No abstract

When an attacker wants to falsify an image, in most of cases she/he will perform a JPEG recompression. Different techniques have been developed based on diverse theoretical assumptions but very effective solutions have not been developed yet. Recently, machine learning based approaches have been started to appear in the field of image forensics to solve diverse tasks such as acquisition source identification and forgery detection. In this last case, the aim ahead would be to get a trained neural network able, given a to-be-checked image, to reliably localize the forged areas. With this in mind, our paper proposes a step forward in this direction by analyzing how a single or double JPEG compression can be revealed and localized using convolutional neural networks (CNNs). Different kinds of input to the CNN have been taken into consideration, and various experiments have been carried out trying also to evidence potential issues to be further investigated

Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.

Conditioned and composed image retrieval extend CBIR systems by combining a query image with an additional text that expresses the intent of the user, describing additional requests w.r.t. the visual content of the query image. This type of search is interesting for e-commerce applications, e.g. to develop interactive multimodal searches and chatbots. In this demo, we present an interactive system based on a combiner network, trained using contrastive learning, that combines visual and textual features obtained from the OpenAI CLIP network to address conditioned CBIR. The system can be used to improve e-shop search engines. For example, considering the fashion domain it lets users search for dresses, shirts and toptees using a candidate start image and expressing some visual differences w.r.t. its visual content, e.g. asking to change color, pattern or shape. The proposed network obtains state-of-the-art performance on the FashionIQ dataset and on the more recent CIRR dataset, showing its applicability to the fashion domain for conditioned retrieval, and to more generic content considering the more general task of composed image retrieval.

In this paper we investigate the use of a multimodal feature learning approach, using neural network based models such as Skip-gram and Denoising Autoencoders, to address sentiment analysis of micro-blogging content, such as Twitter short messages, that are composed by a short text and, possibly, an image. The approach used in this work is motivated by the recent advances in: i) training language models based on neural networks that have proved to be extremely efficient when dealing with web-scale text corpora, and have shown very good performances when dealing with syntactic and semantic word similarities; ii) unsupervised learning, with neural networks, of robust visual features, that are recoverable from partial observations that may be due to occlusions or noisy and heavily modified images. We propose a novel architecture that incorporates these neural networks, testing it on several standard Twitter datasets, and showing that the approach is efficient and obtains good classification results.