Copertina

Human-like compositional learning of visually-grounded concepts using synthetic environments

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lin, Zijun, Kumar, M Ganesh, Tan, Cheston
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding
di: Lin, Zijun, et al.
Pubblicazione: (2025)

Bridging the gap to real-world language-grounded visual concept learning
di: Jung, Whie, et al.
Pubblicazione: (2025)

Inferring Past Human Actions in Homes with Abductive Reasoning
di: Tan, Clement, et al.
Pubblicazione: (2022)

STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
di: Agrawal, Palaash, et al.
Pubblicazione: (2023)

Evaluating the Generation of Spatial Relations in Text and Image Generative Models
di: Sim, Shang Hong, et al.
Pubblicazione: (2024)

Stencil: Subject-Driven Generation with Context Guidance
di: Chen, Gordon, et al.
Pubblicazione: (2025)

Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis
di: Nagar, Aishik, et al.
Pubblicazione: (2024)

Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm
di: Shu, Yan, et al.
Pubblicazione: (2023)

Evaluation of image simulation open source solutions for simulation of synthetic images in lunar environment
di: Singla, Jai G, et al.
Pubblicazione: (2026)

A workflow for generating synthetic LiDAR datasets in simulation environments
di: Phadke, Abhishek, et al.
Pubblicazione: (2025)

Weakly supervised training of universal visual concepts for multi-domain semantic segmentation
di: Bevandić, Petra, et al.
Pubblicazione: (2022)

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
di: Jaiswal, Shantanu, et al.
Pubblicazione: (2024)

Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
di: Rawal, Ishaan Singh, et al.
Pubblicazione: (2023)

HVIS: A Human-like Vision and Inference System for Human Motion Prediction
di: Lyu, Kedi, et al.
Pubblicazione: (2025)

Probabilistic road classification in historical maps using synthetic data and deep learning
di: Mühlematter, Dominik J., et al.
Pubblicazione: (2024)

Training point-based deep learning networks for forest segmentation with synthetic data
di: Capua, Francisco Raverta, et al.
Pubblicazione: (2024)

Training deep learning based dynamic MR image reconstruction using synthetic fractals
di: Raman, Anirudh, et al.
Pubblicazione: (2026)

Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
di: Niehorster, Diederick C., et al.
Pubblicazione: (2026)

The effects of using created synthetic images in computer vision training
di: Smutny, John W.
Pubblicazione: (2025)

Deep learning assisted high resolution microscopy image processing for phase segmentation in functional composite materials
di: Raghavendran, Ganesh, et al.
Pubblicazione: (2024)

Audio-visual training for improved grounding in video-text LLMs
di: Sagare, Shivprasad, et al.
Pubblicazione: (2024)

SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images
di: Dhakara, Pushpendra, et al.
Pubblicazione: (2025)

Precise localization of corneal reflections in eye images using deep learning trained on synthetic data
di: Byrne, Sean Anthony, et al.
Pubblicazione: (2023)

Sparse autoencoders reveal selective remapping of visual concepts during adaptation
di: Lim, Hyesu, et al.
Pubblicazione: (2024)

PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
di: Assouel, Rim, et al.
Pubblicazione: (2026)

PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos
di: Zhang, Yufei, et al.
Pubblicazione: (2024)

Beyond Motion Pattern: An Empirical Study of Physical Forces for Human Motion Understanding
di: Dao, Anh, et al.
Pubblicazione: (2025)

Do MLLMs Exhibit Human-like Perceptual Behaviors? HVSBench: A Benchmark for MLLM Alignment with Human Perceptual Behavior
di: Lin, Jiaying, et al.
Pubblicazione: (2024)

MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
di: Chen, Yanyuan, et al.
Pubblicazione: (2025)

Exploring learning environments for label\-efficient cancer diagnosis
di: Rani, Samta, et al.
Pubblicazione: (2024)

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
di: Shin, Soyong, et al.
Pubblicazione: (2023)

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
di: Park, Yonghyun, et al.
Pubblicazione: (2025)

SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
di: Yan, Hongyu, et al.
Pubblicazione: (2025)

Self-supervised visual learning in the low-data regime: a comparative evaluation
di: Konstantakos, Sotirios, et al.
Pubblicazione: (2024)

Affine transformation estimation improves visual self-supervised learning
di: Torpey, David, et al.
Pubblicazione: (2024)

rareboost3d: a synthetic lidar dataset with enhanced rare classes
di: Lin, Shutong, et al.
Pubblicazione: (2025)

Impact of color and mixing proportion of synthetic point clouds on semantic segmentation
di: Zhou, Shaojie, et al.
Pubblicazione: (2024)

Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation
di: Zhang, Jinchang, et al.
Pubblicazione: (2025)

Temporal evolution in synthetic handwriting
di: Carmona-Duarte, Cristina, et al.
Pubblicazione: (2024)

Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy images
di: Ruano, Josué, et al.
Pubblicazione: (2023)