Temporal Action Localization
421 papers with code • 14 benchmarks • 42 datasets
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.
Benchmarks
These leaderboards are used to track progress in Temporal Action Localization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Temporal Action Localization models and implementationsDatasets
UCF101
Kinetics
HMDB51
ActivityNet
MPII
Charades
THUMOS14
KTH
EPIC-KITCHENS-100
Kinetics-700
Subtasks
Latest papers
Generative Model-based Feature Knowledge Distillation for Action Recognition
aaai-24/generative-based-kd
•
•
Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model.
Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables
ami-iit/paper_guo_2023_humanoids_lifting_risk_prediction
•
•
This paper proposes a framework that combines online human state estimation, action recognition and motion prediction to enable early assessment and prevention of worker biomechanical risk during lifting tasks.
EZ-CLIP: Efficient Zeroshot Video Action Recognition
Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks.
Unsupervised Temporal Action Localization via Self-paced Incremental Learning
Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance.
Towards a geometric understanding of Spatio Temporal Graph Convolution Networks
In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN.
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
sming256/OpenTAD
•
•
Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training.
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis.
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art
Automated human action recognition, a burgeoning field within computer vision, boasts diverse applications spanning surveillance, security, human-computer interaction, tele-health, and sports analysis.
Learning Human Action Recognition Representations Without Real Humans
howardzh01/ppma
•
•
NeurIPS 2023
To this end, we present, for the first time, a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model.
FPGA-QHAR: Throughput-Optimized for Quantized Human Action Recognition on The Edge
Accelerating Human Action Recognition (HAR) efficiently for real-time surveillance and robotic systems on edge chips remains a challenging research field, given its high computational and memory requirements.
