SOTAVerified

Activity Detection

Detecting activities in extended videos.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 380 papers

TitleStatusHype
Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads—0
Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation—0
The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description—0
KIDS: kinematics-based (in)activity detection and segmentation in a sleep case study—0
Activity Detection for Grant-Free NOMA in Massive IoT Networks—0
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks—0
Trajectory-User Linking Is Easier Than You Think—0
BC-VAD: A Robust Bone Conduction Voice Activity Detection—0
Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks—0
Joint Estimation of Clustered User Activity and Correlated Channels with Unknown Covariance in mMTC—0
Multi-timescale Event Detection in Nonintrusive Load Monitoring based on MDL Principle—0
Token Turing Machines—0
On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches—0
Two-stream Multi-dimensional Convolutional Network for Real-time Violence Detection—0
OFDM-Based Massive Connectivity for LEO Satellite Internet of Things—0
Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction—0
Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition—0
TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge—0
Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization—0
The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022—0
Learnable Acoustic Frontends in Bird Activity Detection—0
Signed Latent Factors for Spamming Activity Detection—0
Joint Speech Activity and Overlap Detection with Multi-Exit Architecture—0
The Kriston AI System for the VoxCeleb Speaker Recognition Challenge 2022—0
Cross-domain Voice Activity Detection with Self-Supervised Representations—0
Show:102550
← PrevPage 7 of 16Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CNN-BiLSTM_bestROC-AUC95.14—Unverified
2CNN-BiLSTM_smallROC-AUC95.13—Unverified
3SG-VAD (ours)ROC-AUC94.3—Unverified
4ADA-VADROC-AUC79.1—Unverified