Related papers: Annotation-Efficient Untrimmed Video Action Recogn…
Classification of new class entities requires collecting and annotating hundreds or thousands of samples that is often prohibitively costly. Few-shot learning suggests learning to classify new classes using just a few examples. Only a small…
Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider…
This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…
Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…
This notebook paper describes our system for the untrimmed classification task in the ActivityNet challenge 2016. We investigate multiple state-of-the-art approaches for action recognition in long, untrimmed videos. We exploit hand-crafted…
Few-shot Knowledge Graph (KG) completion is a focus of current research, where each task aims at querying unseen facts of a relation given its few-shot reference entity pairs. Recent attempts solve this problem by learning static…
We propose action-agnostic point-level (AAPL) supervision for temporal action detection to achieve accurate action instance detection with a lightly annotated dataset. In the proposed scheme, a small portion of video frames is sampled in an…
Fight detection in videos is an emerging deep learning application with today's prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper,…
Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak…
Conventional methods for object detection typically require a substantial amount of training data and preparing such high-quality training data is very labor-intensive. In this paper, we propose a novel few-shot object detection network…
We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive learning to capture…
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in…
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-based and RGB+D-based action recognition benchmarks have a…
Video object segmentation is a fundamental step in many advanced vision applications. Most existing algorithms are based on handcrafted features such as HOG, super-pixel segmentation or texture-based techniques, while recently deep features…
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially…
We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where the gaze target is out-of-frame. Our novel architecture…
Pixelwise annotation of image sequences can be very tedious for humans. Interactive video object segmentation aims to utilize automatic methods to speed up the process and reduce the workload of the annotators. Most contemporary approaches…
On public benchmarks, current action recognition techniques have achieved great success. However, when used in real-world applications, e.g. sport analysis, which requires the capability of parsing an activity into phases and…
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…