Deep Point-Wise Prediction for Action Temporal Proposal

Li, Luxuan; Kong, Tao; Sun, Fuchun; Liu, Huaping

doi:10.1007/978-3-030-36718-3_40

Cited by 9 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging the capabilities of video recognition backbones [69], [70], [71], which provide representative features, and adopting the end-to-end learning paradigm [36], which simplifies complex designs, the field has seen significant advancements. In the realm of supervised approaches, the anchor mechanism has seen notable developments, resulting in one-stage methods [33], [39], [72], [73], two-stage methods [14], [36], [52], [74], and anchor-free methods [44], [75], [76], [77]. On the other hand, in the context of weakly supervised methods, the community has introduced the pre-classification pipeline [2], [78], [79], [80] and the postclassification pipeline [20], [54], [81], [82].…”

Section: History and Scopementioning

confidence: 99%

Temporal Action Localization in the Deep Learning Era: A Survey

Wang,

Zhao,

Yang

et al. 2024

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

The temporal action localization research aims to discover action instances from untrimmed videos, representing a fundamental step in the field of intelligent video understanding. With the advent of deep learning, backbone networks have been instrumental in providing representative spatiotemporal features, while the end-to-end learning paradigm has enabled the development of high-quality models through data-driven training. Both supervised and weakly supervised learning approaches have contributed to the rapid progress of temporal action localization, resulting in a multitude of methods and a large body of literature, making a comprehensive survey a pressing necessity. This paper presents a thorough analysis of existing action localization works, offering a well-organized taxonomy that highlights the strengths and weaknesses of each strategy. In the realm of supervised learning, in addition to the anchor mechanism, we introduce a novel classification mechanism to categorize and summarize existing works. Similarly, for weakly supervised learning, we extend the traditional pre-classification and post-classification mechanisms by providing a fresh perspective on enhancement strategies. Furthermore, we shed light on the bottleneck of confidence estimation, a critical yet overlooked aspect of current works. By conducting detailed analyses, this survey serves as a valuable resource for researchers, providing beneficial guidance to newcomers and inspiring seasoned researchers alike.

show abstract

Section: History and Scopementioning

confidence: 99%

Temporal Action Localization in the Deep Learning Era: A Survey

Wang,

Zhao,

Yang

et al. 2024

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…Xie [2021, 2023] study the behavior of conformal methods under classical nonparametric assumptions such as model consistency and distributional smoothness for its validity, and thus cannot give distribution-free guarantees in Settings 1 or 2. Lin et al [2022] studies the problem of cross-sectional coverage for multiple exchangeable time-series. The online conformal prediction setup was also considered early on by Vovk [2002] for exchangeable sequences.…”

Section: Related Workmentioning

confidence: 99%

Private Prediction Sets

Angelopoulos

Bates

Zrnic

et al. 2022

Harvard Data Science Review

View full text Add to dashboard Cite

We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.

show abstract

“…In addition, their strategy was complex and time consuming. To solve this issue, Deep Point-wise Prediction (DPP) [ 38 ] was introduced as a simple yet efficient method that does not utilize any predefined sliding windows to generate temporal proposals. Inspired by the feature pyramid network [ 47 ], the model was designed for extracting temporal features in different temporal lengths or scales from low to high levels via a top-down pathway.…”

Section: The Review Of Tapg Networkmentioning

confidence: 99%

A Comprehensive Review on Temporal-Action Proposal Generation

Sooksatra

Watcharapinchai

2022

J. Imaging

View full text Add to dashboard Cite

Temporal-action proposal generation (TAPG) is a well-known pre-processing of temporal-action localization and mainly affects localization performance on untrimmed videos. In recent years, there has been growing interest in proposal generation. Researchers have recently focused on anchor- and boundary-based methods for generating action proposals. The main purpose of this paper is to provide a comprehensive review of temporal-action proposal generation with network architectures and empirical results. The pre-processing step for input data is also discussed for network construction. The content of this paper was obtained from the research literature related to temporal-action proposal generation from 2012 to 2022 for performance evaluation and comparison. From several well-known databases, we used specific keywords to select 71 related studies according to their contributions and evaluation criteria. The contributions and methodologies are summarized and analyzed in a tabular form for each category. The result from state-of-the-art research was further analyzed to show its limitations and challenges for action proposal generation. TAPG performance in average recall ranges from 60% up to 78% in two TAPG benchmarks. In addition, several future potential research directions in this field are suggested based on the current limitations of the related studies.

show abstract

Deep Point-Wise Prediction for Action Temporal Proposal

Cited by 9 publications

References 29 publications

Temporal Action Localization in the Deep Learning Era: A Survey

Temporal Action Localization in the Deep Learning Era: A Survey

Private Prediction Sets

A Comprehensive Review on Temporal-Action Proposal Generation

Contact Info

Product

Resources

About