Related papers: On Evaluating Weakly Supervised Action Segmentatio…
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal variations (e.g. different people may perform the same…
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require…
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…
Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights in training videos. We propose a…
Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations…
To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Fully supervised action segmentation works on frame-wise action recognition with dense annotations and often suffers from the over-segmentation issue. Existing works have proposed a variety of solutions such as boundary-aware networks,…
Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video…
Multi-step manipulation tasks where robots interact with their environment and must apply process forces based on the perceived situation remain challenging to learn and prone to execution errors. Accurately simulating these tasks is also…
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions…
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…
As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a…
We address the highly challenging problem of video object segmentation. Given only the initial mask, the task is to segment the target in the subsequent frames. In order to effectively handle appearance changes and similar background…
Human doing actions will result in WiFi distortion, which is widely explored for action recognition, such as the elderly fallen detection, hand sign language recognition, and keystroke estimation. As our best survey, past work recognizes…
With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize…
We present an image preprocessing technique capable of improving the performance of few-shot classifiers on abstract visual reasoning tasks. Many visual reasoning tasks with abstract features are easy for humans to learn with few examples…
Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a…
Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational resources, which hinders their applications in practice.…
We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps. The first two steps extract high-quality pseudo masks from image-level annotated data, which are then used to train a…