SOTAVerified

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

Showing 251300 of 455 papers

TitleStatusHype
Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations0
Defending Against Multiple and Unforeseen Adversarial Videos0
Active Contrastive Learning of Audio-Visual Video RepresentationsCode1
Making a Case for 3D Convolutions for Object Segmentation in VideosCode1
Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation0
Self-Supervised Multi-Task Procedure Learning from Instructional Videos0
Actor-Action Video Classification CSC 249/449 Spring 2020 Challenge ReportCode0
Approximated Bilinear Modules for Temporal ModelingCode1
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification0
Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos0
MotionSqueeze: Neural Motion Feature Learning for Video UnderstandingCode1
Region-based Non-local Operation for Video ClassificationCode1
3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels0
Generalized Few-Shot Video Classification with Video Retrieval and Feature GenerationCode1
NLP-based Feature Extraction for the Detection of COVID-19 Misinformation Videos on YouTubeCode0
SmallBigNet: Integrating Core and Contextual Views for Video ClassificationCode1
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual RecognitionCode1
Learn to cycle: Time-consistent feature discovery for action recognitionCode0
Video Understanding as Machine Translation0
Non-Local Neural Networks With Grouped Bilinear Attentional TransformsCode1
Optimizing Temporal Convolutional Network inference on FPGA-based accelerators0
Video Contents Understanding using Deep Neural Networks0
PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-SpoofingCode1
TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition0
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?Code2
X3D: Expanding Architectures for Efficient Video RecognitionCode2
Revisiting Few-shot Activity Detection with Class Similarity Control0
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Motion-Excited Sampler: Video Adversarial Attack with Sparked PriorCode1
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial LocationCode1
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic ApplicationsCode1
VideoSSL: Semi-Supervised Learning for Video Classification0
Over-the-Air Adversarial Flickering Attacks against Video Recognition NetworksCode1
Learning spatio-temporal representations with temporal squeeze pooling0
FSD-10: A Dataset for Competitive Sports Content Analysis0
iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention0
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification0
Appending Adversarial Frames for Universal Video Attack0
Video action detection by learning graph-based spatio-temporal interactionsCode0
VideoDG: Generalizing Temporal Relations in Videos to Novel DomainsCode0
DASZL: Dynamic Action Signatures for Zero-shot Learning0
A Multigrid Method for Efficiently Training Video ModelsCode1
A Spectral Nonlocal Block for Neural Networks0
Towards Train-Test Consistency for Semi-supervised Temporal Action Localization0
Fast Non-Local Neural Networks with Spectral Residual LearningCode0
AWSD: Adaptive Weighted Spatiotemporal Distillation for Video Representation0
UNIVERSAL MODAL EMBEDDING OF DYNAMICS IN VIDEOS AND ITS APPLICATIONS0
Spectral Nonlocal Block for Neural Network0
Gated Channel Transformation for Visual RecognitionCode0
Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks0
Show:102550
← PrevPage 6 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HERMESAccuracy (%)95.2Unverified
2MA-LMMAccuracy (%)93Unverified
3S5Accuracy (%)90.7Unverified
4TranS4merAccuracy (%)90.27Unverified
5D-Sprv.Accuracy (%)89.9Unverified
6ViS4merAccuracy (%)88.2Unverified
7GHRMAccuracy (%)75.5Unverified
8TimeceptionAccuracy (%)71.3Unverified
9VideoGraphAccuracy (%)69.5Unverified
#ModelMetricClaimedVerifiedStatus
1HERMESAccuracy (%)93.5Unverified
2MA-LMMAccuracy (%)93.2Unverified
3S5Accuracy (%)90.8Unverified
4D-Sprv.Accuracy (%)90Unverified
5TranS4merAccuracy (%)89.3Unverified
6ViS4merAccuracy (%)88.4Unverified
7TSNAccuracy (%)73.4Unverified
#ModelMetricClaimedVerifiedStatus
1VTNAccuracy77.85Unverified
2I3DAccuracy72.11Unverified
3ConvLSTMAccuracy69.71Unverified
#ModelMetricClaimedVerifiedStatus
1DCGN (self-attention graph pooling)Hit@187.7Unverified
2Hierarchical LSTM with MoEHit@186.8Unverified
3Mixture-of-2-ExpertsHit@170.1Unverified
#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy99.5Unverified
2CNN+LSTM1:1 Accuracy98Unverified
#ModelMetricClaimedVerifiedStatus
1MultigridmAP38.2Unverified
#ModelMetricClaimedVerifiedStatus
1Cooperative Ours (3rd-person)Accuracy (%)24.7Unverified
#ModelMetricClaimedVerifiedStatus
1MultigridTop-177.6Unverified
#ModelMetricClaimedVerifiedStatus
1VideoAccuracy (%)73.95Unverified
#ModelMetricClaimedVerifiedStatus
1MSNet-R50En (ours)Top-5 Accuracy84Unverified
#ModelMetricClaimedVerifiedStatus
1MSNet-R50En (ours)Top-5 Accuracy91Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Label Prototypes Contrastive LearningAUPR88.4Unverified