Related papers: HACS: Human Action Clips and Segments Dataset for …
Action detection and temporal segmentation of actions in videos are topics of increasing interest. While fully supervised systems have gained much attention lately, full annotation of each action within the video is costly and impractical…
Enabled by large annotated datasets, tracking and segmentation of objects in videos has made remarkable progress in recent years. Despite these advancements, algorithms still struggle under degraded conditions and during fast movements.…
A new large-scale video dataset for human action recognition, called STAIR Actions is introduced. STAIR Actions contains 100 categories of action labels representing fine-grained everyday home actions so that it can be applied to research…
Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and…
Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer…
Human action recognition refers to automatic recognizing human actions from a video clip. In reality, there often exist multiple human actions in a video stream. Such a video stream is often weakly-annotated with a set of relevant human…
While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantically defined…
Human-object interaction segmentation is a fundamental task of daily activity understanding, which plays a crucial role in applications such as assistive robotics, healthcare, and autonomous systems. Most existing learning-based methods…
Temporal action segmentation (TAS) is a critical step toward long-term video understanding. Recent studies follow a pattern that builds models based on features instead of raw video picture information. However, we claim those models are…
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…
Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic…
Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of action classes, which exhibits two major limitations in this…
We consider the task of temporal human action localization in lifestyle vlogs. We introduce a novel dataset consisting of manual annotations of temporal localization for 13,000 narrated actions in 1,200 video clips. We present an extensive…
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities…
Advancements in deep neural networks have contributed to near perfect results for many computer vision problems such as object recognition, face recognition and pose estimation. However, human action recognition is still far from…
In still image human action recognition, existing studies have mainly leveraged extra bounding box information along with class labels to mitigate the lack of temporal information in still images; however, preparing extra data with manual…
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,…
Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…
Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…