNets: Mobile Video Networks for Efficient Video Recognition
MoViNet-A5	39.1	MoViNets: Mobile Video Networks for Efficient Video Recognition
MoViNet-A4	37.9	MoViNets: Mobile Video Networks for Efficient Video Recognition
VTN	37.4	Video Transformer Network
MBT (AV)	37.3	Attention Bottlenecks for Multimodal Fusion
MoViNet-A3	35.6	MoViNets: Mobile Video Networks for Efficient Video Recognition
MoViNet-A2	34.3	MoViNets: Mobile Video Networks for Efficient Video Recognition
AssembleNet	34.27%	AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
SRTG r3d-101	33.56	Learn to cycle: Time-consistent feature discovery for action recognition
CoST (ResNet-101, 32 frames)	32.4%	Collaborative Spatiotemporal Feature Learning for Video Action Recognition	-
MoViNet-A1	32.0	MoViNets: Mobile Video Networks for Efficient Video Recognition
EvaNet	31.8%	Evolving Space-Time Neural Architectures for Videos	-

0 of 29 row(s) selected.