Related papers: Distill and Collect for Semi-Supervised Temporal A…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…
Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…
Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion…
Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain,…
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…
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,…
The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents…
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and challenging, we propose to exploit auxiliary unlabeled videos,…
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…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision…
Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…
Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of…
Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes. As a long-range video understanding task, researchers have developed an extended collection of…
Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action…
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…
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…
Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods…