paper-with-me

Action Understanding

1개 벤치마크 · 논문 141편 · 이 태스크의 논문 보기 →

Benchmarks

Most implemented

Papers

MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching

2026-08-26 · Hao Yin, Paritosh Parmar, Lijun Gu, Lin Xu 외 arxiv

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic pat…

Action Quality AssessmentAction Understanding

Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding

2026-08-21 · Fengshun Wang, Jin'ang Han, Zhigang Tu arxiv

Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little conscious intent yet that reliably leak emotional and psychological state. Un…

Action Understanding

G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding

2026-08-20 · Marko Haralović, Akash Ramakrishnan, Estefania Talavera Martinez arxiv

Egocentric action understanding is often addressed using large video models pretrained on extensive exocentric datasets. However, many first-person actions depend on a small number of hand-object interactions involving o…

Action UnderstandingAction Recognition

Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos

2026-07-12 · Hao Zheng, Jinyi Huang, Tiantian Zheng, Xun Xu 외 arxiv

Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models…

Hyperparameter OptimizationAction UnderstandingMulti-Task LearningAction Recognition

Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach

2026-07-01 · Yingjie Dai, Tianyang Xu, Yanglin Deng, Xiao-Jun Wu 외 arxiv

Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In rea…

Action UnderstandingAction Recognition

Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding

2026-06-21 · Haodi Liu, Xinhang Yang, Kunda Yan, Sen Cui 외 arxiv

Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occupy only small regions, a capability unmet by current systems. While …

Action UnderstandingMultimodal ReasoningAction RecognitionVisual Reasoning

전체 141편 보기 →