paper-with-me

Papers Unsupervised Action Segmentation

“Unsupervised Action Segmentation” 태그가 달린 논문 20편 · 필터 해제

D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation

2026-08-06 · Elena Bueno-Benito, Mariella Dimiccoli arxiv

Optimal transport (OT) has emerged as an effective framework for unsupervised action segmentation. Yet, in existing OT-based methods, the latent action prototypes that define the OT costs are not re-estimated from the re…

Unsupervised Action Segmentation

Learning Probabilistic Embeddings for Unsupervised Action Segmentation

2026-07-06 · Shuai Li, Duc Manh Vu, Juergen Gall arxiv

This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint representation learning and clustering paradigm, where optimal transpor…

Unsupervised Action SegmentationRepresentation Learning

Deep kernel video approximation for unsupervised action segmentation

2026-04-23 · Silvia L. Pintea, Jouke Dijkstra arxiv

This work focuses on per-video unsupervised action segmentation, which is of interest to applications where storing large datasets is either not possible, or nor permitted. We propose to segment videos by learning in dee…

Unsupervised Action Segmentation

CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation

2025-07-04 · Elena Bueno-Benito, Mariella Dimiccoli arxiv

Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike othe…

Unsupervised Action Segmentation

Hierarchical Vector Quantization for Unsupervised Action Segmentation

2024-12-23 · Federico Spurio, Emad Bahrami, Gianpiero Francesca, Juergen Gall

In this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos. While recent approaches combine …

Action SegmentationClusteringQuantizationRepresentation Learning+2

Transformer with Controlled Attention for Synchronous Motion Captioning

2024-09-13 · Karim Radouane, Sylvie Ranwez, Julien Lagarde, Andon Tchechmedjiev

In this paper, we address a challenging task, synchronous motion captioning, that aim to generate a language description synchronized with human motion sequences. This task pertains to numerous applications, such as alig…

Action LocalizationAction SegmentationMotion CaptioningPhrase Grounding+4

Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation

2024-04-01 · CVPR 2024 1 · Ming Xu, Stephen Gould

We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem, we are ab…

Action SegmentationSegmentationUnsupervised Action Segmentation

Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment

2023-05-31 · Quoc-Huy Tran, Ahmed Mehmood, Muhammad Ahmed, Muhammad Naufil 외

This paper presents an unsupervised transformer-based framework for temporal activity segmentation which leverages not only frame-level cues but also segment-level cues. This is in contrast with previous methods which of…

Action SegmentationDecoderPredictionSegmentation+1

Leveraging triplet loss for unsupervised action segmentation

2023-04-13 · E. Bueno-Benito, B. Tura, M. Dimiccoli

In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our met…

Action SegmentationClusteringMetric LearningSegmentation+3

TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering

2023-03-09 · Wei Lin, Anna Kukleva, Horst Possegger, Hilde Kuehne 외

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-s…

Action SegmentationClusteringSegmentationTemporal Action Segmentation+1

Fast and Unsupervised Action Boundary Detection for Action Segmentation

2022-01-01 · CVPR 2022 1 · Zexing Du, Xue Wang, Guoqing Zhou, Qing Wang

To deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD). In particular, the…

Action SegmentationBoundary DetectionChange Point DetectionUnsupervised Action Segmentation

Unsupervised Action Segmentation for Instructional Videos

2021-06-07 · AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Irfan Essa

In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions. We present an unsupervised approach to le…

Action SegmentationSegmentationUnsupervised Action Segmentation

Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering

2021-05-27 · CVPR 2022 1 · Sateesh Kumar, Sanjay Haresh, Awais Ahmed, Andrey Konin 외

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 p…

Action SegmentationClusteringOnline ClusteringPseudo Label+2

Action Shuffle Alternating Learning for Unsupervised Action Segmentation

2021-04-05 · CVPR 2021 1 · Jun Li, Sinisa Todorovic

This paper addresses unsupervised action segmentation. Prior work captures the frame-level temporal structure of videos by a feature embedding that encodes time locations of frames in the video. We advance prior work wit…

Action SegmentationSegmentationSelf-Supervised LearningUnsupervised Action Segmentation

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

Unsupervised learning of action classes with continuous temporal embedding

2019-04-08 · CVPR 2019 6 · Anna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall

The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and label action boundaries to create annot…

Action SegmentationUnsupervised Action Segmentation

A Perceptual Prediction Framework for Self Supervised Event Segmentation

2018-11-12 · CVPR 2019 6 · Sathyanarayanan N. Aakur, Sudeep Sarkar

Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of s…

Action LocalizationAction RecognitionEvent SegmentationPrediction+2

Watch-n-Patch: Unsupervised Learning of Actions and Relations

2016-03-11 · Chenxia Wu, Jiemi Zhang, Ozan Sener, Bart Selman 외

There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple basic level actions in a completely unsupervised se…

Action SegmentationClusteringUnsupervised Action Segmentation

Watch-Bot: Unsupervised Learning for Reminding Humans of Forgotten Actions

2015-12-14 · Chenxia Wu, Jiemi Zhang, Bart Selman, Silvio Savarese 외

We present a robotic system that watches a human using a Kinect v2 RGB-D sensor, detects what he forgot to do while performing an activity, and if necessary reminds the person using a laser pointer to point out the relat…

Action SegmentationObjectUnsupervised Action Segmentation

Watch-n-Patch: Unsupervised Understanding of Actions and Relations

2015-06-01 · CVPR 2015 6 · Chenxia Wu, Jiemi Zhang, Silvio Savarese, Ashutosh Saxena

We focus on modeling human activities comprising multiple actions in a completely unsupervised setting. Our model learns the high-level action co-occurrence and temporal relations between the actions in the activity vide…

Action SegmentationUnsupervised Action Segmentation
1–20 / 20