Publications associées à Vivisection

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Alexandre Massoud Alahi, Yuejiang Liu, Parth Ashit Kothari, Danya Li

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for efficiently adapting p ...

2022

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

Alexandre Massoud Alahi, Parth Ashit Kothari

Human trajectory forecasting in crowds presents the challenges of modelling social interactions and outputting collision-free multimodal distribution. Following the success of Social Generative Adversarial Networks (SGAN), recent works propose various GAN- ...

IEEE Institute of Electrical and Electronics Engineers2023

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Alexandre Massoud Alahi, Parth Ashit Kothari

Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal distributions. In recent ...

2021

Efficient User Guidance for Validating Participatory Sensing Data

Quoc Viet Hung Nguyen, Thành Tâm Nguyên

Participatory sensing has become a new data collection paradigm that leverages the wisdom of the crowd for big data applications without spending cost to buy dedicated sensors. It collects data from human sensors by using their own devices such as cell pho ...

ASSOC COMPUTING MACHINERY2019

Experimental study of large scale plunging jets

Michael Pfister

The lack of knowledge regarding air entrainment caused by large jets in hydraulic structures, such as downstream Pelton turbines, has led EDF (Electricité de France) to carry out a test series to optimize the La Coche Power plant. The data extracted from t ...

2016

Construction par procédé additif réalisée avec des robots mobiles autonomes hétérogènes

Philippe Rétornaz

This thesis lies at the crossroad of three research fields: heterogenous mobile collective robotics, autonomous construction with mobile robots and 3D printing. The main goal of this work is to implement and study an innovative way to interact and modify t ...

EPFL2015

Tag-based Paper Retrieval: Minimizing User Effort with Diversity Awareness

Karl Aberer, Quoc Viet Hung Nguyen, Thành Tâm Nguyên, Son Thanh Do

As the number of scientific papers getting published is likely to soar, most of modern paper management systems (e.g. ScienceWise, Mendeley, CiteULike) support tag-based retrieval. In that, each paper is associated with a set of \emph{tags}, allowing user ...

2015

Towards Enabling Probabilistic Databases for Participatory Sensing

Karl Aberer, Quoc Viet Hung Nguyen, Chi Thang Duong, Saket Sathe

Participatory sensing has emerged as a new data collection paradigm, in which humans use their own devices (cell phone accelerometers, cameras, etc.) as sensors. This paradigm enables to collect a huge amount of data from the crowd for world-wide applicati ...

2014

Fast Object Detection with Entropy-Driven Evaluation

Pascal Fua, François Fleuret, Raphael Sznitman, Carlos Joaquin Becker

Cascade-style approaches to implementing ensemble classifiers can deliver significant speed-ups at test time. While highly effective, they remain challenging to tune and their overall performance depends on the availability of large validation sets to esti ...

2013

Compressive Source Separation: Theory and Methods for Hyperspectral Imaging

Pierre Vandergheynst, Mohammad Golbabaee

With the development of numbers of high resolution data acquisition systems and the global requirement to lower the energy consumption, the development of efficient sensing techniques becomes critical. Recently, Compressed Sampling (CS) techniques, which e ...

Institute of Electrical and Electronics Engineers2013