Few Shot Action Recognition
25 papers with code • 4 benchmarks • 5 datasets
Few-shot (FS) action recognition is a challenging com- puter vision problem, where the task is to classify an unlabelled query video into one of the action categories in the support set having limited samples per action class.
UCF101
Kinetics
HMDB51
Kinetics-100
Most implemented papers
Revisiting spatio-temporal layouts for compositional action recognition
gorjanradevski/revisiting-spatial-temporal-layouts
•
•
Recognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects involved.
Spatio-temporal Relation Modeling for Few-shot Action Recognition
Experiments are performed on four few-shot action recognition benchmarks: Kinetics, SSv2, HMDB51 and UCF101.
Multi-level Second-order Few-shot Learning
The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning.
Hybrid Relation Guided Set Matching for Few-shot Action Recognition
alibaba-mmai-research/HyRSM
•
•
CVPR 2022
To overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation module and set matching metric.
Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition
In this paper, we propose a novel video frame sampler for few-shot action recognition to address this issue, where task-specific spatial-temporal frame sampling is achieved via a temporal selector (TS) and a spatial amplifier (SA).
Uncertainty-DTW for Time Series and Sequences
leiwangr/udtw
•
•
Dynamic Time Warping (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time series or even matching sequence pairs in few-shot action recognition.
TempCLR: Temporal Alignment Representation with Contrastive Learning
yyuncong/tempclr
•
•
For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly.
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition
alibaba-mmai-research/hyrsmplusplus
•
•
To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric.
CLIP-guided Prototype Modulating for Few-shot Action Recognition
alibaba-mmai-research/clip-fsar
•
•
Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task.
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary.
