Papers Action Segmentation
“Action Segmentation” 태그가 달린 논문 263편 · 필터 해제
Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding
Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this paper, we propose MoSaiC, a novel Motion-Saliency Complementary masked modeling framework for self-supervised point cloud v…
Representation LearningSemantic SegmentationScene UnderstandingAction SegmentationOpen-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable t…
Action SegmentationAdaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation
Dataset condensation for action segmentation synthesizes compact, informative representations of long, untrimmed video datasets. The existing approach relies on Variational Autoencoders and an iterative latent optimizati…
Action SegmentationP-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture
The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale l…
Representation LearningAction ClassificationAction SegmentationThe Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection
Procedural mistake detection is important for quality control and user assistance across many disciplines. Recent work in this field has achieved significant gains by using the reasoning capabilities of Video-Language Mo…
Action SegmentationUNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning
Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action. We argue that a …
Representation LearningAction SegmentationAction RecognitionVideo RetrievalUncertainty-Aware Intention Prediction for Human-to-Robot Assembly Teleoperation
In assisted teleoperation for human-robot collaboration, accurate intention prediction is critical for enabling timely and reliable robotic assistance during long-horizon manipulation and assembly tasks. These systems re…
Action SegmentationAction RecognitionTransfer LearningPolyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand …
Action SegmentationEgo-METAS: Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark
To operate in the physical world, embodied agents must perceive their environment in an "always-on" fashion, selectively accessing the most informative sensors to balance energy constraints and task accuracy. Despite its…
Action SegmentationFlat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly
The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, cla…
Action SegmentationEgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
Collecting large-scale egocentric video datasets with dense spatial and temporal annotations is costly, slow, and often constrained by environmental biases, privacy constraints, and limited coverage of interaction patter…
Active Object DetectionAction SegmentationVideo GenerationImproving Temporal Action Segmentation via Constraint-Aware Decoding
Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high anno…
Action SegmentationProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation
Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajecto…
Action SegmentationDiffusion Masked Pretraining for Dynamic Point Cloud
Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth tube centers as decoder positional embed…
Action SegmentationPoint CloudsIMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limit…
Action UnderstandingAction SegmentationSASI: Leveraging Sub-Action Semantics for Robust Early Action Recognition in Human-Robot Interaction
Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactive feedback, robots must recognize human actions as early as possible…
Action SegmentationAction RecognitionHOI-aware Adaptive Network for Weakly-supervised Action Segmentation
In this paper, we propose an HOI-aware adaptive network named AdaAct for weakly-supervised action segmentation. Most existing methods learn a fixed network to predict the action of each frame with the neighboring frames.…
Action SegmentationATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation
Annotating long-horizon robotic demonstrations with precise temporal action boundaries is crucial for training and evaluating action segmentation and manipulation policy learning methods. Existing annotation tools, howev…
Reinforcement LearningAction SegmentationUnderstanding Human Actions through the Lens of Executable Models
Human-centred systems require an understanding of human actions in the physical world. Temporally extended sequences of actions are intentional and structured, yet existing methods for recognising what actions are perfor…
Action SegmentationAnomaly DetectionBoundary-Centric Clip-Budgeted Active Learning for Temporal Action Segmentation
Temporal action segmentation (TAS) in untrimmed videos requires dense temporal supervision. However, most of the annotation cost is spent identifying action transitions where segmentation errors concentrate and small tem…
Action SegmentationActive Learning