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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 141–150 of 817 papers

Title	Date	Tasks	Status	Hype	Score
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers	Sep 3, 2023	Action DetectionAction Spotting	CodeCode Available	1	5
Post-Processing Temporal Action Detection	Nov 27, 2022	Action ClassificationAction Detection	CodeCode Available	1	5
Continual Transformers: Redundancy-Free Attention for Online Inference	Jan 17, 2022	Action DetectionAudio Classification	CodeCode Available	1	5
Semi-Supervised Temporal Action Detection with Proposal-Free Masking	Jul 14, 2022	Action DetectionGeneral Classification	CodeCode Available	1	5
Continuous control with deep reinforcement learning	Sep 9, 2015	Action Detectioncontinuous-control	CodeCode Available	1	5
BMN: Boundary-Matching Network for Temporal Action Proposal Generation	Jul 23, 2019	Action DetectionAction Recognition	CodeCode Available	1	5
Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment	Dec 1, 2024	Action DetectionActivity Detection	CodeCode Available	0	5
Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality	Jan 24, 2025	Action DetectionActivity Detection	CodeCode Available	0	5
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding	Nov 1, 2019	Action DetectionAction Recognition	CodeCode Available	0	5
Modality Distillation with Multiple Stream Networks for Action Recognition	Jun 19, 2018	Action ClassificationAction Detection	CodeCode Available	0	5

Show:10 25 50

← PrevPage 15 of 82Next →

All datasets UCF101-24 J-HMDB Charades Multi-THUMOS UCF Sports THUMOS' 14 MultiSports TSU TTStroke-21 ME21 TTStroke-21 ME22 MultiTHUMOS

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	STAR/L	Frame-mAP 0.5	90.3	—	Unverified
2	SiA	Frame-mAP 0.5	88.5	—	Unverified
3	YOWO + LFB	Frame-mAP 0.5	87.3	—	Unverified
4	HIT	Frame-mAP 0.5	84.8	—	Unverified
5	HISAN (ResNet-101 + FPN)	Video-mAP 0.2	82.3	—	Unverified
6	YOWO	Frame-mAP 0.5	80.4	—	Unverified
7	Two-in-one Two Stream	Video-mAP 0.2	78.48	—	Unverified
8	MOC	Frame-mAP 0.5	77.8	—	Unverified
9	Faster-RCNN + two-stream I3D conv	Frame-mAP 0.5	76.3	—	Unverified
10	Two-in-one	Video-mAP 0.2	75.48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SiA	Frame-mAP 0.5	88.5	—	Unverified
2	HISAN (ResNet-101 + FPN)	Video-mAP 0.2	87.59	—	Unverified
3	HIT	Frame-mAP 0.5	83.8	—	Unverified
4	HISAN (VGG-16)	Frame-mAP 0.5	76.72	—	Unverified
5	DTS	Video-mAP 0.2	76.1	—	Unverified
6	YOWO + LFB	Frame-mAP 0.5	75.7	—	Unverified
7	Two-in-one Two Stream	Video-mAP 0.5	74.74	—	Unverified
8	YOWO	Frame-mAP 0.5	74.4	—	Unverified
9	MOC	Frame-mAP 0.5	74	—	Unverified
10	Faster-RCNN + two-stream I3D conv	Frame-mAP 0.5	73.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TTM	mAP	28.79	—	Unverified
2	CTRN	mAP	27.8	—	Unverified
3	Coarse-Fine Networks (w/ self-supervised detection pretraining)	mAP	26.95	—	Unverified
4	UniMD+Sync. (RGB+Flow)	mAP	26.53	—	Unverified
5	PDAN (RGB+Flow)	mAP	26.5	—	Unverified
6	PAT	mAP	26.5	—	Unverified
7	MS-TCT (RGB only)	mAP	25.4	—	Unverified
8	3D ResNet-50 + super-events pretrained on AViD	mAP	25.2	—	Unverified
9	Coarse-Fine Networks	mAP	25.1	—	Unverified
10	MLAD (RGB + Flow)	mAP	23.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MLAD	mAP	51.5	—	Unverified
2	CTRN	mAP	51.2	—	Unverified
3	PDAN	mAP	47.6	—	Unverified
4	TGM	mAP	46.4	—	Unverified
5	MS-TCT (RGB only)	mAP	43.1	—	Unverified
6	I3D + our super-event	mAP	36.4	—	Unverified
7	Two-stream + LSTM	mAP	28.1	—	Unverified
8	Two-stream	mAP	27.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Two-in-one Two Stream	Video-mAP 0.5	96.52	—	Unverified
2	DTS	Video-mAP 0.2	94.3	—	Unverified
3	Two-in-one	Video-mAP 0.5	92.74	—	Unverified
4	T-CNN	Frame-mAP 0.5	86.7	—	Unverified
5	MR-TS R-CNN	Frame-mAP 0.5	84.52	—	Unverified
6	TS R-CNN	Frame-mAP 0.5	82.3	—	Unverified
7	Action Tubes	Frame-mAP 0.5	68.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MAT (Ours) Trans	mAP	71.6	—	Unverified
2	TadML-two stream	mAP	59.7	—	Unverified
3	MAT (ours)	mAP	58.2	—	Unverified
4	TadML-rgb	mAP	53.46	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HIT	Frame-mAP 0.5	33.3	—	Unverified
2	SiA	Frame-mAP 0.5	28.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MS-TCT	Frame-mAP	33.7	—	Unverified
2	PDAN	Frame-mAP	32.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STCNN	IoU	0.14	—	Unverified
2	Two Stream Network	IoU	0.07	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STCNN-V2 (Vote decision)	IoU	0.52	—	Unverified
2	RGB and PRGB	IoU	0.35	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PAT	mAP	44.6	—	Unverified