Alleviating noisy pseudo labels remains a key challenge in Semi-Supervised Temporal Action Localization (SS-TAL). Existing methods often filter pseudo labels based on strict conditions, but they typically assess classification and localization ...

Weakly-supervised temporal action localization aims to train an accurate and robust localization model using only video-level labels. Due to the lack of frame-level temporal annotations, existing weakly-supervised temporal action localization ...

Temporal action localization plays a significant role in video understanding, which aims to recognize action category as well as temporal interval in untrimmed videos. Most of previous transformer-based methods employ a feature space of single-...

Weakly supervised temporal action localization aims to locate the temporal boundaries of action instances in untrimmed videos using video-level labels and assign them the corresponding action category. Generally, it is solved by a pipeline called ...

Temporal action localization presents a significant challenge in computer vision, as the development of an efficient method for this task remains elusive. The objective is to identify human activities within untrimmed videos, determining when and ...

• An end-to-end network for action localization in untrimmed videos is introduced.
• A new Regression module refines action proposal boundary precision.
• Error estimation significantly boosts mean Average Precision (mAP).
• The ...

Weakly supervised temporal action localization (WTAL) aims to classify and localize actions in untrimmed videos with only video-level labels. Recent studies have attempted to obtain more accurate temporal boundaries by exploiting latent action instances ...

Weakly supervised Temporal Action localization (WTAL) aims to locate the action instances and identify their corresponding labels. Most current methods rely on a Multi-Instance Learning (MIL) framework to predict start and end boundaries of each ...

• Due to the boundary ambiguity of an action and its context, we construct a sparse graph focusing on the effective representation of context motion by optical flow modal learning, and find subtle differences between motion and context ...

Weakly-supervised temporal action localization aims to identify and localize action instances in untrimmed videos using only video-level action labels. Due to the lack of frame-level annotation information, correctly distinguishing foreground and ...

Weakly-supervised Temporal Action Localization (W-TAL) is a significant task in video understanding, intending to recognize the category and pinpoint the temporal boundaries of action segments in untrimmed videos based on the video-level labels. Due to ...

Temporal action localization (TAL), which aims to localize actions in long untrimmed videos, requires a large number of annotated training data. However, it is expensive to obtain segment-level annotations for large-scale datasets. To overcome ...

Transformer based networks have been widely used in Temporal Action Localization (TAL). An example of this is the previous state of the art method ActionFormer. By analyzing the predicted results of these transformer based models, we find that ...

Point-level temporal action localization (PTAL) aims to locate action instances in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the localization-by-classification paradigm to locate action ...

• Adversarial mechanism is proposed to precisely regress action proposal boundaries aiming to enhance their exclusivity and independence.

Weakly supervised Temporal Action Localization (WTAL) aims to locate the start and end boundaries of action instances and recognize their corresponding categories. Classical methods mainly rely on random erasure mechanisms, attention ...

Temporal action localization in videos presents significant challenges in the field of computer vision. While the boundary-sensitive method has been widely adopted, its limitations include incomplete use of intermediate and global information, as ...

To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization. It provides a rough temporal location for an action but implicitly overstates the supervision from the ...

Weakly supervised temporal action detection uses the extracted appearance and motion features to localize the action segments in untrimmed videos with only action category labels. Most previous methods detect action segments based on temporally ...

Weakly-supervised temporal action localization (W-TAL) is to locate the boundaries of action instances and classify them in an untrimmed video, which is a challenging task due to only video-level labels during training. Existing methods mainly ...

The weakly-supervised temporal action localization task aims to train a model that can accurately locate each action instance in the video using only video-level class labels. The existing methods take into account the information of different ...${}_{\mathrm{}}$

• Develop a two-branch framework for open-world temporal action localization.
• ...

Current temporal action localization methods work well on a closed-world assumption, in which all action categories to be localized are known as a priori. However, this assumption doesn’t apply to open-world scenarios, as novel ...

Enormous untrimmed videos from the real world are difficult to analyze and manage. Temporal action localization algorithms can help us to locate and recognize human activity clips in untrimmed videos. Recently, anchor-free temporal action ...

• We focus on instance features for anchor-free temporal action localization.
• A novel temporal context-aware module is designed to improve the capability.
• The state-of-the-art performances are achieved on three public datasets.