Papers Temporal Action Localization
“Temporal Action Localization” 태그가 달린 논문 1,503편 · 필터 해제
Density-Guided Label Smoothing for Temporal Localization of Driving Actions
Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliabi…
Action LocalizationAction RecognitionTemporal Action LocalizationTemporal LocalizationTransformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reli…
2D Human Pose EstimationAction RecognitionPose EstimationTemporal Action Localization+1Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos
The increasing variety and quantity of tagged multimedia content on a variety of online platforms offer a unique opportunity to advance the field of human action recognition. In this study, we utilize 283,582 unique, unl…
Action RecognitionSelf-Supervised LearningTemporal Action LocalizationBoosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation an…
Action Recognitionimage-classificationImage ClassificationTemporal Action LocalizationActive Generation Network of Human Skeleton for Action Recognition
Data generation is a data augmentation technique for enhancing the generalization ability for skeleton-based human action recognition. Most existing data generation methods face challenges to ensure the temporal consiste…
Action GenerationAction RecognitionData AugmentationDiversity+3Cutup and Detect: Human Fall Detection on Cutup Untrimmed Videos Using a Large Foundational Video Understanding Model
This work explores the performance of a large video understanding foundation model on the downstream task of human fall detection on untrimmed video and leverages a pretrained vision transformer for multi-class action de…
Action DetectionAction LocalizationTemporal Action LocalizationVideo UnderstandingM2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevert…
Action RecognitionDecoderTemporal Action LocalizationAdversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shifts between training and test data. We p…
Action RecognitionSchedulingTemporal Action LocalizationVideo PredictionRealigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization
Point-level weakly-supervised temporal action localization (P-TAL) aims to localize action instances in untrimmed videos through the use of single-point annotations in each instance. Existing methods predict the clas…
Action LocalizationTemporal Action LocalizationWeakly-supervised Temporal Action LocalizationPeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
Recent progress in Vision-Language (VL) foundation models has revealed the great advantages of cross-modality learning. However due to a large gap between vision and text they might not be able to sufficiently utiliz…
Action RecognitionContrastive LearningLanguage ModelingLanguage Modelling+1Just Add ?! Pose Induced Video Transformers for Understanding Activities of Daily Living
Video transformers have become the de facto standard for human action recognition yet their exclusive reliance on the RGB modality still limits their adoption in certain domains. One such domain is Activities of Dail…
Action RecognitionTemporal Action LocalizationA Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point
Re-identifying participants in ultra-distance running competitions can be daunting due to the extensive distances and constantly changing terrain. To overcome these challenges, computer vision techniques have been develo…
Action RecognitionGait RecognitionTemporal Action LocalizationA Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities
The vulnerability of RGB-based human action recognition in complex environment and variational scenes can be compensated by skeleton modality. Therefore, action recognition methods fusing RGB and skeleton modalities have…
Action RecognitionAction Recognition In VideosSkeleton Based Action RecognitionTemporal Action LocalizationClassifying Soccer Ball-on-Goal Position Through Kicker Shooting Action
This research addresses whether the ball's direction after a soccer free-kick can be accurately predicted solely by observing the shooter's kicking technique. To investigate this, we meticulously curated a dataset of soc…
Action RecognitionPositionTemporal Action LocalizationSpatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition
Skeleton-based action recognition is a central task in human-computer interaction. However, most previous methods suffer from two issues: (i) semantic ambiguity arising from spatial-temporal information mixture; and (ii)…
Action RecognitionContrastive LearningSkeleton Based Action RecognitionTemporal Action LocalizationRevisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
Weakly-supervised temporal action localization aims to localize action instances in videos with only video-level action labels. Existing methods mainly embrace a localization-by-classification pipeline that optimizes the…
Action LocalizationClassificationClusteringTemporal Action Localization+3SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, …
Action DetectionAction LocalizationDomain AdaptationTemporal Action Localization+1Generative Model-based Feature Knowledge Distillation for Action Recognition
Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tas…
Action DetectionAction RecognitionKnowledge DistillationModel Compression+2Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables
This paper proposes a framework that combines online human state estimation, action recognition and motion prediction to enable early assessment and prevention of worker biomechanical risk during lifting tasks. The frame…
Action RecognitionMixture-of-Expertsmotion predictionState Estimation+1EZ-CLIP: Efficient Zeroshot Video Action Recognition
Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks. Building on this success, efforts have bee…
Action RecognitionGPUTemporal Action LocalizationVisual Prompting+2