Related papers: O-TALC: Steps Towards Combating Oversegmentation w…
Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context…
Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have…
We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where…
The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…
Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more…
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…
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…
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…
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…
Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action…
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…
Due to the rapid temporal and fine-grained nature of complex human assembly atomic actions, traditional action segmentation approaches requiring the spatial (and often temporal) down sampling of video frames often loose vital fine-grained…
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…
Online Temporal Action Localization (On-TAL) is a critical task that aims to instantaneously identify action instances in untrimmed streaming videos as soon as an action concludes -- a major leap from frame-based Online Action Detection…
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,…
This paper addresses a new problem of weakly-supervised online action segmentation in instructional videos. We present a framework to segment streaming videos online at test time using Dynamic Programming and show its advantages over greedy…
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…
Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution…
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…
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…