SOTAVerified

Action Detection

Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 751–800 of 817 papers

TitleStatusHype
Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos—0
Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks—0
GateHUB: Gated History Unit with Background Suppression for Online Action Detection—0
GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge—0
Grant-Free Access via Bilinear Inference for Cell-Free MIMO with Low-Coherent Pilots—0
Grant-free Massive Random Access with Retransmission: Receiver Optimization and Performance Analysis—0
Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection—0
Group Activity Detection from Trajectory and Video Data in Soccer—0
Group Event Detection with a Varying Number of Group Members for Video Surveillance—0
GTTS-EHU Systems for QUESST at MediaEval 2014—0
Hand Action Detection from Ego-centric Depth Sequences with Error-correcting Hough Transform—0
Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices—0
Hierarchical Graph-RNNs for Action Detection of Multiple Activities—0
Hierarchical MTC User Activity Detection and Channel Estimation with Unknown Spatial Covariance—0
Hierarchical Self-Attention Network for Action Localization in Videos—0
High-speed Low-consumption sEMG-based Transient-state micro-Gesture Recognition—0
Human Attention Detection Using AM-FM Representations—0
Human-to-Human Interaction Detection—0
Hybrid Active Learning via Deep Clustering for Video Action Detection—0
Identity-aware Graph Memory Network for Action Detection—0
Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing—0
Improve Temporal Action Proposals using Hierarchical Context—0
Improving Action Localization by Progressive Cross-stream Cooperation—0
Improving endpoint detection in end-to-end streaming ASR for conversational speech—0
Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition—0
Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications—0
Accelerating temporal action proposal generation via high performance computing—0
Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads—0
Indoor Activity Detection and Recognition for Sport Games Analysis—0
In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms—0
Preemptive Detection and Correction of Misaligned Actions in LLM Agents—0
Information Elevation Network for Fast Online Action Detection—0
Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization—0
Intelligent Reflecting Surface for Massive Device Connectivity: Joint Activity Detection and Channel Estimation—0
Intelligent Video Recording Optimization using Activity Detection for Surveillance Systems—0
Introducing Gating and Context into Temporal Action Detection—0
Introducing SSBD+ Dataset with a Convolutional Pipeline for detecting Self-Stimulatory Behaviours in Children using raw videos—0
Investigation of Speaker Representation for Target-Speaker Speech Processing—0
Iterative Reweighted Algorithms for Joint User Identification and Channel Estimation in Spatially Correlated Massive MTC—0
結合I-Vector 及深層神經網路之語者驗證系統 (Text-independent Speaker Verification using a Hybrid I-Vector/DNN Approach) [In Chinese]—0
JARViS: Detecting Actions in Video Using Unified Actor-Scene Context Relation Modeling—0
JOADAA: joint online action detection and action anticipation—0
Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access—0
Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access: A Free Probability Theory Approach—0
Joint Activity Detection and Channel Estimation for Clustered Massive Machine Type Communications—0
Joint Activity Detection and Channel Estimation for Massive Connectivity: Where Message Passing Meets Score-Based Generative Priors—0
Joint Activity Detection and Data Decoding in Massive Random Access via a Turbo Receiver—0
Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-free Massive Random Access—0
Joint Channel Estimation and Device Activity Detection in Heterogeneous Networks—0
Joint Estimation of Clustered User Activity and Correlated Channels with Unknown Covariance in mMTC—0
Show:102550
← PrevPage 16 of 17Next →
All datasetsUCF101-24J-HMDBCharadesMulti-THUMOSUCF SportsTHUMOS' 14MultiSportsTSUTTStroke-21 ME21TTStroke-21 ME22MultiTHUMOS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1STAR/LFrame-mAP 0.590.3—Unverified
2SiAFrame-mAP 0.588.5—Unverified
3YOWO + LFBFrame-mAP 0.587.3—Unverified
4HITFrame-mAP 0.584.8—Unverified
5HISAN (ResNet-101 + FPN)Video-mAP 0.282.3—Unverified
6YOWOFrame-mAP 0.580.4—Unverified
7Two-in-one Two StreamVideo-mAP 0.278.48—Unverified
8MOCFrame-mAP 0.577.8—Unverified
9Faster-RCNN + two-stream I3D convFrame-mAP 0.576.3—Unverified
10Two-in-oneVideo-mAP 0.275.48—Unverified
#ModelMetricClaimedVerifiedStatus
1SiAFrame-mAP 0.588.5—Unverified
2HISAN (ResNet-101 + FPN)Video-mAP 0.287.59—Unverified
3HITFrame-mAP 0.583.8—Unverified
4HISAN (VGG-16)Frame-mAP 0.576.72—Unverified
5DTSVideo-mAP 0.276.1—Unverified
6YOWO + LFBFrame-mAP 0.575.7—Unverified
7Two-in-one Two StreamVideo-mAP 0.574.74—Unverified
8YOWOFrame-mAP 0.574.4—Unverified
9MOCFrame-mAP 0.574—Unverified
10Faster-RCNN + two-stream I3D convFrame-mAP 0.573.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TTMmAP28.79—Unverified
2CTRNmAP27.8—Unverified
3Coarse-Fine Networks (w/ self-supervised detection pretraining)mAP26.95—Unverified
4UniMD+Sync. (RGB+Flow)mAP26.53—Unverified
5PDAN (RGB+Flow)mAP26.5—Unverified
6PATmAP26.5—Unverified
7MS-TCT (RGB only)mAP25.4—Unverified
83D ResNet-50 + super-events pretrained on AViDmAP25.2—Unverified
9Coarse-Fine NetworksmAP25.1—Unverified
10MLAD (RGB + Flow)mAP23.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MLADmAP51.5—Unverified
2CTRNmAP51.2—Unverified
3PDANmAP47.6—Unverified
4TGMmAP46.4—Unverified
5MS-TCT (RGB only)mAP43.1—Unverified
6I3D + our super-eventmAP36.4—Unverified
7Two-stream + LSTMmAP28.1—Unverified
8Two-streammAP27.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Two-in-one Two StreamVideo-mAP 0.596.52—Unverified
2DTSVideo-mAP 0.294.3—Unverified
3Two-in-oneVideo-mAP 0.592.74—Unverified
4T-CNNFrame-mAP 0.586.7—Unverified
5MR-TS R-CNNFrame-mAP 0.584.52—Unverified
6TS R-CNNFrame-mAP 0.582.3—Unverified
7Action TubesFrame-mAP 0.568.1—Unverified
#ModelMetricClaimedVerifiedStatus
1MAT (Ours) TransmAP71.6—Unverified
2TadML-two streammAP59.7—Unverified
3MAT (ours)mAP58.2—Unverified
4TadML-rgbmAP53.46—Unverified
#ModelMetricClaimedVerifiedStatus
1HITFrame-mAP 0.533.3—Unverified
2SiAFrame-mAP 0.528.8—Unverified
#ModelMetricClaimedVerifiedStatus
1MS-TCTFrame-mAP33.7—Unverified
2PDANFrame-mAP32.7—Unverified
#ModelMetricClaimedVerifiedStatus
1STCNNIoU0.14—Unverified
2Two Stream NetworkIoU0.07—Unverified
#ModelMetricClaimedVerifiedStatus
1STCNN-V2 (Vote decision)IoU0.52—Unverified
2RGB and PRGBIoU0.35—Unverified
#ModelMetricClaimedVerifiedStatus
1PATmAP44.6—Unverified