Related papers: Temporal-Relational CrossTransformers for Few-Shot…
This paper introduces the task of few-shot common action localization in time and space. Given a few trimmed support videos containing the same but unknown action, we strive for spatio-temporal localization of that action in a long…
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify…
Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the…
Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-domain annotated data. In this paper, we tackle an even harder…
The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…
Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomous navigation, and task planning of self-driving vehicles…
We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discriminability while simultaneously learning higher-order temporal representations. The focus of our approach is a novel spatio-temporal…
We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D body joints, we propose an…
Few-shot action recognition has attracted increasing attention due to the difficulty in acquiring the properly labelled training samples. Current works have shown that preserving spatial information and comparing video descriptors are…
In recent years, 2D Convolutional Networks-based video action recognition has encouragingly gained wide popularity; However, constrained by the lack of long-range non-linear temporal relation modeling and reverse motion information…
Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos.…
Many interesting events in the real world are rare making preannotated machine learning ready videos a rarity in consequence. Thus, temporal activity detection models that are able to learn from a few examples are desirable. In this paper,…
In this paper, we propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-training framework, to integrate both the spatial information and…
Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies. Nevertheless, they are limited in that…
Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the…
Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few examples are desirable. In this paper, we present a conceptually…
Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two…
Existing works in few-shot action recognition mostly fine-tune a pre-trained image model and design sophisticated temporal alignment modules at feature level. However, simply fully fine-tuning the pre-trained model could cause overfitting…
Sign language recognition from sequences of monocular images or 2D poses is a challenging field, not only due to the difficulty to infer 3D information from 2D data, but also due to the temporal relationship between the sequences of…
Few-shot algorithms aim at learning new tasks provided only a handful of training examples. In this work we investigate few-shot learning in the setting where the data points are sequences of tokens and propose an efficient learning…