Video Classification

Video Classification is the task of producing a label that is relevant to the video given its frames. A good video level classifier is one that not only provides accurate frame labels, but also best describes the entire video given the features and the annotations of the various frames in the video. For example, a video might contain a tree in some frame, but the label that is central to the video might be something else (e.g., “hiking”). The granularity of the labels that are needed to describe the frames and the video depends on the task. Typical tasks include assigning one or more global labels to the video, and assigning one or more labels for each frame inside the video.

Source: Efficient Large Scale Video Classification

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 276–300 of 455 papers

Title	Date	Tasks	Status	Hype
X3D: Expanding Architectures for Efficient Video Recognition	Apr 9, 2020	Action Classificationfeature selection	CodeCode Available	2
Revisiting Few-shot Activity Detection with Class Similarity Control	Mar 31, 2020	Action DetectionActivity Detection	—Unverified	0
Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction	Mar 27, 2020	Activity Recognition In VideosEvent data classification	CodeCode Available	1
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior	Mar 17, 2020	Adversarial AttackVideo Classification	CodeCode Available	1
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location	Mar 16, 2020	General Classificationimage-classification	CodeCode Available	1
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications	Mar 3, 2020	BenchmarkingGeneral Classification	CodeCode Available	1
VideoSSL: Semi-Supervised Learning for Video Classification	Feb 29, 2020	ClassificationGeneral Classification	—Unverified	0
Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks	Feb 12, 2020	Action ClassificationClassification	CodeCode Available	1
Learning spatio-temporal representations with temporal squeeze pooling	Feb 11, 2020	Action RecognitionClassification	—Unverified	0
FSD-10: A Dataset for Competitive Sports Content Analysis	Feb 9, 2020	Action RecognitionBenchmarking	—Unverified	0
iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention	Feb 7, 2020	General ClassificationVideo Classification	—Unverified	0
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification	Dec 17, 2019	ClassificationGeneral Classification	—Unverified	0
Appending Adversarial Frames for Universal Video Attack	Dec 10, 2019	ClassificationGeneral Classification	—Unverified	0
Video action detection by learning graph-based spatio-temporal interactions	Dec 9, 2019	Action DetectionAction Localization	CodeCode Available	0
VideoDG: Generalizing Temporal Relations in Videos to Novel Domains	Dec 8, 2019	Action RecognitionData Augmentation	CodeCode Available	0
DASZL: Dynamic Action Signatures for Zero-shot Learning	Dec 8, 2019	Action DetectionActivity Detection	—Unverified	0
A Multigrid Method for Efficiently Training Video Models	Dec 2, 2019	Action DetectionAction Recognition	CodeCode Available	1
A Spectral Nonlocal Block for Neural Networks	Nov 4, 2019	Action RecognitionFine-Grained Image Classification	—Unverified	0
Towards Train-Test Consistency for Semi-supervised Temporal Action Localization	Oct 24, 2019	Action LocalizationMultiple Instance Learning	—Unverified	0
Fast Non-Local Neural Networks with Spectral Residual Learning	Oct 15, 2019	Pose EstimationVideo Classification	CodeCode Available	0
AWSD: Adaptive Weighted Spatiotemporal Distillation for Video Representation	Oct 1, 2019	General ClassificationVideo Classification	—Unverified	0
UNIVERSAL MODAL EMBEDDING OF DYNAMICS IN VIDEOS AND ITS APPLICATIONS	Sep 25, 2019	DecoderTime Series	—Unverified	0
Spectral Nonlocal Block for Neural Network	Sep 25, 2019	Video Classification	—Unverified	0
Gated Channel Transformation for Visual Recognition	Sep 25, 2019	General Classificationimage-classification	CodeCode Available	0
Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks	Sep 16, 2019	Data AugmentationGeneral Classification	—Unverified	0

Show:10 25 50

← PrevPage 12 of 19Next →

All datasets Breakfast COIN MoB YouTube-8M Hockey Fight Detection Dataset Charades Home Action Genome Kinetics Multimodal PISA Something-Something V1 Something-Something V2 SRI-APPROVE Fine-Grained Video Classification

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	HERMES	Accuracy (%)	95.2	—	Unverified
2	MA-LMM	Accuracy (%)	93	—	Unverified
3	S5	Accuracy (%)	90.7	—	Unverified
4	TranS4mer	Accuracy (%)	90.27	—	Unverified
5	D-Sprv.	Accuracy (%)	89.9	—	Unverified
6	ViS4mer	Accuracy (%)	88.2	—	Unverified
7	GHRM	Accuracy (%)	75.5	—	Unverified
8	Timeception	Accuracy (%)	71.3	—	Unverified
9	VideoGraph	Accuracy (%)	69.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HERMES	Accuracy (%)	93.5	—	Unverified
2	MA-LMM	Accuracy (%)	93.2	—	Unverified
3	S5	Accuracy (%)	90.8	—	Unverified
4	D-Sprv.	Accuracy (%)	90	—	Unverified
5	TranS4mer	Accuracy (%)	89.3	—	Unverified
6	ViS4mer	Accuracy (%)	88.4	—	Unverified
7	TSN	Accuracy (%)	73.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	VTN	Accuracy	77.85	—	Unverified
2	I3D	Accuracy	72.11	—	Unverified
3	ConvLSTM	Accuracy	69.71	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DCGN (self-attention graph pooling)	Hit@1	87.7	—	Unverified
2	Hierarchical LSTM with MoE	Hit@1	86.8	—	Unverified
3	Mixture-of-2-Experts	Hit@1	70.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Structured Keypoint Pooling	Accuracy	99.5	—	Unverified
2	CNN+LSTM	1:1 Accuracy	98	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multigrid	mAP	38.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Cooperative Ours (3rd-person)	Accuracy (%)	24.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multigrid	Top-1	77.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Video	Accuracy (%)	73.95	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MSNet-R50En (ours)	Top-5 Accuracy	84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MSNet-R50En (ours)	Top-5 Accuracy	91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Label Prototypes Contrastive Learning	AUPR	88.4	—	Unverified