Semantic Attribute Matching Networks

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training data through weakly ...

Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes traditional eva ...

Robustness of medical image classification models is limited by its exposure to the candidate disease classes. Generalized zero shot learning (GZSL) aims at correctly predicting seen and unseen classes and most current GZSL approaches have focused on the s ...

With ever greater computational resources and more accessible software, deep neural networks have become ubiquitous across industry and academia. Their remarkable ability to generalize to new samples defies the conventional view, which holds that complex, ...

By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions generate near-ph ...

Information diffusion is usually modeled as a process in which immutable pieces of information propagate over a network. In reality, however, messages are not immutable, but may be morphed with every step, potentially entailing large cumulative distortions ...

Conceptual models such as database schemas, ontologies or process models have been established as a means for effective engineering of information systems. Yet, for complex systems, conceptual models are created by a variety of stakeholders, which calls fo ...

A two-platform measurement system for realizing airborne thermography of the Lake Surface Water Temperature (LSWT) with ~0.8 m pixel resolution (sub-pixel satellite scale) is presented. It consists of a tethered Balloon Launched Imaging and Monitoring Plat ...

With the increasing complexity of engineered systems, digital twins (DTs) have been widely used to support integrated modeling, simulation, and decision-making of the system of systems (SoS). However, when integrating DTs of each constituent system, it is ...

Algorithms are everywhere. The recipe for the frangipane cake is an algorithm. If all the listed ingredients are available and the cook is sufficiently deft, after a finite number of small, well-defined steps a delicious dessert will exit the oven. Now, wh ...

Attribute-based representations help machine learning models perform tasks based on human understandable concepts, allowing a closer human-machine collaboration. However, learning attributes that accurately reflect the content of an image is not always str ...

Systems modelling and simulation are two important facets for thoroughly and effectively analysing manufacturing processes. The ever-growing complexity of the latter, the increasing amount of knowledge, and the use of Semantic Web techniques adhering meani ...

The objective of this study was to evaluate the effect of Motor Imagery (MI) training on language comprehension. In line with literature suggesting an intimate relationship between the language and the motor system, we proposed that a MI-training could imp ...

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space ...

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance. However, it is also very challenging without absolute scale information. Here, we examine the rarely addressed case, where camer ...

We present a deep architecture and learning framework for establishing correspondences across cross-spectral visible and infrared images in an unpaired setting. To overcome the unpaired cross-spectral data problem, we design the unified image translation a ...

This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to ...

In the present information era, a huge amount of machine-readable data is available regarding scientific publications. Such unprecedented wealth of data offers the opportunity to investigate science itself as a complex interacting system by means of quanti ...

We address the challenge of learning factored policies in cooperative MARL scenarios. In particular, we consider the situation in which a team of agents collaborates to optimize a common cost. The goal is to obtain factored policies that determine the indi ...

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent ...

Semantic Attribute Matching Networks

Chat with Graph Search

Joint Learning of Semantic Alignment and Object Landmark Detection

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

Class Specific Feature Disentanglement and Text Embeddings for Multi-label Generalized Zero Shot CXR Classification

Evaluating and Interpreting Deep Convolutional Neural Networks via Non-negative Matrix Factorization

SROBB: Targeted Perceptual Loss for Single Image Super-Resolution

Message Distortion in Information Cascades

Reconciling Matching Networks of Conceptual Models

Achieving high-resolution thermal imagery in low-contrast lake surface waters by aerial remote sensing and image registration

Cognitive twin construction for system of systems operation based on semantic integration and high-level architecture

Practical Byzantine-resilient Stochastic Gradient Descent

Attribute Prediction as Multiple Instance Learning

Towards semantics-driven modelling and simulation of context-aware manufacturing systems

Kinesthetic motor-imagery training improves performance on lexical-semantic access

Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

What Face and Body Shapes Can Tell Us About Height

Learning to Find Unpaired Cross-Spectral Correspondences

Network Classifiers Based On Social Learning

Unleashing the power of semantic text analysis: a complex systems approach

Logical Team Q-learning: An approach towards factored policies in cooperative MARL

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval