mesnico
Researcher at ISTI-CNR, Pisa, Italy. I'm interested in the secrets of intelligence and I'm passionate about Computer Vision and Deep Learning.
Pisa, Italy
Pinned Repositories
ALADIN
Official implementation of the paper "ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval"
attentive_video_crowd_counting
Code for reproducing the results for the paper "A Spatio-Temporal Attentive Network for Video-Based Crowd Counting"
learning-relationship-aware-visual-features
Relational Content-Based Image Retrieval (R-CBIR) - Retrieving images with given relationships among objects
MemePersuasionDetection
Deep learning methods for detecting persuasion techniques in memes
RelationNetworks-CLEVR
A pytorch implementation for "A simple neural network module for relational reasoning", working on the CLEVR dataset
TERAN
Code and Resources for the Transformer Encoder Reasoning and Alignment Network (TERAN), accepted for publication in ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
TERN
Code and Resources for the Transformer Encoder Reasoning Network (TERN) - https://arxiv.org/abs/2004.09144
text-to-motion-retrieval
Official code for reproducing results obtained in the short paper "Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language", accepted at SIGIR 2023.
WifiIndoorLocation
Android application that localizes people in indoor environments, using wifi fingerprinting methods
Wiki-Image-Caption-Matching
mesnico's Repositories
mesnico/RelationNetworks-CLEVR
A pytorch implementation for "A simple neural network module for relational reasoning", working on the CLEVR dataset
mesnico/TERAN
Code and Resources for the Transformer Encoder Reasoning and Alignment Network (TERAN), accepted for publication in ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
mesnico/TERN
Code and Resources for the Transformer Encoder Reasoning Network (TERN) - https://arxiv.org/abs/2004.09144
mesnico/text-to-motion-retrieval
Official code for reproducing results obtained in the short paper "Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language", accepted at SIGIR 2023.
mesnico/ALADIN
Official implementation of the paper "ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval"
mesnico/learning-relationship-aware-visual-features
Relational Content-Based Image Retrieval (R-CBIR) - Retrieving images with given relationships among objects
mesnico/WifiIndoorLocation
Android application that localizes people in indoor environments, using wifi fingerprinting methods
mesnico/Wiki-Image-Caption-Matching
mesnico/MemePersuasionDetection
Deep learning methods for detecting persuasion techniques in memes
mesnico/attentive_video_crowd_counting
Code for reproducing the results for the paper "A Spatio-Temporal Attentive Network for Video-Based Crowd Counting"
mesnico/VBS22-KIS-Analysis
mesnico/ai4eu-text-to-visual-search
Code for building the Text to Visual search component for use in Acumos. It is compliant with the AI4EU specifications.
mesnico/Akka-File-Sharing
File sharing distributed application developed with Akka Framework
mesnico/DTfH-Laboratory
Colab notebooks for experimenting with the techniques explained at the course "Deep Learning tools for image classification and retrieval" of the Digital Tools for Humanists summer school
mesnico/faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn
mesnico/food-recognition-MIM
Similarity search index and knn classifier for food searching and recognition. Implemented with Transfer Learning using Deep Features.
mesnico/graph-rcnn.pytorch
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers
mesnico/monet
An implementation of the MONet model for unsupervised scene decomposition in PyTorch
mesnico/networkx
Official NetworkX source code repository.
mesnico/pyskl
A toolbox for skeleton-based action recognition.
mesnico/pytorch-retinanet
Pytorch implementation of RetinaNet object detection.
mesnico/recurrent_vision_transformer_visual_reasoning
Code for reproducing the results from our paper "Recurrent Vision Transformer for Solving Visual Reasoning Problems", accepted at ICIAP 2021
mesnico/scene_graph_benchmark
image scene graph generation benchmark
mesnico/str-encoders
Surrogate Text Representation Encoders for Real Vectors
mesnico/tag_my_outfit_pipeline
mesnico/vsepp
PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"
mesnico/clip-vip_video_search
showing how to use CLIP-Vip to do video search
mesnico/ray
A high-performance distributed execution engine