Related papers: A Novel Online Action Detection Framework from Unt…
The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future…
The task of action recognition or action detection involves analyzing videos and determining what action or motion is being performed. The primary subject of these videos are predominantly humans performing some action. However, this…
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…
Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and classification of each…
Temporal action detection is a fundamental yet challenging task in video understanding. Many of the state-of-the-art methods predict the boundaries of action instances based on predetermined anchors akin to the two-dimensional object…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…
Weakly supervised temporal action localization is a challenging vision task due to the absence of ground-truth temporal locations of actions in the training videos. With only video-level supervision during training, most existing methods…
Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual challenge of temporal and class overlaps is too complex to…
Temporal modeling still remains challenging for action recognition in videos. To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal…
Semi-supervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this…
With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video. Nevertheless, most practical methods still require all…
Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the…
Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available. Existing approaches typically leverage off-the-shelf segment-level…
Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision. Pseudo label generation is a promising…
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity…
Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for…