Search Results for author:
Found 26 papers, 13 papers with code
Are all training examples equally valuable?
When learning a new concept, not all training examples may prove equally useful for training: some may have higher or lower training value than others.
Learning Deep Features for Scene Recognition using Places Database
Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CNNs) for learning high-level features, performance at scene recognition has not attained the same level of success.
Object Detectors Emerge in Deep Scene CNNs
With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e. g., ImageNet, Places), the state of the art in computer vision is advancing rapidly.
Speeding Up Neural Networks for Large Scale Classification using WTA Hashing
In this paper we propose to use the Winner Takes All hashing technique to speed up forward propagation and backward propagation in fully connected layers in convolutional neural networks.
Learning Deep Features for Discriminative Localization
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
Places: An Image Database for Deep Scene Understanding
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification at tasks such as object and scene recognition.
Emotion Recognition in Context
In this paper we present the Emotions in Context Database (EMCO), a dataset of images containing people in context in non-controlled environments.
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
To investigate the strengths of this novel metric and interactive evaluation in comparison to state-of-the-art metrics and human evaluation of static conversations, we perform extended experiments with a set of models, including several that make novel improvements to recent hierarchical dialog generation architectures through sentiment and semantic knowledge distillation on the utterance level.
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment.
Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog
This is a critical shortcoming for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e. g. systems that learn from human interaction.
Context Based Emotion Recognition using EMOTIC Dataset
In this paper we present EMOTIC, a dataset of images of people in a diverse set of natural situations, annotated with their apparent emotion.
Ranked #4 on
Emotion Recognition in Context
on EMOTIC
(using extra training data)
Detecting natural disasters, damage, and incidents in the wild
While most studies on social media are limited to text, images offer more information for understanding disaster and incident scenes.
Understanding the Role of Individual Units in a Deep Neural Network
Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.
Learning Emotional-Blinded Face Representations
We propose two face representations that are blind to facial expressions associated to emotional responses.
Human-centric Dialog Training via Offline Reinforcement Learning
We start by hosting models online, and gather human feedback from real-time, open-ended conversations, which we then use to train and improve the models using offline reinforcement learning (RL).
Facial Expressions as a Vulnerability in Face Recognition
This work explores facial expression bias as a security vulnerability of face recognition systems.
Person Perception Biases Exposed: Revisiting the First Impressions Dataset
This work revisits the ChaLearn First Impressions database, annotated for personality perception using pairwise comparisons via crowdsourcing.
Recognizing Emotions evoked by Movies using Multitask Learning
In this paper, we model the emotions evoked by videos in a different manner: instead of modeling the aggregated value we jointly model the emotions experienced by each viewer and the aggregated value using a multi-task learning approach.
Interpreting Face Inference Models using Hierarchical Network Dissection
Our pipeline is inspired by Network Dissection, a popular interpretability model for object-centric and scene-centric models.
Predicting Driver Self-Reported Stress by Analyzing the Road Scene
Several studies have shown the relevance of biosignals in driver stress recognition.
Explainable, automated urban interventions to improve pedestrian and vehicle safety
At the moment, urban mobility research and governmental initiatives are mostly focused on motor-related issues, e. g. the problems of congestion and pollution.
Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents
In this work, we present the Incidents1M Dataset, a large-scale multi-label dataset which contains 977, 088 images, with 43 incident and 49 place categories.
Predicting the impact of urban change in pedestrian and road safety
In this paper, by considering historical accident data and Street View images, we detail how to automatically predict the impact (increase or decrease) of urban interventions on accident incidence.
Local Relighting of Real Scenes
We introduce the task of local relighting, which changes a photograph of a scene by switching on and off the light sources that are visible within the image.
On the use of Vision-Language models for Visual Sentiment Analysis: a study on CLIP
First, we test on WEBEmo and compare the CLIP-E architectures with state-of-the-art (SOTA) models and with CLIP Zero-Shot.
Analyzing the contribution of different passively collected data to predict Stress and Depression
In this paper, we analyze the contribution of different passively collected sensor data types (WiFi, GPS, Social interaction, Phone Log, Physical Activity, Audio, and Academic features) to predict daily selfreport stress and PHQ-9 depression score.
