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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 455 papers

TitleStatusHype
Billion-scale semi-supervised learning for image classificationCode1
iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention—0
DynamoNet: Dynamic Action and Motion Network—0
AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction—0
Document-Level Sentiment Analysis of Urdu Text Using Deep Learning Techniques—0
DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark—0
AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction—0
Isometric Transformation Invariant Graph-based Deep Neural Network—0
AM Flow: Adapters for Temporal Processing in Action Recognition—0
Distributed Deep Convolutional Neural Networks for the Internet-of-Things—0
Discriminatively Trained Latent Ordinal Model for Video Classification—0
Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning—0
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification—0
Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning—0
IntFormer: Predicting pedestrian intention with the aid of the Transformer architecture—0
Defending Against Multiple and Unforeseen Adversarial Videos—0
A Unified Method for First and Third Person Action Recognition—0
Distribution Adaptive INT8 Quantization for Training CNNs—0
Deep Unsupervised Key Frame Extraction for Efficient Video Classification—0
Accurate and Efficient Two-Stage Gun Detection in Video—0
Deep-Temporal LSTM for Daily Living Action Recognition—0
Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception—0
I Have Seen Enough: A Teacher Student Network for Video Classification Using Fewer Frames—0
Automatic Concept Extraction for Concept Bottleneck-based Video Classification—0
AVD: Adversarial Video Distillation—0
Efficient Action Localization with Approximately Normalized Fisher Vectors—0
Attention-Aware Noisy Label Learning for Image Classification—0
Deep Multimodal Learning: An Effective Method for Video Classification—0
Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification—0
Deep Motion Features for Visual Tracking—0
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths—0
Identifying and Resisting Adversarial Videos Using Temporal Consistency—0
CNNs for JPEGs: A Study in Computational Cost—0
Attend and Interact: Higher-Order Object Interactions for Video Understanding—0
Attacking Automatic Video Analysis Algorithms: A Case Study of Google Cloud Video Intelligence API—0
Deep End2End Voxel2Voxel Prediction—0
Deep Discriminative Model for Video Classification—0
Higher-order Network for Action Recognition—0
Deep Architectures and Ensembles for Semantic Video Classification—0
DAiSEE: Towards User Engagement Recognition in the Wild—0
A Temporal Fusion Approach for Video Classification with Convolutional and LSTM Neural Networks Applied to Violence Detection—0
Aligning Correlation Information for Domain Adaptation in Action Recognition—0
Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning—0
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification—0
CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification—0
Co-training Transformer with Videos and Images Improves Action Recognition—0
A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP—0
Aggregating Frame-level Features for Large-Scale Video Classification—0
Convolutional Drift Networks for Video Classification—0
Active Learning for Video Classification with Frame Level Queries—0
Show:102550
← PrevPage 3 of 10Next →
All datasetsBreakfastCOINMoBYouTube-8MHockey Fight Detection DatasetCharadesHome Action GenomeKineticsMultimodal PISASomething-Something V1Something-Something V2SRI-APPROVE Fine-Grained Video Classification

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HERMESAccuracy (%)95.2—Unverified
2MA-LMMAccuracy (%)93—Unverified
3S5Accuracy (%)90.7—Unverified
4TranS4merAccuracy (%)90.27—Unverified
5D-Sprv.Accuracy (%)89.9—Unverified
6ViS4merAccuracy (%)88.2—Unverified
7GHRMAccuracy (%)75.5—Unverified
8TimeceptionAccuracy (%)71.3—Unverified
9VideoGraphAccuracy (%)69.5—Unverified
#ModelMetricClaimedVerifiedStatus
1HERMESAccuracy (%)93.5—Unverified
2MA-LMMAccuracy (%)93.2—Unverified
3S5Accuracy (%)90.8—Unverified
4D-Sprv.Accuracy (%)90—Unverified
5TranS4merAccuracy (%)89.3—Unverified
6ViS4merAccuracy (%)88.4—Unverified
7TSNAccuracy (%)73.4—Unverified
#ModelMetricClaimedVerifiedStatus
1VTNAccuracy77.85—Unverified
2I3DAccuracy72.11—Unverified
3ConvLSTMAccuracy69.71—Unverified
#ModelMetricClaimedVerifiedStatus
1DCGN (self-attention graph pooling)Hit@187.7—Unverified
2Hierarchical LSTM with MoEHit@186.8—Unverified
3Mixture-of-2-ExpertsHit@170.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy99.5—Unverified
2CNN+LSTM1:1 Accuracy98—Unverified
#ModelMetricClaimedVerifiedStatus
1MultigridmAP38.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Cooperative Ours (3rd-person)Accuracy (%)24.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MultigridTop-177.6—Unverified
#ModelMetricClaimedVerifiedStatus
1VideoAccuracy (%)73.95—Unverified
#ModelMetricClaimedVerifiedStatus
1MSNet-R50En (ours)Top-5 Accuracy84—Unverified
#ModelMetricClaimedVerifiedStatus
1MSNet-R50En (ours)Top-5 Accuracy91—Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Label Prototypes Contrastive LearningAUPR88.4—Unverified