[ICCV 2025] - Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

FRED: The Florence RGB-Event Drone Dataset

Machine learning metrics for distributed, scalable PyTorch applications.

[ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".

[CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

[TMM-2024] Official Pytorch implementation of "Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics".

[NeurIPS '24] Frustratingly easy Test-Time Adaptation of VLMs!!

Large Language Models for Anomaly and Out-of-Distribution Detection

The Most Comprehensive Survey of Video Quality Assessment to Date.

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

[WACV 2025] - EmoVOCA: Speech-Driven Emotional 3D Talking Heads

[COG24] - Official repository of "OfflineMania: A Benchmark Environment for Offline Reinforcement Learning in Racing Games"

List of startups doing AI & ML

Processed / Cleaned Data for Paper Copilot

[BSPC 2024] All-in-one electrical atrial substrate indicators with deep anomaly detection

A unified interface for downloading and loading popular Image Quality Assessment (IQA) datasets.

Writing AI Conference Papers: A Handbook for Beginners

[ECCV 2024] - ScanTalk: 3D Talking Heads from Unregistered Scans

The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

Official Code for Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency

[SIGIR'2024 Best Paper Honorable Mention] Official repository for "LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval"

Collection of Composed Image Retrieval (CIR) papers.

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

[ECCV 2024] BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues.

[ECCV'24] Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models. ECCV 2024

Dataset for Surface Landmine detection. Videos are taken in Italy (Faculty of Engineering, Florence) and USA (Franklyn and Marshal college, Philadelphia).

[ECCV 2024] - Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation