Skip to content
@aimagelab

AImageLab

AImageLab is a research laboratory of the Dipartimento di Ingegneria "Enzo Ferrari" at the University of Modena and Reggio Emilia, Italy.

Popular repositories Loading

  1. mammoth mammoth Public

    An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

    Python 838 157

  2. dress-code dress-code Public

    Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022

    Python 660 81

  3. meshed-memory-transformer meshed-memory-transformer Public

    [CVPR 2020] Meshed-Memory Transformer for Image Captioning

    Python 545 134

  4. multimodal-garment-designer multimodal-garment-designer Public

    [ICCV 2023] This is the official repository for the paper "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing"

    Python 444 52

  5. show-control-and-tell show-control-and-tell Public

    [CVPR 2019] Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions

    Python 281 61

  6. novelty-detection novelty-detection Public

    Latent space autoregression for novelty detection.

    Python 200 57

Repositories

Showing 10 of 118 repositories
  • Dress-ED Public

    [ECCV 2026 Spotlight] "Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off"

    aimagelab/Dress-ED's past year of commit activity
    HTML 14 0 1 0 Updated Sep 9, 2026
  • spark Public

    Official implementation of "SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-Resolution"

    aimagelab/spark's past year of commit activity
    Python 3 Apache-2.0 0 0 0 Updated Sep 4, 2026
  • DocAttriBench Public

    [BMVC 2026] DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering

    aimagelab/DocAttriBench's past year of commit activity
    Python 3 0 0 0 Updated Sep 4, 2026
  • CounterVid Public

    [EMNLP 2026] Official implementation of CounterVid, a counterfactual video generation framework for mitigating action and temporal hallucinations in video-language models.

    aimagelab/CounterVid's past year of commit activity
    4 0 0 0 Updated Aug 28, 2026
  • ShieldCLIP Public

    Official repository for ShieldCLIP: selective safety alignment for harmful content mitigation in multimodal foundation models. Code, trained models, and dataset access instructions coming soon.

    aimagelab/ShieldCLIP's past year of commit activity
    2 0 0 0 Updated Aug 24, 2026
  • GramSR Public

    Official implementation of "GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution"

    aimagelab/GramSR's past year of commit activity
    Python 10 1 1 0 Updated Aug 12, 2026
  • LoT Public

    Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering

    aimagelab/LoT's past year of commit activity
    HTML 4 0 0 1 Updated Aug 7, 2026
  • ReAG Public

    [CVPR 2026 Highlight] ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

    aimagelab/ReAG's past year of commit activity
    Python 29 0 2 0 Updated Jul 13, 2026
  • fed-mammoth Public

    General Federated Continual Learning Framework

    aimagelab/fed-mammoth's past year of commit activity
    Python 21 MIT 3 1 0 Updated Jul 11, 2026
  • HyperMIL Public

    [ICPR 2026] HyperMIL: Hypergraph-based channel reasoning for Multiple Instance Learning on Multivariate Time Series

    aimagelab/HyperMIL's past year of commit activity
    Python 1 0 0 0 Updated Jul 1, 2026
View all repositories