Related papers: Few-Shot Temporal Action Localization with Query A…
Few-shot Learning (FSL) aims to classify new concepts from a small number of examples. While there have been an increasing amount of work on few-shot object classification in the last few years, most current approaches are limited to images…
An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…
Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant…
We introduce Few-Shot Video Object Detection (FSVOD) with three contributions to real-world visual learning challenge in our highly diverse and dynamic world: 1) a large-scale video dataset FSVOD-500 comprising of 500 classes with…
Spatio-temporal action detection in videos is typically addressed in a fully-supervised setup with manual annotation of training videos required at every frame. Since such annotation is extremely tedious and prohibits scalability, there is…
Most existing studies on few-shot learning focus on unimodal settings, where models are trained to generalize to unseen data using a limited amount of labeled examples from a single modality. However, real-world data are inherently…
Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains,…
Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive…
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…
Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long,…
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…
Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning algorithms extract a transferable embedding from seen classes…
Applying large-scale vision-language pre-trained models like CLIP to few-shot action recognition (FSAR) can significantly enhance both performance and efficiency. While several studies have recognized this advantage, most of them resort to…
Traditional temporal action detection (TAD) usually handles untrimmed videos with small number of action instances from a single label (e.g., ActivityNet, THUMOS). However, this setting might be unrealistic as different classes of actions…
One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either…
In recent years, few-shot action recognition has achieved remarkable performance through spatio-temporal relation modeling. Although a wide range of spatial and temporal alignment modules have been proposed, they primarily address spatial…
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…
Few-shot recognition (FSR) aims to train a classification model with only a few labeled examples of each concept concerned by a downstream task, where data annotation cost can be prohibitively high. We develop methods to solve FSR by…
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous…