paper-with-me

Papers

Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment

2024-08-19 · Zhanzhong Pang, Fadime Sener, Shrinivas Ramasubramanian, Angela Yao

Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail actions. Existing long-tail methods make class-independent assumptions and struggle to identify tail classes when applied to temporal segmentation frameworks. This work proposes a novel group-wise temporal logit adjustment~(G-TLA) framework that combines a group-wise softmax formulation while leveraging activity information and action ordering for logit adjustment. The proposed framework significantly improves in segmenting tail actions without any performance loss on head actions.

📄 PDF Abstract BibTeX arXiv:2408.09919

Code (1)

pangzhan27/GTLA 공식 구현 pytorch

Tasks

Action SegmentationSegmentationTemporal Action Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation

2025-03-24 · Zhanzhong Pang, Fadime Sener, Shrinivas Ramasubramanian, Angela Yao

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…

Action SegmentationSegmentationTemporal Action Segmentation

LOGO: A Long-Form Video Dataset for Group Action Quality Assessment

2024-04-07 · CVPR 2023 1 · Shiyi Zhang, Wenxun Dai, Sujia Wang, Xiangwei Shen 외

Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios. However, most existing methods and datasets focus on single-person short-sequence scenes, hindering …

Action Quality AssessmentAction SegmentationForm

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

2021-03-20 · CVPR 2021 1 · M. Saquib Sarfraz, Naila Murray, Vivek Sharma, Ali Diba 외

Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, su…

Action SegmentationClusteringSegmentationUnsupervised Action Segmentation+1

Learning unbiased group-wise registration (LUGR) and joint segmentation: evaluation on longitudinal diffusion MRI

2020-11-03 · Bo Li, Wiro J. Niessen, Stefan Klein, M. Arfan Ikram 외

Analysis of longitudinal changes in imaging studies often involves both segmentation of structures of interest and registration of multiple timeframes. The accuracy of such analysis could benefit from a tailored framewor…

Diffusion MRI

How Much Temporal Long-Term Context is Needed for Action Segmentation?

2023-08-22 · ICCV 2023 1 · Emad Bahrami, Gianpiero Francesca, Juergen Gall

Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal …

Action SegmentationSegmentationTemporal Action Segmentation