paper-with-me

Papers Action Localization

“Action Localization” 태그가 달린 논문 369편 · 필터 해제

Zero-Shot Temporal Interaction Localization for Egocentric Videos

2025-06-04 · Erhang Zhang, Junyi Ma, Yin-Dong Zheng, Yixuan Zhou 외

Locating human-object interaction (HOI) actions within video serves as the foundation for multiple downstream tasks, such as human behavior analysis and human-robot skill transfer. Current temporal action localization me…

Action LocalizationHuman-Object Interaction DetectionTemporal Action Localization

LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization

2025-05-30 · Zirui Shang, Xinxiao wu, Shuo Yang

Language-driven action localization in videos requires not only semantic alignment between language query and video segment, but also prediction of action boundaries. However, the language query primarily describes the m…

Action Localization

CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization

2025-05-29 · Rui Xia, Dan Jiang, Quan Zhang, Ke Zhang 외

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which ar…

Action LocalizationInformation RetrievalTemporal Action Localization

DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition

2025-05-27 · Marius Bock, Michael Moeller, Kristof Van Laerhoven

Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets. Deep learning models like t…

Action LocalizationActivity RecognitionHuman Activity RecognitionTemporal Action Localization+1

ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization

2025-05-23 · Yuchen He, Jianbing Lv, Liqi Cheng, Lingyu Meng 외

Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually annotated data. Data programming is an e…

Action LocalizationTemporal Action Localization

Action Spotting and Precise Event Detection in Sports: Datasets, Methods, and Challenges

2025-05-06 · Hao Xu, Arbind Agrahari Baniya, Sam Well, Mohamed Reda Bouadjenek 외

Video event detection has become an essential component of sports analytics, enabling automated identification of key moments and enhancing performance analysis, viewer engagement, and broadcast efficiency. Recent advanc…

Action LocalizationAction SpottingEvent DetectionKnowledge Distillation+4

Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer

2025-04-21 · CVPR 2025 1 · Ziyi Liu, Yangcen Liu

Weakly-supervised Temporal Action Localization (WTAL) has achieved notable success but still suffers from a lack of temporal annotations, leading to a performance and framework gap compared with fully-supervised methods.…

Action LocalizationTemporal Action LocalizationWeakly-supervised Temporal Action Localization

Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts

2025-04-20 · Zhenkui Yang, Zeyi Huang, Ge Wang, Han Ding 외

Wireless signal-based human sensing technologies, such as WiFi, millimeter-wave (mmWave) radar, and Radio Frequency Identification (RFID), enable the detection and interpretation of human presence, posture, and activitie…

Action LocalizationAction RecognitionTemporal Action Localization

Chain-of-Thought Textual Reasoning for Few-shot Temporal Action Localization

2025-04-18 · Hongwei Ji, Wulian Yun, Mengshi Qi, Huadong Ma

Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categor…

Action LocalizationAnomaly DetectionAnomaly LocalizationFew-Shot Learning+5

TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos

2025-03-09 · Chen-Lin Zhang, Lin Sui, Shuming Liu, Fangzhou Mu 외

Temporal localization in untrimmed videos, which aims to identify specific timestamps, is crucial for video understanding but remains challenging. This task encompasses several subtasks, including temporal action localiz…

Action LocalizationBoundary DetectionChunkingGeneric Event Boundary Detection+5

Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues

2025-02-01 · Rohit Girmaji, Siddharth Jain, Bhav Beri, Sarthak Bansal 외

This paper introduces ViNet-S, a 36MB model based on the ViNet architecture with a U-Net design, featuring a lightweight decoder that significantly reduces model size and parameters without compromising performance. Addi…

Action ClassificationAction LocalizationDecoderSaliency Prediction+3

XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glasses

2025-01-31 · Bo Lan, Pei Li, Jiaxi Yin, Yunpeng Song 외

Human Action Recognition (HAR) plays a crucial role in applications such as health monitoring, smart home automation, and human-computer interaction. While HAR has been extensively studied, action summarization, which in…

Action LocalizationAction RecognitionPose EstimationSynthetic Data Generation+1

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

2025-01-19 · Quan Zhang, Yuxin Qi, Xi Tang, Rui Yuan 외

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training…

Action LocalizationDenoisingPseudo LabelTemporal Action Localization+1

A Multimodal Dataset for Enhancing Industrial Task Monitoring and Engagement Prediction

2025-01-10 · Naval Kishore Mehta, Arvind, Himanshu Kumar, Abeer Banerjee 외

Detecting and interpreting operator actions, engagement, and object interactions in dynamic industrial workflows remains a significant challenge in human-robot collaboration research, especially within complex, real-worl…

Action Localization

Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models

2025-01-01 · CVPR 2025 1 · Quan Zhang, Jinwei Fang, Rui Yuan, Xi Tang 외

Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Model…

Action LocalizationTemporal Action LocalizationVideo UnderstandingWeakly-supervised Temporal Action Localization+1

Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport

2025-01-01 · CVPR 2025 1 · Mengnan Liu, Le Wang, Sanping Zhou, Kun Xia 외

Point-supervised Temporal Action Localization poses significant challenges due to the difficulty of identifying complete actions with a single-point annotation per action. Existing methods typically employ Multiple …

Action LocalizationMultiple Instance LearningTemporal Action Localization

DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments

2024-12-28 · Xijun Wang, Pedro Sandoval-Segura, ChengYuan Zhang, Junyun Huang 외

Most existing traffic video datasets including Waymo are structured, focusing predominantly on Western traffic, which hinders global applicability. Specifically, most Asian scenarios are far more complex, involving numer…

Action LocalizationAction RecognitionMoment RetrievalTemporal Action Localization+1

Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization

2024-12-27 · Yuanpeng He, Lijian Li, Tianxiang Zhan, Wenpin Jiao 외

Weakly supervised temporal action localization (WS-TAL) is a task of targeting at localizing complete action instances and categorizing them with video-level labels. Action-background ambiguity, primarily caused by backg…

Action LocalizationOptical Flow EstimationTemporal Action LocalizationWeakly-supervised Temporal Action Localization

Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos

2024-12-19 · Haitao Tian, Pierre Payeur

Existing skeleton-based human action classification models rely on well-trimmed action-specific skeleton videos for both training and testing, precluding their scalability to real-world applications where untrimmed video…

Action ClassificationAction LocalizationAction SegmentationSegmentation+1

Temporal Action Localization with Cross Layer Task Decoupling and Refinement

2024-12-12 · Qiang Li, Di Liu, Jun Kong, Sen Li 외

Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ …

Action ClassificationAction LocalizationTemporal Action Localization
1–20 / 369 다음 →