SOTAVerified

Temporal Action Localization

Temporal Action Localization aims to detect activities in the video stream and output beginning and end timestamps. It is closely related to Temporal Action Proposal Generation.

Papers

Showing 276300 of 1477 papers

TitleStatusHype
Actor and Observer: Joint Modeling of First and Third-Person VideosCode0
Audio-Visual Model Distillation Using Acoustic ImagesCode0
ActivityNet: A Large-Scale Video Benchmark for Human Activity UnderstandingCode0
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer VisionCode0
Attentive Semantic Video Generation using CaptionsCode0
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action LocalizationCode0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual LearningCode0
Out-of-Distribution Detection for Generalized Zero-Shot Action RecognitionCode0
Im2Flow: Motion Hallucination from Static Images for Action RecognitionCode0
Attentional Pooling for Action RecognitionCode0
Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial SensorsCode0
Asynchronous Temporal Fields for Action RecognitionCode0
Human activity recognition from skeleton posesCode0
A Bag-of-Words Equivalent Recurrent Neural Network for Action RecognitionCode0
Human Action Recognition by Representing 3D Skeletons as Points in a Lie GroupCode0
I3D-LSTM: A New Model for Human Action RecognitionCode0
High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action RecognitionCode0
Hierarchical Explanations for Video Action RecognitionCode0
Temporal Unet: Sample Level Human Action Recognition using WiFiCode0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA DevicesCode0
Action Tubelet Detector for Spatio-Temporal Action LocalizationCode0
A Simple Transformer-Based Model for Ego4D Natural Language Queries ChallengeCode0
Show:102550
← PrevPage 12 of 60Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AdaTAD (VideoMAEv2-giant)Avg mAP (0.3:0.7)76.9Unverified
2RDFA-S6 (InternVideo2-6B)Avg mAP (0.3:0.7)74.2Unverified
3ActionMamba(InternVideo2-6B)Avg mAP (0.3:0.7)72.72Unverified
4GCMmAP IOU@0.172.5Unverified
5AGT (Ours)mAP IOU@0.172.1Unverified
6InternVideo2-6BAvg mAP (0.3:0.7)72Unverified
7ActionFormer (InternVideo features)Avg mAP (0.3:0.7)71.58Unverified
8TriDet (VideoMAE v2-g feature)Avg mAP (0.3:0.7)70.1Unverified
9InternVideo2-1BAvg mAP (0.3:0.7)69.8Unverified
10ActionFormer (VideoMAE V2-g features)Avg mAP (0.3:0.7)69.6Unverified
#ModelMetricClaimedVerifiedStatus
1UnLoc-LmAP IOU@0.559.3Unverified
2RDFA-S6 (InternVideo2-6B)mAP42.9Unverified
3ActionMamba (InternVideo2-6B)mAP42.02Unverified
4PRN+BMN (ensemble)mAP42Unverified
5AdaTAD (VideoMAEv2-giant)mAP41.93Unverified
6InternVideo2-6BmAP41.2Unverified
7InternVideo2-1BmAP40.4Unverified
8UniMD+Sync.mAP39.83Unverified
9PRN (CSN)mAP39.4Unverified
10InternVideomAP39Unverified
#ModelMetricClaimedVerifiedStatus
1RDFA-S6 (InternVideo2-6B)Average-mAP45.8Unverified
2ActionMamba(InternVideo2-6B)Average-mAP44.56Unverified
3DyFADet(VideoMAEv2)Average-mAP44.3Unverified
4InternVideo2-6BAverage-mAP43.3Unverified
5TriDet (VideoMAEv2)Average-mAP43.1Unverified
6InternVideo2-1BAverage-mAP42.4Unverified
7InternVideoAverage-mAP41.55Unverified
8TriDet (SlowFast)Average-mAP38.6Unverified
9TriDet (I3D RGB)Average-mAP36.8Unverified
10TadTr (I3D RGB)Average-mAP32.09Unverified
#ModelMetricClaimedVerifiedStatus
1RDFA-S6 (InternVideo2-6B)mAP29.6Unverified
2ActionMamba(InternVideo2-6B)mAP29.04Unverified
3InternVideo2-6BmAP27.7Unverified
4DyFADet (VideoMAE v2-g)mAP23.8Unverified
5VideoMAE V2-gmAP18.24Unverified
6InternVideomAP17.57Unverified
7BMN (i3d feaure)mAP9.25Unverified
8G-TAD (i3d feature)mAP9.06Unverified
9DBG (i3d feature)mAP6.75Unverified
#ModelMetricClaimedVerifiedStatus
1TriDet (VideoMAEv2)Average mAP37.5Unverified
2DualDETR (I3D-rgb)Average mAP32.64Unverified
3TriDet (I3D-rgb)Average mAP30.7Unverified
4TemporalMaxerAverage mAP29.9Unverified
5PointTADAverage mAP23.5Unverified
6PDANAverage mAP17.3Unverified
7MS-TCTAverage mAP16.2Unverified
8MLADAverage mAP14.2Unverified
#ModelMetricClaimedVerifiedStatus
1VideoCLIPRecall47.3Unverified
2VLMRecall46.5Unverified
3TACoRecall42.5Unverified
4Text-Video EmbeddingRecall33.6Unverified
5Fully-supervised upper-boundRecall31.6Unverified
6ZhukovRecall22.4Unverified
7AlayracRecall13.3Unverified
#ModelMetricClaimedVerifiedStatus
1AdaTAD (verb, VideoMAE-L)Avg mAP (0.1-0.5)29.3Unverified
2TriDet (verb)Avg mAP (0.1-0.5)25.4Unverified
3TemporalMaxer (verb)Avg mAP (0.1-0.5)24.5Unverified
4ActionFormer (verb)Avg mAP (0.1-0.5)23.5Unverified
5G-TAD (verb)Avg mAP (0.1-0.5)9.4Unverified
6BMN (verb)Avg mAP (0.1-0.5)8.4Unverified
#ModelMetricClaimedVerifiedStatus
1TemporalMaxermAP27.2Unverified
2MUSESmAP18.6Unverified
#ModelMetricClaimedVerifiedStatus
1DeepMetricLearnermAP IOU@0.535.2Unverified
#ModelMetricClaimedVerifiedStatus
1ActionFormer (SlowFast+Omnivore+EgoVLP)Average mAP21.76Unverified
#ModelMetricClaimedVerifiedStatus
1ActionFormer (SlowFast+Omnivore+EgoVLP)Average mAP21.4Unverified
#ModelMetricClaimedVerifiedStatus
1S-CNNmAP7.4Unverified