No article text was recorded for this version.
compositional generalization (compositional action representation)
Version 1 of 195 papers125 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compositional action recognition with multi-view feature fusion
- Blog: Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection
- Blog: All About Knowledge Graphs for Actions
- Blog: Opening the Vocabulary of Egocentric Actions
- Blog: Object-Region Video Transformers
- Blog: Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data
- Blog: Align Before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
- Blog: Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
- Blog: Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
- Blog: Something-Else: Compositional Action Recognition With Spatial-Temporal Interaction Networks
- Blog: Hierarchical Compositional Representations for Few-shot Action Recognition
- Blog: Opening the Vocabulary of Egocentric Actions
- Blog: Transition-Based Syntactic Linearization with Lookahead Features
- Blog: Generating Videos of Zero-Shot Compositions of Actions and Objects
- Blog: Cross-task weakly supervised learning from instructional videos
- Blog: LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities
- Blog: Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs
- Blog: HAKE: A Knowledge Engine Foundation for Human Activity Understanding
- Blog: Toward Open-Set Human Object Interaction Detection
- Blog: Home Action Genome: Cooperative Compositional Action Understanding
- Blog: Video Action Recognition with Attentive Semantic Units
- Blog: An Analysis of Action Recognition Datasets for Language and Vision Tasks
- Blog: Neural Task Planning with And-Or Graph Representations
- Blog: Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos
- Blog: Cross-Task Weakly Supervised Learning From Instructional Videos
- Blog: HAKE: Human Activity Knowledge Engine
- Blog: Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning
- Blog: MOMA: Multi-Object Multi-Actor Activity Parsing
- Blog: Pseudo Siamese Network for Few-shot Intent Generation
- Blog: Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space
- Blog: Compositional Learning for Human Object Interaction
- Blog: Static and Dynamic Concepts for Self-supervised Video Representation Learning
- Blog: Graph Embedded Pose Clustering for Anomaly Detection
- Blog: Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
- Blog: Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
- Blog: Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games
- Blog: Temporal Action Segmentation with High-level Complex Activity Labels
- Blog: LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
- Blog: Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
- Blog: Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
- Blog: PaStaNet: Toward Human Activity Knowledge Engine
- Blog: How Much Does Audio Matter to Recognize Egocentric Object Interactions?
- Blog: Compositional Video Synthesis with Action Graphs
- Blog: ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries
- Blog: HICO: A Benchmark for Recognizing Human-Object Interactions in Images
- Blog: EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning
- Blog: Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
- Blog: Towards Holistic Surgical Scene Understanding
- Blog: MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning
- Blog: Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
- Blog: Generalizable and Explainable Dialogue Generation via Explicit Action Learning
- Blog: Learning Planning Abstractions from Language
- Blog: ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
- Blog: Few-Shot Video Classification via Representation Fusion and Promotion Learning
- Blog: EgoPrompt: Prompt Learning for Egocentric Action Recognition
- Blog: Revisiting spatio-temporal layouts for compositional action recognition
- Blog: Action Unit Memory Network for Weakly Supervised Temporal Action Localization
- Blog: Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data
- Blog: Knowledge Prompting for Few-shot Action Recognition
- Blog: Disentangled Action Recognition with Knowledge Bases
Showing 60 of 95 papers.
History & citation
Current · Permanent link
- Decoupling Action and Object for Compositional Generalization merged into this direction (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_compositional_generalization_composition_6ca259e5,
title = {compositional generalization (compositional action representation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compositional-generalization-compositional-action-representation/rdr_6ca259e5164f42c49eb8c4b3acb276e8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_compositional_generalization_composition_6ca259e5_v1,
title = {compositional generalization (compositional action representation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compositional-generalization-compositional-action-representation/rdr_6ca259e5164f42c49eb8c4b3acb276e8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}