Action Classification On Charades

评估指标

MAP

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
TokenLearner	66.3	TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
TubeViT-L	66.2	Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
MoViNet-A6	63.2	MoViNets: Mobile Video Networks for Efficient Video Recognition
DEEP-HAL with ODF+SDF (AssembleNet++)	62.29	Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors	-
AssembleNet++ 50	59.8	AssembleNet++: Assembling Modality Representations via Attention Connections
AssembleNet-101	58.6	AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
AssembleNet	58.6	AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
VicTR (ViT-L/14)	57.6	VicTR: Video-conditioned Text Representations for Activity Recognition	-
AssembleNet++ 50 without object	54.98	AssembleNet++: Assembling Modality Representations via Attention Connections
BIKE	50.7	Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
DEEP-HAL with ODF+SDF (I3D)	50.16	Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors	-
MoViNet-A4	48.5	MoViNets: Mobile Video Networks for Efficient Video Recognition
AdaFocus (weak supervision, MViT-B-24, 32x3)	47.8	Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition	-
MViT-B-24, 32x3 (Kinetics-600 pretraining)	47.7	Multiscale Vision Transformers
En-VidTr-L	47.3	VidTr: Video Transformer Without Convolutions	-
MViT-B, 32x3 (Kinetics-600 pretraining)	47.1	Multiscale Vision Transformers
MViT-B-24, 32x3 (Kinetics-400 pretraining)	46.3	Multiscale Vision Transformers
SlowFast (Kinetics-600 pretraining, NL)	45.2	SlowFast Networks for Video Recognition
ActionCLIP (ViT-B/16)	44.3	ActionCLIP: A New Paradigm for Video Action Recognition
MViT-B, 32x3 (Kinetics-400 pretraining)	44.3	Multiscale Vision Transformers

0 of 49 row(s) selected.