Action Recognition

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 2301–2325 of 2759 papers

Title	Date	Tasks	Status	Hype
Distributed non-parametric deep and wide networks	Jan 1, 2018	Action RecognitionGaussian Processes	—Unverified	0
A Unified Method for First and Third Person Action Recognition	Dec 30, 2017	Action RecognitionGeneral Classification	—Unverified	0
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization	Dec 26, 2017	Action ClassificationAction Localization	CodeCode Available	0
On the Integration of Optical Flow and Action Recognition	Dec 22, 2017	Action RecognitionOptical Flow Estimation	—Unverified	0
Human Action Recognition: Pose-based Attention draws focus to Hands	Dec 20, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition	Dec 14, 2017	Action RecognitionAction Recognition In Videos	—Unverified	0
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification	Dec 13, 2017	Action ClassificationAction Detection	CodeCode Available	0
Deception Detection in Videos	Dec 12, 2017	Action RecognitionDeception Detection	—Unverified	0
Im2Flow: Motion Hallucination from Static Images for Action Recognition	Dec 12, 2017	Action RecognitionActivity Recognition	CodeCode Available	0
Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition	Dec 5, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions	Dec 4, 2017	3D Action RecognitionAction Recognition	—Unverified	0
Multimodal Visual Concept Learning with Weakly Supervised Techniques	Dec 3, 2017	Action RecognitionDescriptive	CodeCode Available	0
Compressed Video Action Recognition	Dec 2, 2017	Action ClassificationAction Recognition	CodeCode Available	0
Label Efficient Learning of Transferable Representations acrosss Domains and Tasks	Dec 1, 2017	Action RecognitionMetric Learning	—Unverified	0
Label Efficient Learning of Transferable Representations across Domains and Tasks	Nov 30, 2017	Action RecognitionMetric Learning	—Unverified	0
A Closer Look at Spatiotemporal Convolutions for Action Recognition	Nov 30, 2017	Action ClassificationAction Recognition	CodeCode Available	1
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition	Nov 29, 2017	Action RecognitionAction Recognition In Videos	CodeCode Available	0
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN Features	Nov 28, 2017	Action RecognitionActivity Recognition	CodeCode Available	0
Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories	Nov 28, 2017	Action RecognitionTemporal Action Localization	CodeCode Available	0
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks	Nov 28, 2017	Action RecognitionPhilosophy	CodeCode Available	1
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines	Nov 28, 2017	3D Action RecognitionAction Recognition	—Unverified	0
Highly Efficient Human Action Recognition with Quantum Genetic Algorithm Optimized Support Vector Machine	Nov 27, 2017	Action ClassificationAction Recognition	—Unverified	0
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?	Nov 27, 2017	Action Recognition	CodeCode Available	2
Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction	Nov 25, 2017	Action RecognitionRepresentation Learning	—Unverified	0
Appearance-and-Relation Networks for Video Classification	Nov 24, 2017	Action ClassificationAction Recognition	CodeCode Available	0

Show:10 25 50

← PrevPage 93 of 111Next →

All datasets Something-Something V2 UCF101 HMDB-51 Something-Something V1 AVA v2.2 EPIC-KITCHENS-100 NTU RGB+D NTU RGB+D 120 Diving-48 ActivityNet AVA v2.1 H2O (2 Hands and Objects)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MViTv2-B (IN-21K + Kinetics400 pretrain)	Top-5 Accuracy	93.4	—	Unverified
2	RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)	Top-5 Accuracy	91.1	—	Unverified
3	MVD (Kinetics400 pretrain, ViT-H, 16 frame)	Top-1 Accuracy	77.3	—	Unverified
4	DejaVid	Top-1 Accuracy	77.2	—	Unverified
5	InternVideo	Top-1 Accuracy	77.2	—	Unverified
6	InternVideo2-1B	Top-1 Accuracy	77.1	—	Unverified
7	VideoMAE V2-g	Top-1 Accuracy	77	—	Unverified
8	MVD (Kinetics400 pretrain, ViT-L, 16 frame)	Top-1 Accuracy	76.7	—	Unverified
9	Hiera-L (no extra data)	Top-1 Accuracy	76.5	—	Unverified
10	TubeViT-L	Top-1 Accuracy	76.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FTP-UniFormerV2-L/14	3-fold Accuracy	99.7	—	Unverified
2	OmniVec2	3-fold Accuracy	99.6	—	Unverified
3	VideoMAE V2-g	3-fold Accuracy	99.6	—	Unverified
4	OmniVec	3-fold Accuracy	99.6	—	Unverified
5	BIKE	3-fold Accuracy	98.8	—	Unverified
6	SMART	3-fold Accuracy	98.64	—	Unverified
7	OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)	3-fold Accuracy	98.6	—	Unverified
8	PERF-Net (multi-distilled S3D)	3-fold Accuracy	98.6	—	Unverified
9	ZeroI2V ViT-L/14	3-fold Accuracy	98.6	—	Unverified
10	LGD-3D Two-stream	3-fold Accuracy	98.2	—	Unverified