Related papers: Sub-action Prototype Learning for Point-level Weak…
Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize…
The performance of object detection, to a great extent, depends on the availability of large annotated datasets. To alleviate the annotation cost, the research community has explored a number of ways to exploit unlabeled or weakly labeled…
We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of…
Domain adaptation tackles the challenge of generalizing knowledge acquired from a source domain to a target domain with different data distributions. Traditional domain adaptation methods presume that the classes in the source and target…
Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal WSOL work of class activation mapping (CAM), the field has…
Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually annotated data. Data programming is an efficient method to…
Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training,…
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most…
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track. Temporal Action Localization (TAL)…
Recent approaches for weakly supervised instance segmentations depend on two components: (i) a pseudo label generation model that provides instances which are consistent with a given annotation; and (ii) an instance segmentation model,…
Although large-scale video-language pre-training models, which usually build a global alignment between the video and the text, have achieved remarkable progress on various downstream tasks, the idea of adopting fine-grained information…
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works struggled to localize objects through various spatial…
This paper addresses the challenge of point-supervised temporal action detection, in which only one frame per action instance is annotated in the training set. Self-training aims to provide supplementary supervision for the training process…
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…
Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either…
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data…
Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class…
Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multiple Instance Learning (MIL) framework, where a bag (video)…
The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive and effective algorithm that localizes actions from their class…
Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…