paper-with-me

Papers Temporal Action Localization

“Temporal Action Localization” 태그가 달린 논문 1,503편 · 필터 해제

PL-NBA: A Possession-level Universal Basketball Video Dataset Supporting Multiple Visual Understanding Tasks

2026-08-20 · Yunhao Zhao, Haoying Sun, Jiarui Li, Zhuming Wang 외 arxiv

Visual understanding in sports has emerged as a hot topic in computer vision in recent years. Most existing basketball video datasets adopt single action or activity as sample, which can neither preserve the temporal con…

Temporal Action LocalizationAction AnticipationVideo Captioning

OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization

2026-07-01 · Sakib Reza, Gauri Jagatap, Mohsen Moghaddam, Octavia Camps 외 arxiv

Temporal Action Localization (TAL) typically relies on segment annotations or offline access to full videos, limiting scalability and online use. We introduce Point-Supervised Online TAL (POTAL), which localizes actions …

Temporal Action Localization

ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization

2026-05-29 · Kanchan Keisham, Thenukan Pathmanathan, Thangarajah Akilan arxiv

Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches primarily focus on modeling long-range contextual information, often n…

Temporal Action Localization

Masked Diffusion Vision-Language Models for Temporal Action Localization

2026-05-28 · Fengshun Wang, Zhengbo Zhang, Zhigang Tu arxiv

Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vision-language formulations improve semantic reasoning and support la…

Temporal Action Localization

Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

2026-05-22 · Tianyu Wang, Junjie Wu, Jingquan Gao, Shishuo Li arxiv

Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle sp…

Temporal Action Localization

Zero-Shot Temporal Action Localization Through Textual Guidance

2026-05-21 · Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero, Paolo Rota 외 arxiv

Zero-shot temporal action localization (ZS-TAL) consists of classifying and localizing actions in untrimmed videos, where action classes are unseen at training time. Existing work uses Vision and Language Models (VLMs), …

Temporal Action LocalizationAction Classification

OZ-TAL: Online Zero-Shot Temporal Action Localization

2026-05-11 · Chaolei Han, Hongsong Wang, Xin Gong, Jie Gui arxiv

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 developi…

Temporal Action LocalizationOnline Action Detection

From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection

2026-04-10 · Narges Rashvand, Shanle Yao, Armin Danesh Pazho, Babak Rahimi Ardabili 외 arxiv

Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations. However, traditional frame-level evaluations treat video as a collec…

Temporal Action LocalizationVideo Anomaly Detection

RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization

2026-03-25 · Ting Yu Tsai, An Yu, Lucy Lee, Felix X. -F. Ye 외 arxiv

Animal models, particularly rats, play a critical role in seizure research for studying epileptogenesis and treatment response. However, progress is limited by the lack of datasets with precise temporal annotations and s…

Temporal Action Localization

A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors

2026-03-22 · Gia-Bao Doan, Nam-Khoa Huynh, Minh-Nhat-Huy Ho, Khanh-Thanh-Khoa Nguyen 외 arxiv

The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal…

Temporal Action LocalizationComputational Efficiency

WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?

2026-02-02 · Pei Li, Jiaxi Yin, Lei Ouyang, Shihan Pan 외 arxiv

IMU-based Human Activity Recognition (HAR) has enabled a wide range of ubiquitous computing applications, yet its dominant clip classification paradigm cannot capture the rich temporal structure of real-world behaviors. …

Temporal Action LocalizationHuman Activity Recognition

Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment

2026-02-01 · Yunchuan Ma, Laiyun Qing, Guorong Li, Yuqing Liu 외 arxiv

Recently, point-supervised temporal action localization has gained significant attention for its effective balance between labeling costs and localization accuracy. However, current methods only consider features from vi…

Temporal Action LocalizationContrastive Learning

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization

2026-01-28 · Jiaqi Li, Guangming Wang, Shuntian Zheng, Minzhe Ni 외 arxiv

Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language models (VLMs) offer rich semantics to complement visual evidence, existing …

Temporal Action Localization

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

2026-01-22 · Onkar Susladkar, Tushar Prakash, Adheesh Juvekar, Kiet A. Nguyen 외 arxiv

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supe…

Temporal Action LocalizationText-to-Video GenerationVideo ReconstructionVideo Segmentation

Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization

2025-12-18 · Qiushuo Cheng, Jingjing Liu, Catherine Morgan, Alan Whone 외 arxiv

The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for …

Temporal Action LocalizationContrastive LearningAction RecognitionTransfer Learning

Multi-task Learning with Extended Temporal Shift Module for Temporal Action Localization

2025-12-12 · Anh-Kiet Duong, Petra Gomez-Krämer arxiv

We present our solution to the BinEgo-360 Challenge at ICCV 2025, which focuses on temporal action localization (TAL) in multi-perspective and multi-modal video settings. The challenge provides a dataset containing panor…

Temporal Action LocalizationScene ClassificationMulti-Task LearningEnsemble Learning

TBT-Former: Learning Temporal Boundary Distributions for Action Localization

2025-12-01 · Thisara Rathnayaka, Uthayasanker Thayasivam arxiv

Temporal Action Localization (TAL) remains a fundamental challenge in video understanding, aiming to identify the start time, end time, and category of all action instances within untrimmed videos. While recent single-st…

Temporal Action Localization

FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videos

2025-11-20 · Jeremie Ochin, Raphael Chekroun, Bogdan Stanciulescu, Sotiris Manitsaris arxiv

Soccer video understanding has motivated the creation of datasets for tasks such as temporal action localization, spatiotemporal action detection (STAD), or multiobject tracking (MOT). The annotation of structured sequen…

Temporal Action LocalizationTrajectory ForecastingAction RecognitionAction Detection

MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization

2025-11-17 · Zhenying Fang, Richang Hong arxiv

Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mos…

Temporal Action Localization

Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization

2025-11-06 · Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma arxiv

Temporal action localization requires both precise boundary detection and computational efficiency. Current methods apply uniform computation across all temporal positions, wasting resources on easy boundaries while stru…

Temporal Action LocalizationComputational EfficiencyKnowledge DistillationDistance regression
1–20 / 1,503 다음 →